{"object":"list","data":[{"id":"meganova-ai/manta-mini-1.0","name":"Manta-Mini-1.0","tags":["text_generation","best_role_play","free","Manta"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"created":1762544265,"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Lightweight tier optimized for speed and cost. (Free)","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":null},"canonical_slug":"meganova-ai/manta-mini-1.0","context_length":8192,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova"},{"id":"meganova-ai/manta-flash-1.0","name":"Manta-Flash-1.0","tags":["text_generation","best_role_play","free","Manta"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"created":1762544265,"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Balanced tier for general-purpose roleplay, good tradeoff between cost and latency. (Mid-tier)","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":16384,"max_completion_tokens":null},"canonical_slug":"meganova-ai/manta-flash-1.0","context_length":16384,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova"},{"id":"meganova-ai/manta-pro-1.0","name":"Manta-Pro-1.0","tags":["text_generation","best_role_play","free","Manta"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"created":1762544265,"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Premium tier with advanced reasoning and long context, best for complex roleplay.(Top-tier)","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":null},"canonical_slug":"meganova-ai/manta-pro-1.0","context_length":65536,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova"},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3-235B-A22B-Instruct-2507","tags":["text_generation","recently_added","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0900","request":"0.00","completion":"0.1000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A 235B-parameter MoE instruction-tuned language model for general, multilingual, and coding tasks","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3-235B-A22B-Instruct-2507","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi-K2-Thinking","tags":["text_generation","Kimi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.6000","request":"0.00","completion":"2.6000","web_search":"0.00","internal_reasoning":"0.00"},"description":"1T-parameter reasoning-focused language model designed for complex, multi-step problem solving and tool use","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"moonshotai/Kimi-K2-Thinking","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"zai-org/GLM-4.6","name":"GLM-4.6","tags":["text_generation","recently_added","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.4500","request":"0.00","completion":"1.9000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Flagship model from Z.ai with 200K token context, superior reasoning, advanced tool use, and coding excellence","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-4.6","context_length":202752,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"openai/gpt-4o-mini","name":"GPT-4o-mini","tags":["multimodal","text_generation","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1200","request":"0.00","completion":"0.4800","web_search":"0.00","internal_reasoning":"0.00"},"description":"Compact GPT-4 Omni, supports text & image inputs","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-4o-mini","context_length":128000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"gemini/gemini-2.5-pro","name":"Gemini-2.5-Pro","tags":["multimodal","text_generation","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.0000","request":"0.00","completion":"8.0000","web_search":"0.00","input_cache_read":"0.1250","internal_reasoning":"0.00"},"description":"Strongest Gemini, 1M context, great for code & knowledge","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-2.5-pro","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"gemini/gemini-2.5-flash","name":"Gemini-2.5-Flash","tags":["multimodal","text_generation","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2400","request":"0.00","completion":"2.0000","web_search":"0.00","input_cache_read":"0.0300","internal_reasoning":"0.00"},"description":"Fast reasoning with improved latency & accuracy","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-2.5-flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"gemini/gemini-2.5-flash-lite","name":"Gemini-2.5-Flash-Lite","tags":["multimodal","text_generation","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0800","request":"0.00","completion":"0.3200","web_search":"0.00","input_cache_read":"0.0100","internal_reasoning":"0.00"},"description":"Ultra-low latency Gemini variant","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-2.5-flash-lite","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"TheDrummer/Cydonia-24B-v4.1","name":"Cydonia-24B-v4.1","tags":["text_generation","best_role_play","recently_added","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.3000","request":"0.00","completion":"0.5000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A 24B-parameter uncensored instruction-tuned model focused on creative writing with strong recall and prompt adherence","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":null},"canonical_slug":"TheDrummer/Cydonia-24B-v4.1","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Sao10K/L3.3-70B-Euryale-v2.3","name":"L3.3-70B-Euryale-v2.3","tags":["text_generation","best_role_play","recently_added","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.8500","request":"0.00","completion":"0.8500","web_search":"0.00","internal_reasoning":"0.00"},"description":"70B model focused on creative roleplay from Sao10k","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":null},"canonical_slug":"Sao10K/L3.3-70B-Euryale-v2.3","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Sao10K/L3.1-70B-Euryale-v2.2","name":"L3.1-70B-Euryale-v2.2","tags":["text_generation","best_role_play","recently_added","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.8500","request":"0.00","completion":"0.8500","web_search":"0.00","internal_reasoning":"0.00"},"description":"70B model focused on creative roleplay from Sao10k","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":null},"canonical_slug":"Sao10K/L3.1-70B-Euryale-v2.2","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"BruhzWater/Sapphira-L3.3-70b-0.1","name":"Sapphira-L3.3-70B-0.1","tags":["text_generation","best_role_play","recently_added","free","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"70B parameter language model optimized for storytelling, dialogue, and immersive role-play","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":null},"canonical_slug":"BruhzWater/Sapphira-L3.3-70b-0.1","context_length":65536,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"FallenMerick/MN-Violet-Lotus-12B","name":"MN-Violet-Lotus-12B","tags":["text_generation","best_role_play","recently_added","free","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"12B parameter model for creative, emotionally intelligent conversations","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":null},"canonical_slug":"FallenMerick/MN-Violet-Lotus-12B","context_length":65536,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Steelskull/L3.3-MS-Nevoria-70b","name":"L3.3-MS-Nevoria-70B","tags":["text_generation","best_role_play","recently_added","free","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"70B narrative generation, LoRA tuning & story-rich outputs","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":null},"canonical_slug":"Steelskull/L3.3-MS-Nevoria-70b","context_length":65536,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral-Small-3.2-24B-Instruct-2506","tags":["text_generation","free","Mistral"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"24B instruction model, long context, fewer errors","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":null},"canonical_slug":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","context_length":8192,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Sao10K/L3-70B-Euryale-v2.1","name":"L3-70B-Euryale-v2.1","tags":["text_generation","best_role_play","free","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"70B tuned for storytelling, roleplay, creative writing","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":null},"canonical_slug":"Sao10K/L3-70B-Euryale-v2.1","context_length":8192,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Sao10K/L3-8B-Stheno-v3.2","name":"L3-8B-Stheno-v3.2","tags":["text_generation","best_role_play","free","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"8B LLaMA-3 model for roleplay & assistant tasks","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":null},"canonical_slug":"Sao10K/L3-8B-Stheno-v3.2","context_length":8192,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"DeepSeek-V3.2-Exp","tags":["text_generation","best_role_play","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2600","request":"0.00","completion":"0.3800","web_search":"0.00","input_cache_read":"0.1300","internal_reasoning":"0.00"},"description":"Experimental version with sparse-attention architecture for long-context efficiency","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V3.2-Exp","context_length":163840,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek-V3-0324","tags":["text_generation","best_role_play","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2750","request":"0.00","completion":"1.1000","web_search":"0.00","internal_reasoning":"0.00"},"description":"High-performance open-source MoE language model optimized for reasoning, coding, and efficient text generation","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V3-0324","context_length":163840,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek-V3.1","tags":["text_generation","best_role_play","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1900","request":"0.00","completion":"0.7900","web_search":"0.00","internal_reasoning":"0.00"},"description":"Hybrid inference LLM with Think/Non-Think modes, 128K context, advanced agent","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V3.1","context_length":163840,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek-R1-0528","tags":["text_generation","best_role_play","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.5000","request":"0.00","completion":"2.1500","web_search":"0.00","input_cache_read":"0.4000","internal_reasoning":"0.00"},"description":"An open-source next-generation reasoning-optimized language model with enhanced logic, math, and code performance, larger context handling, and improved function-calling capabilities","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-R1-0528","context_length":163840,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama3.3-70B","tags":["text_generation","Llama"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":10000},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.3000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Multilingual 70B delivering 405B-level performance","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":10000},"canonical_slug":"meta-llama/Llama-3.3-70B-Instruct","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Bytedance/seedream-4-5-251128","name":"Bytedance-Seedream-4.5","tags":["text_to_image","image_to_image","best_image_generation","featured","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0400","request":"0.00","completion":"0.0400","web_search":"0.00","internal_reasoning":"0.00"},"description":"The latest Bytedance image model, delivering better editing consistency, improved multi-image fusion, finer detail control, natural small text and faces, and harmonious, aesthetic visuals","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":0,"max_completion_tokens":null},"canonical_slug":"Bytedance/seedream-4-5-251128","context_length":0,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Bytedance/seedream-4-0-250828","name":"Bytedance-Seedream-4.0","tags":["text_to_image","image_to_image","best_image_generation","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0300","request":"0.00","completion":"0.0300","web_search":"0.00","internal_reasoning":"0.00"},"description":"Next-generation image creation model that unifies image generation and editing to handle complex multimodal tasks with faster inference and produce high-definition images up to 4K","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":0,"max_completion_tokens":null},"canonical_slug":"Bytedance/seedream-4-0-250828","context_length":0,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Byteplus/seedance-1-0-pro-250528","name":"Seedance-1.0-Pro-Text-to-Video","tags":["text_to_video","best_video_generation","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.5000","request":"0.00","completion":"2.5000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Pro-tier text-to-video, generates multi-shot 1080p videos with narrative flow","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Byteplus/seedance-1-0-pro-250528","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Byteplus/seedance-1-0-pro-250528","name":"Seedance-1.0-Pro-Text-to-Video","tags":["text_to_video","best_video_generation","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.5000","request":"0.00","completion":"2.5000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Pro-tier text-to-video, generates multi-shot 1080p videos with narrative flow","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Byteplus/seedance-1-0-pro-250528","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Byteplus/seedance-1-0-lite-i2v-250428","name":"Seedance-1.0-Lite-Image-to-Video","tags":["image_to_video","best_video_generation","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.8000","request":"0.00","completion":"1.8000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Lite version, quick image-to-video at up to 1080p, shorter sequences","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Byteplus/seedance-1-0-lite-i2v-250428","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Byteplus/seedance-1-0-lite-t2v-250428","name":"Seedance-1.0-Lite-Text-to-Video","tags":["text_to_video","best_video_generation","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.8000","request":"0.00","completion":"1.8000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Lite text-to-video, faster, lower compute, shorter outputs","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Byteplus/seedance-1-0-lite-t2v-250428","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Systran/faster-whisper-large-v3","name":"Faster-Whisper-Large-V3","tags":["audio","speech_to_text","Whisper"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.00","request":"0.00","completion":"0.00","web_search":"0.00","audio_per_minute":"0.0060","internal_reasoning":"0.00"},"description":"High-performance speech-to-text model optimized for fast, accurate transcription using an efficient Whisper-based architecture","architecture":{"modality":"audio->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["audio"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":false,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Systran/faster-whisper-large-v3","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen3-Embedding-8B","tags":["embeddings","free","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"8B embedding model, strong multilingual & code support, top MTEB scorer","architecture":{"modality":"text->embedding","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["embedding"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3-Embedding-8B","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"BAAI/bge-reranker-v2-m3","name":"BGE-reranker-v2-m3","tags":["reranker","free"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Multilingual reranker, query+passage → relevance score, lightweight & fast","architecture":{"modality":"text->rerank","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["rerank"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"BAAI/bge-reranker-v2-m3","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1765571302},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","tags":["multimodal","text_generation","featured","Kimi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.4500","request":"0.00","completion":"2.2500","web_search":"0.00","input_cache_read":"0.0700","internal_reasoning":"0.00"},"description":"An open-source native multimodal AI model that combines vision and language understanding with advanced agent-oriented capabilities, including self-directed agent swarm and visual coding, for versatile reasoning and tool use","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"moonshotai/Kimi-K2.5","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"anthropic/claude-opus-4-6","name":"Claude-Opus-4.6","tags":["multimodal","text_generation","recently_added","featured","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"4.0000","request":"0.00","completion":"20.0000","web_search":"0.00","input_cache_read":"0.5000","input_cache_write":"6.2500","internal_reasoning":"0.00"},"description":"Anthropic's most intelligent model, excelling at complex reasoning, coding, analysis, and multi-step tasks","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-opus-4-6","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude-Opus-4.5","tags":["multimodal","text_generation","recently_added","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"4.0000","request":"0.00","completion":"20.0000","web_search":"0.00","input_cache_read":"0.5000","input_cache_write":"6.2500","internal_reasoning":"0.00"},"description":"An advanced flagship model delivering top-tier reasoning, deep analysis, and long-context performance for the most demanding enterprise and research workloads","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-opus-4-5-20251101","context_length":200000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude-Haiku-4.5","tags":["multimodal","text_generation","recently_added","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.8000","request":"0.00","completion":"4.0000","web_search":"0.00","input_cache_read":"0.1000","input_cache_write":"1.2500","internal_reasoning":"0.00"},"description":"A lightweight, low-latency model built for rapid responses, simple reasoning, and high-throughput applications","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-haiku-4-5-20251001","context_length":200000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude-Sonnet-4.5","tags":["multimodal","text_generation","recently_added","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.4000","request":"0.00","completion":"12.0000","web_search":"0.00","input_cache_read":"0.3000","input_cache_write":"3.7500","internal_reasoning":"0.00"},"description":"A fast, cost-efficient model optimized for everyday reasoning, coding, and high-quality conversational tasks","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-sonnet-4-5-20250929","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax-M2.1","tags":["text_generation","recently_added","MiniMax"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2800","request":"0.00","completion":"1.2000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A lightweight, open-source text-to-text large language model optimized for coding, agent-oriented workflows, and instruction following, delivering faster, cleaner outputs and strong reasoning and problem-solving performance compared to its predecessor","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":196608,"max_completion_tokens":null},"canonical_slug":"MiniMaxAI/MiniMax-M2.1","context_length":196608,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","tags":["text_generation","featured","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.4000","request":"0.00","completion":"1.7500","web_search":"0.00","input_cache_read":"0.0800","internal_reasoning":"0.00"},"description":"An open-weights MoE chat model from Z.ai optimized for strong reasoning and tool-using agents","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-4.7","context_length":202752,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"gemini/gemini-3-flash-preview","name":"Gemini-3-Flash-Preview","tags":["multimodal","text_generation","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.4000","request":"0.00","completion":"2.4000","web_search":"0.00","input_cache_read":"0.0500","internal_reasoning":"0.00"},"description":"Google’s agentic workhorse model, bringing near Pro agentic, coding and multimodal intelligence, with more balanced cost and speed","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3-flash-preview","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"openai/gpt-5.2","name":"GPT-5.2","tags":["multimodal","text_generation","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.4000","request":"0.00","completion":"11.2000","web_search":"0.00","internal_reasoning":"0.00"},"description":"OpenAI’s flagship multimodal (text + image) GPT-5.2 model for top-tier coding and agentic tasks, producing text output with the highest reasoning capability in the GPT-5 family","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5.2","context_length":400000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"openai/gpt-5.1","name":"GPT-5.1","tags":["multimodal","text_generation","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.0000","request":"0.00","completion":"8.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"OpenAI’s multimodal (text + image) GPT-5 model for strong coding, reasoning, and agentic tasks across domains, producing text outputs","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5.1","context_length":400000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"openai/gpt-5","name":"GPT-5","tags":["multimodal","text_generation","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.0000","request":"0.00","completion":"8.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"OpenAI’s multimodal (text + image) GPT-5 model for strong coding, reasoning, and agentic tasks across domains, producing text outputs","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5","context_length":400000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"openai/gpt-5-mini","name":"GPT-5-Mini","tags":["multimodal","text_generation","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2000","request":"0.00","completion":"1.6000","web_search":"0.00","internal_reasoning":"0.00"},"description":"OpenAI’s faster, more cost-efficient GPT-5 model for well-defined tasks, supporting text and image input with text output","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5-mini","context_length":400000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"openai/gpt-5-nano","name":"GPT-5-Nano","tags":["multimodal","text_generation","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0400","request":"0.00","completion":"0.3200","web_search":"0.00","internal_reasoning":"0.00"},"description":"OpenAI’s fastest, most cost-efficient GPT-5 model for lightweight tasks like summarization and classification, supporting text and image input with text output","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5-nano","context_length":400000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral-Nemo-Instruct-2407","tags":["text_generation","recently_added","Mistral"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0200","request":"0.00","completion":"0.0400","web_search":"0.00","internal_reasoning":"0.00"},"description":"24B instruction model, long context, fewer errors","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":null},"canonical_slug":"mistralai/Mistral-Nemo-Instruct-2407","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","tags":["text_generation","best_role_play","featured","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2600","request":"0.00","completion":"0.3800","web_search":"0.00","input_cache_read":"0.1300","internal_reasoning":"0.00"},"description":"A high-performance open-weight large language model from DeepSeek optimized for strong reasoning, coding, and general chat capabilities with efficient inference","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V3.2","context_length":163840,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"gemini/gemini-3-pro-image","name":"Nano-Banana-Pro","tags":["text_to_image","best_image_generation","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"96.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"High-quality image generation with better text rendering, character consistency, and advanced composition. Powered by Gemini 3 Pro Image.","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3-pro-image","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"gemini/gemini-2.5-flash-image-edit","name":"Nano-Banana-Edit","tags":["image_to_image","text_to_image","best_image_generation","recently_added","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"24.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"AI-powered image editing with Gemini 2.5 Flash. Edit images using natural language instructions - remove backgrounds, change colors, apply styles, and more.","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-2.5-flash-image-edit","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"gemini/gemini-2.5-flash-image","name":"Nano-Banana","tags":["text_to_image","best_image_generation","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"24.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Gemini 2.5 Flash Image - High-quality image generation with multiple aspect ratios","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-2.5-flash-image","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"Google/veo-3.1-fast","name":"Veo-3.1-Fast","tags":["text_to_video","best_video_generation","recently_added","Veo"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0800","request":"0.00","completion":"0.0800","web_search":"0.00","internal_reasoning":"0.00"},"description":"Google Veo 3.1 Fast - Fast and economical text-to-video generation. Supports up to 8 seconds at 720p/1080p. Optional AI-generated audio (+50% cost).","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Google/veo-3.1-fast","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"Google/veo-3.1-fast-i2v","name":"Veo-3.1-Fast-I2V","tags":["image_to_video","best_video_generation","recently_added","Veo"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0800","request":"0.00","completion":"0.0800","web_search":"0.00","internal_reasoning":"0.00"},"description":"Google Veo 3.1 Fast Image-to-Video - Generate video from an input image. Supports up to 8 seconds at 720p/1080p.","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Google/veo-3.1-fast-i2v","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"Google/veo-3.1","name":"Veo-3.1","tags":["text_to_video","best_video_generation","recently_added","Veo"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1600","request":"0.00","completion":"0.1600","web_search":"0.00","internal_reasoning":"0.00"},"description":"Google Veo 3.1 Standard - Balanced quality and speed for text-to-video generation. Supports up to 8 seconds at 720p/1080p.","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Google/veo-3.1","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"Google/veo-3.1-i2v","name":"Veo-3.1-I2V","tags":["image_to_video","best_video_generation","recently_added","Veo"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1600","request":"0.00","completion":"0.1600","web_search":"0.00","internal_reasoning":"0.00"},"description":"Google Veo 3.1 Standard Image-to-Video - Generate high-quality video from an input image.","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Google/veo-3.1-i2v","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen2.5-VL-32B-Instruct","tags":["vision","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2000","request":"0.00","completion":"0.6000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A 32B-parameter vision-language model tuned to follow instructions and reason over images and text","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":16384,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen2.5-VL-32B-Instruct","context_length":16384,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1770695854},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","tags":["text_generation","featured","MiniMax"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.3000","request":"0.00","completion":"1.2000","web_search":"0.00","input_cache_read":"0.1500","internal_reasoning":"0.00"},"description":"MiniMax-M2.5 is a cost-efficient frontier model that achieves SOTA in coding, agentic tool use, and search tasks through extensive reinforcement learning in real-world environments","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":204800,"max_completion_tokens":null},"canonical_slug":"MiniMaxAI/MiniMax-M2.5","context_length":204800,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771036668},{"id":"zai-org/GLM-5","name":"GLM-5","tags":["text_generation","recently_added","featured","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.8000","request":"0.00","completion":"2.5600","web_search":"0.00","input_cache_read":"0.2000","internal_reasoning":"0.00"},"description":"Z.ai's most powerful model — a 744B-parameter (40B active) open-source MoE optimized for reasoning, coding, and agentic tasks","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-5","context_length":202752,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771036668},{"id":"gemini/gemini-3-pro-image-edit","name":"Nano-Banana-Pro-Edit","tags":["image_to_image","text_to_image","best_image_generation","recently_added","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"96.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Premium AI-powered image editing with Gemini 3 Pro. Advanced editing capabilities with better quality, supports multiple resolution outputs (1K/2K/4K).","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3-pro-image-edit","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771036668},{"id":"Lykon/dreamshaper-8","name":"DreamShaper-8","tags":["text_to_image","best_image_generation","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0020","request":"0.00","completion":"0.0020","web_search":"0.00","internal_reasoning":"0.00"},"description":"A Stable Diffusion v1.5-based text-to-image model, balancing photorealistic and stylized (including anime) generation with strong LoRA compatibility","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Lykon/dreamshaper-8","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771036668},{"id":"Qwen/Qwen3.5-Plus","name":"Qwen3.5-Plus","tags":["multimodal","text_generation","recently_added","featured","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.4000","request":"0.00","completion":"2.4000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba's native vision-language model with a 1M-token context window, hybrid MoE architecture, and built-in tool use, offering frontier-class multimodal reasoning at competitive pricing","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3.5-Plus","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771448680},{"id":"anthropic/claude-sonnet-4-6","name":"Claude-Sonnet-4.6","tags":["multimodal","text_generation","recently_added","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.4000","request":"0.00","completion":"12.0000","web_search":"0.00","input_cache_read":"0.3000","input_cache_write":"3.7500","internal_reasoning":"0.00"},"description":"Anthropic's most capable mid-tier model, delivering near-Opus-level intelligence across coding, computer use, agentic workflows, and long-context reasoning with a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-sonnet-4-6","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771448680},{"id":"gemini/gemini-3.1-pro-preview","name":"Gemini-3.1-Pro-Preview","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.6000","request":"0.00","completion":"9.6000","web_search":"0.00","input_cache_read":"0.2000","internal_reasoning":"0.00"},"description":"Google's frontier reasoning model that builds on the Gemini 3 Pro series with enhanced thinking capabilities, improved token efficiency, and stronger performance in software engineering and agentic workflows, featuring a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3.1-pro-preview","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771606259},{"id":"Qwen/Qwen3-VL-Plus","name":"Qwen3-VL-Plus","tags":["vision","recently_added","featured","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2000","request":"0.00","completion":"1.6000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba's multimodal vision-language API model that handles text, image, and video inputs with strong visual reasoning and agent capabilities","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3-VL-Plus","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771606259},{"id":"Qwen/Qwen3-VL-Flash","name":"Qwen3-VL-Flash","tags":["vision","recently_added","featured","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0500","request":"0.00","completion":"0.4000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba's lightweight, cost-effective multimodal vision-language API model designed for fast inference on text, image, and video tasks with integrated thinking and non-thinking modes","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3-VL-Flash","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1771606259},{"id":"Alibaba/z-image-turbo","name":"Alibaba-Z-Image-Turbo","tags":["text_to_image","best_image_generation","recently_added","featured","z-image"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0150","request":"0.00","completion":"0.0150","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba Z-Image Turbo - Fast text-to-image with Chinese/English text rendering support.","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Alibaba/z-image-turbo","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772052781},{"id":"Alibaba/wan2.6-t2v","name":"Alibaba-Wan-2.6-T2V","tags":["text_to_video","best_video_generation","recently_added","featured","wan"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.1000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba Wan 2.6 Flash - Fast text-to-video generation. Supports 2-15 seconds at 720p/1080p.","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Alibaba/wan2.6-t2v","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772052781},{"id":"Alibaba/wan2.6-i2v","name":"Alibaba-Wan-2.6-I2V","tags":["image_to_video","best_video_generation","recently_added","featured","wan"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.1000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba Wan 2.6 I2V - Image-to-video generation. Supports 2-15 seconds at 720p/1080p.","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Alibaba/wan2.6-i2v","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772052781},{"id":"Alibaba/wan2.6-r2v-flash","name":"Alibaba-Wan-2.6-R2V-Flash","tags":["reference_to_video","best_video_generation","recently_added","featured","wan"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0250","request":"0.00","completion":"0.0250","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba Wan 2.6 R2V Flash - Reference-to-video generation from 1-3 reference videos. Supports 5 or 10 seconds.","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Alibaba/wan2.6-r2v-flash","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772052781},{"id":"Bytedance/seedream-5-0-lite-260128","name":"Bytedance-Seedream-5.0-Lite","tags":["text_to_image","image_to_image","best_image_generation","recently_added","featured","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0350","request":"0.00","completion":"0.0350","web_search":"0.00","internal_reasoning":"0.00"},"description":"Advanced text-to-image generation with web search, deep reasoning and smart editing capabilities. Supports up to 3K resolution and seed parameters.","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Bytedance/seedream-5-0-lite-260128","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772069825},{"id":"gemini/gemini-3.1-flash-lite-preview","name":"Gemini-3.1-Flash-Lite-Preview","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2000","request":"0.00","completion":"1.2000","web_search":"0.00","input_cache_read":"0.0250","internal_reasoning":"0.00"},"description":"Google’s fastest and most cost-efficient Gemini 3 model, optimized for high-throughput tasks and scalable real-time applications","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3.1-flash-lite-preview","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772743391},{"id":"gemini/gemini-3.1-flash-image","name":"Nano-Banana-2","tags":["text_to_image","image_generation","best_image_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.5000","request":"0.00","completion":"48.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Text-to-image and image+text-to-image with up to 14 reference images. Supports aspect_ratio, image_size, person_generation, output_mime_type, compression_quality, thinking_level.","architecture":{"modality":"text->image","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["image"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3.1-flash-image","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772743391},{"id":"Alibaba/wan2.6-i2v-flash","name":"Alibaba-Wan2.6-I2V-Flash","tags":["image_to_video","best_video_generation","recently_added","featured","wan"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0250","request":"0.00","completion":"0.0250","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba Wan 2.6 I2V Flash - Fast lightweight I2V with 480P/720P/1080P, audio/silent pricing","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Alibaba/wan2.6-i2v-flash","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772743391},{"id":"Alibaba/wan2.6-r2v","name":"Wan2.6-R2V","tags":["reference_to_video","best_video_generation","recently_added","featured","wan"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.1000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba Wan 2.6 R2V - Mixed image+video references (up to 5 combined)","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Alibaba/wan2.6-r2v","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772743391},{"id":"zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","tags":["text_generation","recently_added","featured","free","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A 30B Mixture-of-Experts language model optimized for efficient inference, strong coding performance, and long-context reasoning tasks","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-4.7-Flash","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1772824518},{"id":"openai/gpt-5.4","name":"GPT-5.4","tags":["multimodal","text_generation","recently_added","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"12.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A frontier large language model optimized for complex professional tasks, combining strong reasoning, coding, and tool-use capabilities with very long context support","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5.4","context_length":400000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1773352969},{"id":"gemini/gemini-2.5-flash-tts","name":"Gemini-2.5-Flash-TTS","tags":["audio","text_to_speech","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.4000","request":"0.00","completion":"8.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A low-latency, cost-efficient text-to-speech model that converts text into expressive single or multi-speaker audio with controllable tone, style, and pacing","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-2.5-flash-tts","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1773352969},{"id":"gemini/gemini-2.5-pro-tts","name":"Gemini-2.5-Pro-TTS","tags":["audio","text_to_speech","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.8000","request":"0.00","completion":"16.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A high-quality text-to-speech model designed to generate natural, expressive audio with fine-grained control over tone, pacing, and emotion for narration, assistants, and conversational voice applications","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-2.5-pro-tts","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1773352969},{"id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral-Small-4","tags":["multimodal","text_generation","recently_added","featured","Mistral"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1500","request":"0.00","completion":"0.6000","web_search":"0.00","input_cache_read":"0.0150","internal_reasoning":"0.00"},"description":"A large (~119B parameter) dense language model designed for efficient, high-quality text generation and reasoning with a focus on strong performance-to-cost efficiency compared to similarly sized models","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"mistralai/Mistral-Small-4-119B-2603","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1773779915},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","tags":["text_generation","recently_added","featured","MiniMax"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.3000","request":"0.00","completion":"1.2000","web_search":"0.00","input_cache_read":"0.0600","internal_reasoning":"0.00"},"description":"A next-generation agentic LLM with native interleaved thinking, built for complex real-world productivity tasks like coding, tool use, and multi-step reasoning — at a highly competitive price point","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":204800,"max_completion_tokens":null},"canonical_slug":"MiniMaxAI/MiniMax-M2.7","context_length":204800,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1773951836},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek-V4-Pro","tags":["text_generation","featured","recently_added","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.3000","request":"0.00","completion":"2.6000","web_search":"0.00","input_cache_read":"0.1000","internal_reasoning":"0.00"},"description":"DeepSeek's next-generation flagship language model delivering state-of-the-art reasoning, coding, and agentic performance with a 1M context window","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V4-Pro","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek-V4-Flash","tags":["text_generation","featured","recently_added","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.2000","web_search":"0.00","input_cache_read":"0.0200","internal_reasoning":"0.00"},"description":"DeepSeek's fast, cost-efficient V4 variant optimized for high-throughput reasoning and coding with a 1M context window","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V4-Flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","tags":["text_generation","featured","recently_added","Xiaomi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.4350","request":"0.00","completion":"0.8700","web_search":"0.00","input_cache_read":"0.0036","internal_reasoning":"0.00"},"description":"Xiaomi's flagship text model tuned for complex software engineering, agentic workflows, and long-horizon tasks with a 1M context window","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"XiaomiMiMo/MiMo-V2.5-Pro","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","tags":["multimodal","text_generation","featured","recently_added","Xiaomi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1400","request":"0.00","completion":"0.2800","web_search":"0.00","input_cache_read":"0.0028","internal_reasoning":"0.00"},"description":"Xiaomi's natively omnimodal model accepting text, image, audio, and video inputs with a 1M context window for agentic and long-horizon reasoning","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"XiaomiMiMo/MiMo-V2.5","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","tags":["multimodal","text_generation","featured","Kimi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.7500","request":"0.00","completion":"3.5000","web_search":"0.00","input_cache_read":"0.1600","internal_reasoning":"0.00"},"description":"An open-weight 1T-parameter MoE multimodal model built for long-horizon agentic coding, with a 256K context window, native vision input, and scaling up to 300 parallel sub-agents","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"moonshotai/Kimi-K2.6","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"anthropic/claude-opus-4-7","name":"Claude-Opus-4.7","tags":["multimodal","text_generation","recently_added","featured","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"4.0000","request":"0.00","completion":"20.0000","web_search":"0.00","input_cache_read":"0.5000","input_cache_write":"6.2500","internal_reasoning":"0.00"},"description":"Anthropic's most capable generally available model, excelling at agentic coding, long-running tasks, and complex professional work with adaptive thinking that adjusts reasoning depth based on task complexity","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-opus-4-7","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","tags":["text_generation","recently_added","featured","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.0500","request":"0.00","completion":"3.5000","web_search":"0.00","input_cache_read":"0.2050","internal_reasoning":"0.00"},"description":"Z.ai's open-source flagship MoE model built for agentic engineering, delivering state-of-the-art coding and long-horizon task performance that improves the longer it runs","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-5.1","context_length":202752,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"Qwen/Qwen3.6-Plus","name":"Qwen3.6-Plus","tags":["multimodal","text_generation","recently_added","featured","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.5000","request":"0.00","completion":"3.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Alibaba's flagship hosted model with a 1M-token context window, excelling at agentic coding, multimodal reasoning, and long-horizon planning tasks","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3.6-Plus","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"google/gemma-4-31b-it","name":"Gemma-4-31B","tags":["multimodal","text_generation","recently_added","featured","Google"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1300","request":"0.00","completion":"0.3800","web_search":"0.00","input_cache_read":"0.0650","internal_reasoning":"0.00"},"description":"Google DeepMind's open-weights, instruction-tuned multimodal model optimized for reasoning, coding, and agentic workflows ","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":null},"canonical_slug":"google/gemma-4-31b-it","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1777050508},{"id":"gemini/gemini-3.1-flash-lite","name":"Gemini-3.1-Flash-Lite","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.2000","request":"0.00","completion":"1.2000","web_search":"0.00","input_cache_read":"0.0250","internal_reasoning":"0.00"},"description":"Google's most cost-efficient, low-latency multimodal model in the Gemini 3 series, optimized for high-volume, latency-sensitive tasks like translation, classification, and simple data extraction with support for text, image, video, audio, and PDF inputs","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3.1-flash-lite","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1778518075},{"id":"x-ai/grok-4.3","name":"Grok-4.3","tags":["multimodal","text_generation","featured","recently_added","Grok"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.2500","request":"0.00","completion":"2.5000","web_search":"0.00","input_cache_read":"0.2000","internal_reasoning":"0.00"},"description":"xAI's reasoning model released in late April 2026, featuring always-on reasoning, a 1-million-token context window, and multimodal text/image input","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"x-ai/grok-4.3","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1778518075},{"id":"openai/gpt-5.5","name":"GPT-5.5","tags":["multimodal","text_generation","featured","recently_added","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"4.0000","request":"0.00","completion":"24.0000","web_search":"0.00","input_cache_read":"0.4000","internal_reasoning":"0.00"},"description":"OpenAI's next-generation multimodal GPT-5.5 model with improved token efficiency for hard reasoning, coding, and agentic tasks","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5.5","context_length":400000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1778518075},{"id":"gemini/gemini-3.5-flash","name":"Gemini-3.5-Flash","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":65535},"default":false,"pricing":{"image":"0.00","prompt":"1.2000","request":"0.00","completion":"7.2000","web_search":"0.00","input_cache_read":"0.1500","input_cache_write":"0.0833","internal_reasoning":"0.00"},"description":"Latest Gemini 3.5 Flash — fast multimodal reasoning with 1M context","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65535},"canonical_slug":"gemini/gemini-3.5-flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1779289631},{"id":"anthropic/claude-opus-4-8","name":"Claude-Opus-4.8","tags":["multimodal","text_generation","recently_added","featured","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"4.2500","request":"0.00","completion":"21.2500","web_search":"0.00","input_cache_read":"0.5000","input_cache_write":"6.2500","internal_reasoning":"0.00"},"description":"Anthropic's most capable generally available model, excelling at agentic coding, long-running tasks, and complex professional work with adaptive thinking that adjusts reasoning depth based on task \n  complexity","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-opus-4-8","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1779997572},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","tags":["multimodal","text_generation","recently_added","featured","MiniMax"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.3000","request":"0.00","completion":"1.2000","web_search":"0.00","input_cache_read":"0.0600","internal_reasoning":"0.00"},"description":"A million-token multimodal frontier model from MiniMax, built for long-horizon agentic work with native text/image/video understanding and tool calling","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"MiniMaxAI/MiniMax-M3","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1781038238},{"id":"anthropic/claude-fable-5","name":"Claude-Fable-5","tags":["multimodal","text_generation","recently_added","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"10.0000","request":"0.00","completion":"50.0000","web_search":"0.00","input_cache_read":"1.0000","input_cache_write":"12.5000","internal_reasoning":"0.00"},"description":"Anthropic's most capable frontier model for demanding reasoning and long-horizon agentic work, with always-on adaptive thinking that adjusts reasoning depth based on task complexity","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-fable-5","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1781114694},{"id":"gemini/gemini-3.1-flash-live-preview","name":"Gemini-3.1-Flash-Live","tags":["audio","realtime","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.7500","request":"0.00","completion":"12.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Gemini Live speech-to-speech model for real-time voice conversations — bidirectional audio streaming over the OpenAI-compatible /v1/realtime WebSocket","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":false,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"gemini/gemini-3.1-flash-live-preview","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1781289755},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi-K2.7-Code","tags":["multimodal","text_generation","recently_added","featured","Kimi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.7500","request":"0.00","completion":"3.5000","web_search":"0.00","input_cache_read":"0.1500","input_cache_write":"0.0000","internal_reasoning":"0.00"},"description":"Moonshot AI's trillion-parameter open-source MoE coding model, built for long-horizon, high-efficiency agentic software engineering","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"moonshotai/Kimi-K2.7-Code","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1781737212},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","tags":["text_generation","recently_added","featured","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.0000","request":"0.00","completion":"3.0000","web_search":"0.00","input_cache_read":"0.1800","input_cache_write":"0.0000","internal_reasoning":"0.00"},"description":"Z.ai's open-source MoE model for long-context reasoning and agentic software engineering, with a 1M-token context window","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-5.2","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1781737213},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6-35B-A3B","tags":["text_generation","recently_added","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1200","request":"0.00","completion":"0.7600","web_search":"0.00","internal_reasoning":"0.00"},"description":"Qwen3.6 35B (3B-active) MoE with built-in NEXTN speculative decoding, reasoning and tool calling — fast low-cost generation","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3.6-35B-A3B","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1782836460},{"id":"anthropic/claude-sonnet-5","name":"Claude-Sonnet-5","tags":["multimodal","text_generation","recently_added","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"10.0000","web_search":"0.00","input_cache_read":"0.2000","input_cache_write":"2.5000","internal_reasoning":"0.00"},"description":"Anthropic's most capable mid-tier model, delivering near-Opus-level intelligence across coding, computer use, agentic workflows, and long-context reasoning with a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-sonnet-5","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1782856096},{"id":"x-ai/grok-4.5","name":"Grok-4.5","tags":["multimodal","text_generation","featured","recently_added","Grok"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"6.0000","web_search":"0.00","input_cache_read":"0.5000","internal_reasoning":"0.00"},"description":"xAI's flagship model released in July 2026, with frontier performance on coding, knowledge work, and STEM. 500K-token context window and multimodal text/image input","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":500000,"max_completion_tokens":null},"canonical_slug":"x-ai/grok-4.5","context_length":500000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1783612238},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6-Terra","tags":["multimodal","text_generation","featured","recently_added","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"12.0000","web_search":"0.00","input_cache_read":"0.2000","internal_reasoning":"0.00"},"description":"OpenAI GPT-5.6 Terra — a balanced multimodal model in the GPT-5.6 series with strong reasoning, positioned between the flagship Sol and cost-efficient Luna tiers","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5.6-terra","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1783633148},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6-Sol","tags":["multimodal","text_generation","featured","recently_added","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"5.0000","request":"0.00","completion":"30.0000","web_search":"0.00","input_cache_read":"0.5000","internal_reasoning":"0.00"},"description":"OpenAI GPT-5.6 Sol — flagship multimodal model in the GPT-5.6 series with top-tier reasoning and agentic coding","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":null},"canonical_slug":"openai/gpt-5.6-sol","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1783955378},{"id":"moonshotai/Kimi-K3","name":"Kimi-K3","tags":["multimodal","text_generation","recently_added","featured","Kimi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"3.0000","request":"0.00","completion":"15.0000","web_search":"0.00","input_cache_read":"0.3000","internal_reasoning":"0.00"},"description":"Moonshot AI's flagship model with a 1M-token context window, built for long-horizon agentic coding and tool use, with native vision input and always-on reasoning","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"moonshotai/Kimi-K3","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1784310779},{"id":"Qwen/Qwen3.8-Max-Preview","name":"Qwen3.8-Max-Preview","tags":["text_generation","recently_added","featured","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":64000},"default":false,"pricing":{"image":"0.00","prompt":"1.5000","request":"0.00","completion":"5.0000","web_search":"0.00","input_cache_read":"0.1500","internal_reasoning":"0.00"},"description":"Alibaba Qwen 2.4T-parameter flagship preview with major gains in coding, full-stack development, data analysis, and office workflows; always uses thinking mode and supports long-horizon tool workflows and structured output","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":991000,"max_completion_tokens":64000},"canonical_slug":"Qwen/Qwen3.8-Max-Preview","context_length":991000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1784565369},{"id":"gemini/gemini-3.6-flash","name":"Gemini-3.6-Flash","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":65535},"default":false,"pricing":{"image":"0.00","prompt":"0.6000","request":"0.00","completion":"3.0000","web_search":"0.00","input_cache_read":"0.0750","internal_reasoning":"0.00"},"description":"Google's latest Flash model — upgraded multimodal reasoning, coding and agentic performance at Flash speed and cost, with a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65535},"canonical_slug":"gemini/gemini-3.6-flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1784740614},{"id":"gemini/gemini-3.5-flash-lite","name":"Gemini-3.5-Flash-Lite","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":65535},"default":false,"pricing":{"image":"0.00","prompt":"0.2400","request":"0.00","completion":"2.0000","web_search":"0.00","input_cache_read":"0.0300","internal_reasoning":"0.00"},"description":"Google's most cost-efficient Gemini 3.5 model — low-latency multimodal inference tuned for high-volume classification, extraction and translation workloads","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65535},"canonical_slug":"gemini/gemini-3.5-flash-lite","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1784740614},{"id":"anthropic/claude-opus-5","name":"Claude-Opus-5","tags":["multimodal","text_generation","recently_added","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"5.0000","request":"0.00","completion":"25.0000","web_search":"0.00","input_cache_read":"0.5000","input_cache_write":"6.2500","internal_reasoning":"0.00"},"description":"Anthropic's most capable model for complex agentic coding and enterprise work, delivering a step-change in deep reasoning and long-horizon autonomy over Claude Opus 4.8, with a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-opus-5","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1784922557},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek-V4-Flash-0731","tags":["text_generation","featured","recently_added","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0900","request":"0.00","completion":"0.1800","web_search":"0.00","input_cache_read":"0.0180","internal_reasoning":"0.00"},"description":"DeepSeek's official V4 Flash release, superseding the preview with substantially stronger agentic and coding performance, at 284B total / 13B active parameters and a 1M-token context window","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1785780192},{"id":"x-ai/grok-4.6","name":"Grok-4.6","tags":["multimodal","text_generation","featured","recently_added","Grok"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"6.0000","web_search":"0.00","input_cache_read":"0.5000","internal_reasoning":"0.00"},"description":"xAI's smartest model, with frontier performance on coding, knowledge work, and STEM. 500K-token context window, always-on reasoning, and multimodal text/image input","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":500000,"max_completion_tokens":null},"canonical_slug":"x-ai/grok-4.6","context_length":500000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1786635972},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek-V4-Pro-0813","tags":["text_generation","featured","recently_added","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.6000","request":"0.00","completion":"1.8000","web_search":"0.00","input_cache_read":"0.0200","internal_reasoning":"0.00"},"description":"DeepSeek's GA release of V4 Pro, a large-scale mixture-of-experts model with a 1M-token context window and configurable reasoning depth","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"deepseek-ai/DeepSeek-V4-Pro-0813","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1786635972},{"id":"gemini/gemini-3.7-flash","name":"Gemini-3.7-Flash","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":65536},"default":false,"pricing":{"image":"0.00","prompt":"0.6000","request":"0.00","completion":"3.0000","web_search":"0.00","input_cache_read":"0.0750","internal_reasoning":"0.00"},"description":"Google's newest Flash model — stronger multimodal reasoning, coding and agentic performance at Flash speed, with a 1M-token context window and always-on thinking","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"canonical_slug":"gemini/gemini-3.7-flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1786647542},{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8-2.4T-A95B","tags":["text_generation","recently_added","featured","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":262144},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"6.0000","web_search":"0.00","input_cache_read":"0.2000","internal_reasoning":"0.00"},"description":"Alibaba's most capable open-weight model — a 2.4T-parameter Mixture-of-Experts with 95B active parameters per token, built for agentic tasks, long-horizon reasoning and complex coding workflows","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":262144},"canonical_slug":"Qwen/Qwen3.8-2.4T-A95B","context_length":262144,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1786719518},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","tags":["text_generation","featured","recently_added","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.4000","request":"0.00","completion":"4.4000","web_search":"0.00","input_cache_read":"0.2600","internal_reasoning":"0.00"},"description":"Z.ai's GLM-5.3, a 1M-token-context reasoning model with tool calling and structured outputs. Reasoning is always on and cannot be switched off","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-5.3","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1787686810},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8-27B","tags":["multimodal","text_generation","featured","recently_added","Qwen"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.3500","request":"0.00","completion":"2.5500","web_search":"0.00","input_cache_read":"0.0350","internal_reasoning":"0.00"},"description":"Qwen's compact 27B dense model from the Qwen3.8 generation, with strong agentic and coding performance, tool calling","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":null},"canonical_slug":"Qwen/Qwen3.8-27B","context_length":65536,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1787686810},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","tags":["multimodal","text_generation","featured","recently_added","GLM"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.1500","request":"0.00","completion":"0.5000","web_search":"0.00","input_cache_read":"0.0300","internal_reasoning":"0.00"},"description":"Z.ai's fast, low-cost GLM-5.3 variant with a 1M-token context window, image understanding and tool calling. Reasoning is always on and cannot be switched off","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"zai-org/GLM-5.3-Flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1787765375},{"id":"anthropic/claude-fable-5-1","name":"Claude-Fable-5.1","tags":["multimodal","text_generation","recently_added","featured","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"10.0000","request":"0.00","completion":"50.0000","web_search":"0.00","input_cache_read":"0.2500","input_cache_write":"12.5000","internal_reasoning":"0.00"},"description":"Anthropic's Fable 5.1, improving on Fable 5 across agentic coding, long-horizon workflows, front-end code generation and analysis, with always-on adaptive thinking","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":null},"canonical_slug":"anthropic/claude-fable-5-1","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1788306682},{"id":"gemini/gemini-3.8-flash","name":"Gemini-3.8-Flash","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":65536},"default":false,"pricing":{"image":"0.00","prompt":"0.7500","request":"0.00","completion":"3.7500","web_search":"0.00","input_cache_read":"0.0750","internal_reasoning":"0.00"},"description":"Google's newest Flash model — stronger multimodal reasoning, coding and agentic performance at Flash speed, with a 1M-token context window and always-on thinking","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"canonical_slug":"gemini/gemini-3.8-flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1788387888},{"id":"openai/gpt-6-astra","name":"GPT-6-Astra","tags":["multimodal","text_generation","recently_added","featured","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"8.0000","request":"0.00","completion":"40.0000","web_search":"0.00","input_cache_read":"0.8000","input_cache_write":"10.0000","internal_reasoning":"0.00"},"description":"OpenAI's most capable model for the hardest end-to-end work — state-of-the-art computer use, browsing, software engineering, science and professional tasks, with a 1M-token context window and always-on reasoning","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6-astra","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1788895397},{"id":"openai/gpt-6-astra-pro","name":"GPT-6-Astra-Pro","tags":["multimodal","text_generation","recently_added","featured","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"8.0000","request":"0.00","completion":"40.0000","web_search":"0.00","input_cache_read":"0.8000","input_cache_write":"10.0000","internal_reasoning":"0.00"},"description":"GPT 6 Astra in Pro reasoning mode — spends additional model work on difficult tasks at the same per-token rates, with higher latency and token usage","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6-astra-pro","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1788895397},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek-V4.1-Flash","tags":["multimodal","text_generation","featured","recently_added","DeepSeek"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":384000},"default":false,"pricing":{"image":"0.00","prompt":"0.3000","request":"0.00","completion":"1.2000","web_search":"0.00","input_cache_read":"0.0060","internal_reasoning":"0.00"},"description":"DeepSeek's first model on the Causal Encoder-Decoder (CED) architecture — a sparse mixture-of-experts that activates 8B parameters on input and 16B on output from a 552B-parameter backbone, with image input and a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":384000},"canonical_slug":"deepseek-ai/DeepSeek-V4.1-Flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1789055410},{"id":"Byteplus/seedance-2-0-260128","name":"Seedance-2.0","tags":["text_to_video","image_to_video","video_to_video","best_video_generation","recently_added","featured","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"7.0000","request":"0.00","completion":"7.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"BytePlus Seedance 2.0 — unified multimodal video (text/image/video/audio refs, native audio). Billed on actual tokens; rate varies by resolution & reference video","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Byteplus/seedance-2-0-260128","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790013191},{"id":"Byteplus/seedance-2-0-fast-260128","name":"Seedance-2.0-Fast","tags":["text_to_video","image_to_video","video_to_video","best_video_generation","recently_added","featured","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"5.6000","request":"0.00","completion":"5.6000","web_search":"0.00","internal_reasoning":"0.00"},"description":"BytePlus Seedance 2.0 Fast — faster/cheaper variant (no 1080p). Billed on actual tokens","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Byteplus/seedance-2-0-fast-260128","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790013191},{"id":"Byteplus/seedance-2-0-mini-260615","name":"Seedance-2.0-Mini","tags":["text_to_video","image_to_video","video_to_video","best_video_generation","recently_added","featured","Bytedance"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"3.5000","request":"0.00","completion":"3.5000","web_search":"0.00","internal_reasoning":"0.00"},"description":"BytePlus Seedance 2.0 Mini — cost-effective variant (no 1080p). Billed on actual tokens","architecture":{"modality":"text->video","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["video"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"Byteplus/seedance-2-0-mini-260615","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790013191},{"id":"TheDrummer/Cydonia-24B-v4.3","name":"Cydonia-24B-v4.3","tags":["text_generation","best_role_play","recently_added","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.3000","request":"0.00","completion":"0.5000","web_search":"0.00","internal_reasoning":"0.00"},"description":"A 24B-parameter uncensored instruction-tuned model focused on creative writing with strong recall and prompt adherence","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":null},"canonical_slug":"TheDrummer/Cydonia-24B-v4.3","context_length":131072,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790013191},{"id":"MegaNova/Web-Search","name":"Web Search","tags":["web_search","recently_added","featured","MegaNova"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"0.0000","request":"0.00","completion":"0.0000","web_search":"0.00","internal_reasoning":"0.00"},"description":"Real-time managed natural-language web search that returns ranked results, optionally enriched with full extracted page text in a single call—includes 50 free queries per user per day, with additional queries priced at $0.002 each","architecture":{"modality":"text->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":false,"completion":true,"chat_completions":true,"function_calling":false},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"canonical_slug":"MegaNova/Web-Search","context_length":null,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790013191},{"id":"x-ai/grok-4.7","name":"Grok-4.7","tags":["multimodal","text_generation","featured","recently_added","Grok"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"1.6000","request":"0.00","completion":"4.8000","web_search":"0.00","input_cache_read":"0.4000","internal_reasoning":"0.00"},"description":"xAI's flagship model, succeeding Grok-4.6. Strongest on long-running software engineering and agentic tool use. 500K context, always-on reasoning, text/image input. Prompts over 200K tokens bill at 2x the listed rate.","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":500000,"max_completion_tokens":null},"canonical_slug":"x-ai/grok-4.7","context_length":500000,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790013191},{"id":"XiaomiMiMo/MiMo-V2.6-Flash","name":"MiMo-V2.6-Flash","tags":["multimodal","text_generation","featured","recently_added","Xiaomi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":131072},"default":false,"pricing":{"image":"0.00","prompt":"0.1400","request":"0.00","completion":"0.2800","web_search":"0.00","input_cache_read":"0.0028","internal_reasoning":"0.00"},"description":"Xiaomi's fast omnimodal MoE model — 309B total parameters with 15B active per token and hybrid attention — accepting text, image, audio, and video input with a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"canonical_slug":"XiaomiMiMo/MiMo-V2.6-Flash","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790088643},{"id":"XiaomiMiMo/MiMo-V2.6-Pro","name":"MiMo-V2.6-Pro","tags":["multimodal","text_generation","featured","recently_added","Xiaomi"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":131072},"default":false,"pricing":{"image":"0.00","prompt":"0.4350","request":"0.00","completion":"0.8700","web_search":"0.00","input_cache_read":"0.0036","internal_reasoning":"0.00"},"description":"Xiaomi's flagship omnimodal model at over 1T parameters, built for demanding agentic, coding, and long-horizon reasoning work, accepting text, image, audio, and video input with a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"canonical_slug":"XiaomiMiMo/MiMo-V2.6-Pro","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790088643},{"id":"anthropic/claude-opus-5-5","name":"Claude-Opus-5.5","tags":["multimodal","text_generation","recently_added","featured","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"4.0000","request":"0.00","completion":"20.0000","web_search":"0.00","input_cache_read":"0.2000","input_cache_write":"5.0000","internal_reasoning":"0.00"},"description":"Anthropic's flagship Claude Opus 5.5, succeeding Claude Opus 5 for demanding reasoning, coding and long-horizon agentic work, with always-on adaptive thinking and a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"canonical_slug":"anthropic/claude-opus-5-5","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790105825},{"id":"openai/gpt-6-luna","name":"GPT-6-Luna","tags":["multimodal","text_generation","recently_added","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.5000","web_search":"0.00","input_cache_read":"0.0100","input_cache_write":"0.1250","internal_reasoning":"0.00"},"description":"OpenAI's fast, cost-efficient GPT-6 model for high-volume and latency-sensitive work such as chat, classification and lightweight agentic tasks, with adjustable reasoning and a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6-luna","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790105825},{"id":"openai/gpt-6-luna-pro","name":"GPT-6-Luna-Pro","tags":["multimodal","text_generation","recently_added","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.5000","web_search":"0.00","input_cache_read":"0.0100","input_cache_write":"0.1250","internal_reasoning":"0.00"},"description":"GPT-6 Luna in Pro reasoning mode — spends additional model work on complex tasks at the same per-token rates, with higher latency and token usage","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6-luna-pro","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790105825},{"id":"openai/gpt-6-sol","name":"GPT-6-Sol","tags":["multimodal","text_generation","recently_added","featured","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"10.0000","web_search":"0.00","input_cache_read":"0.2000","input_cache_write":"2.5000","internal_reasoning":"0.00"},"description":"OpenAI's cost-efficient high-end GPT-6 model, between GPT-6 Luna and the flagship GPT-6 Astra, for demanding professional, coding and agentic work, with adjustable reasoning and a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6-sol","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790105825},{"id":"openai/gpt-6-sol-pro","name":"GPT-6-Sol-Pro","tags":["multimodal","text_generation","recently_added","featured","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"10.0000","web_search":"0.00","input_cache_read":"0.2000","input_cache_write":"2.5000","internal_reasoning":"0.00"},"description":"GPT-6 Sol in Pro reasoning mode — spends additional model work on complex tasks at the same per-token rates, with higher latency and token usage","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6-sol-pro","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790105825},{"id":"anthropic/claude-sonnet-5-5","name":"Claude-Sonnet-5.5","tags":["multimodal","text_generation","recently_added","featured","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"10.0000","web_search":"0.00","input_cache_read":"0.2000","input_cache_write":"2.5000","internal_reasoning":"0.00"},"description":"Anthropic's Claude Sonnet 5.5, succeeding Claude Sonnet 5 with near-Opus intelligence at Sonnet speed and price for everyday coding, agentic and enterprise work, with adaptive thinking and a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"canonical_slug":"anthropic/claude-sonnet-5-5","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790636303},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1-Sol","tags":["multimodal","text_generation","recently_added","featured","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"10.0000","web_search":"0.00","input_cache_read":"0.1000","input_cache_write":"2.5000","internal_reasoning":"0.00"},"description":"OpenAI's GPT-6.1 Sol, an upgrade to GPT-6 Sol below the flagship GPT-6 Astra, for agentic coding, computer use and document-heavy professional work, with always-on reasoning and a 1M-token context window","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6.1-sol","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790796380},{"id":"openai/gpt-6.1-sol-pro","name":"GPT-6.1-Sol-Pro","tags":["multimodal","text_generation","recently_added","featured","OpenAI"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"10.0000","web_search":"0.00","input_cache_read":"0.1000","input_cache_write":"2.5000","internal_reasoning":"0.00"},"description":"GPT-6.1 Sol in Pro reasoning mode — spends additional model work on complex tasks at the same per-token rates, with higher latency and token usage","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"canonical_slug":"openai/gpt-6.1-sol-pro","context_length":1050000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1790796380},{"id":"anthropic/claude-haiku-5-5","name":"Claude-Haiku-5.5","tags":["multimodal","text_generation","recently_added","featured","Claude"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":128000},"default":false,"pricing":{"image":"0.00","prompt":"0.1000","request":"0.00","completion":"0.5000","web_search":"0.00","input_cache_read":"0.0100","input_cache_write":"0.1250","internal_reasoning":"0.00"},"description":"Anthropic's Claude Haiku 5.5, the fast, low-cost Claude for high-volume classification, extraction, routing and sub-agent work, with adaptive thinking and a 1M-token context window. Prompts over 128K tokens bill at 5x the input and output prices","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"canonical_slug":"anthropic/claude-haiku-5-5","context_length":1000000,"hugging_face_id":null,"default_parameters":{"top_p":null,"temperature":null,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1791476315},{"id":"gemini/gemini-4-argon","name":"Gemini-4-Argon","tags":["multimodal","text_generation","recently_added","featured","Gemini"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":65536},"default":false,"pricing":{"image":"0.00","prompt":"2.0000","request":"0.00","completion":"10.0000","web_search":"0.00","input_cache_read":"0.1000","internal_reasoning":"0.00"},"description":"Google's flagship reasoning model for complex software engineering, deep math and science, and autonomous multi-step agents — 1M-token context, multimodal input, always-on thinking","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":true,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"canonical_slug":"gemini/gemini-4-argon","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1791920294},{"id":"meta/muse-wonder","name":"Muse-Wonder","tags":["multimodal","text_generation","featured","recently_added","Muse"],"limits":{"tokens_per_minute":null,"requests_per_minute":null,"max_completion_tokens":null},"default":false,"pricing":{"image":"0.00","prompt":"4.0000","request":"0.00","completion":"20.0000","web_search":"0.00","input_cache_read":"0.2000","internal_reasoning":"0.00"},"description":"Meta's frontier reasoning model for complex personal and professional agentic tasks. 1M-token context, text and image input, always-on reasoning (lowest effort: minimal).","architecture":{"modality":"text+image->text","tokenizer":null,"instruct_type":"aligned","input_modalities":["text","image"],"output_modalities":["text"]},"capabilities":{"audio":false,"vision":true,"completion":true,"chat_completions":true,"function_calling":true},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":null},"canonical_slug":"meta/muse-wonder","context_length":1048576,"hugging_face_id":null,"default_parameters":{"top_p":0.9,"temperature":0.7,"frequency_penalty":null},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","temperature","top_p","tools","tool_choice"],"object":"model","owned_by":"meganova","created":1791997352}]}