{"data":[{"model_info":{"description":"Fast, efficient multimodal model capable of frontier-level agentic work.","huggingface_id":"deepseek-ai/DeepSeek-V4.1-Flash","id":"01a08a5f-6789-75e3-ae82-c2f3a6d04c76","input_cost_per_1m_tokens":0.2,"is_preview":false,"key":"deepseek-ai/DeepSeek-V4.1-Flash","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png","max_input_tokens":1048576,"mode":"chat","model_type":"llm","model_version":"df42c109f1de","output_cost_per_1m_tokens":0.7,"parameters_count":"484.6B","reasoning_efforts":["low","high","max"],"supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":true,"supports_response_schema":false,"supports_vision":true},"model_name":"deepseek-ai/DeepSeek-V4.1-Flash"},{"model_info":{"cache_read_input_cost_per_1m_tokens":1.13,"description":"Frontier MoE reasoning model with 1M context for long-horizon coding and knowledge work.","display_name":"moonshotai/Kimi-K3","huggingface_id":"moonshotai/Kimi-K3","id":"019fa435-b310-738d-82c3-bd9f66e47ef3","input_cost_per_1m_tokens":4.73,"is_preview":false,"key":"moonshotai/Kimi-K3","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg","max_input_tokens":1048576,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":23.63,"parameters_count":"2.8T","precision":"MXFP4","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":true},"model_name":"moonshotai/Kimi-K3"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.35,"description":"MoE reasoning model with 1M-token context for long-horizon agentic tasks.","huggingface_id":"zai-org/GLM-5.3","id":"01a04993-0be2-7cae-8cd1-3c314c22194c","input_cost_per_1m_tokens":1.47,"is_preview":false,"key":"zai-org/GLM-5.3","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png","max_input_tokens":1048576,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":4.62,"parameters_count":"753.3B","precision":"FP8","reasoning_efforts":[],"supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"zai-org/GLM-5.3"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.35,"description":"Rerouted to GLM 5.3. MoE reasoning model with 1M-token context for long-horizon agentic tasks.","huggingface_id":"zai-org/GLM-5.2-FP8","id":"019ed231-18ab-74ff-9689-c53408be446e","input_cost_per_1m_tokens":1.47,"is_preview":false,"key":"zai-org/GLM-5.2-FP8","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png","max_input_tokens":1048576,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":4.62,"parameters_count":"753B","precision":"FP8","superseded_by_model_name":"zai-org/GLM-5.3","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"zai-org/GLM-5.2-FP8"},{"model_info":{"description":"MoE multimodal, efficient reasoning model with 1M-token context for long-horizon agentic tasks.","huggingface_id":"zai-org/GLM-5.3-Flash","id":"01a05906-082b-7aa2-9d8b-9a8aab5c196b","input_cost_per_1m_tokens":0.21,"is_preview":true,"key":"zai-org/GLM-5.3-Flash","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png","max_input_tokens":1048572,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":0.63,"parameters_count":"321.3B","precision":"FP8","reasoning_efforts":["low","high","max"],"supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":true,"supports_response_schema":false,"supports_vision":true},"model_name":"zai-org/GLM-5.3-Flash"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.15,"description":"MoE model for complex, multi-step instructions.","display_name":"mistralai/Mistral-Large-3-675B-Instruct-2512","huggingface_id":"mistralai/Mistral-Large-3-675B-Instruct-2512","id":"019d82af-dd4c-7110-90c9-e4dd9485f503","input_cost_per_1m_tokens":0.6,"is_preview":false,"key":"mistralai/Mistral-Large-3-675B-Instruct-2512","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":1.73,"parameters_count":"675B","precision":"FP8","reasoning_efforts":[],"supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":true},"model_name":"mistralai/Mistral-Large-3-675B-Instruct-2512"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.15,"description":"MoE vision-language reasoning model with native multimodal and agentic capabilities.","huggingface_id":"Qwen/Qwen3.5-397B-A17B-FP8","id":"019ca022-fe62-75c1-b9ec-10b3defc4ee8","input_cost_per_1m_tokens":0.63,"is_preview":true,"key":"Qwen/Qwen3.5-397B-A17B","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":3.78,"parameters_count":"397B","precision":"FP8","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":true},"model_name":"Qwen/Qwen3.5-397B-A17B"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.05,"description":"Multimodal MoE reasoning model with unified video, audio, image, and text understanding.","huggingface_id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8","id":"019dd85c-fa72-7491-82d2-fa9c7fa91894","input_cost_per_1m_tokens":0.16,"is_preview":true,"key":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":1.05,"parameters_count":"30B","precision":"FP8","supports_audio_input":true,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":true},"model_name":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.08,"description":"Hybrid LatentMoE reasoning/chat model with configurable thinking, tool use, and up to 1M context.","huggingface_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","id":"019ce22a-b12a-74c8-831a-5842e2c148c1","input_cost_per_1m_tokens":0.32,"is_preview":true,"key":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png","max_input_tokens":1000000,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":0.69,"parameters_count":"120B total / 12B active","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.05,"description":"Fast, cost-efficient MoE reasoning model for everyday chat and instructions.","huggingface_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","id":"019aeb47-8299-7056-9ca9-cae178944f9f","input_cost_per_1m_tokens":0.21,"is_preview":true,"key":"Qwen/Qwen3-30B-A3B-Instruct-2507","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":0.74,"parameters_count":"30B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":false},"model_name":"Qwen/Qwen3-30B-A3B-Instruct-2507"},{"model_info":{"description":"Fast end-to-end OCR model for document text extraction.","huggingface_id":"lightonai/LightOnOCR-2-1B","id":"019c8e70-fd3d-7469-b2da-399528770335","input_cost_per_1m_tokens":1.08,"is_preview":true,"key":"lightonai/LightOnOCR-2-1B","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/1651597775471-62715572ab9243b5d40cbb1d.png","max_input_tokens":4096,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":5.38,"parameters_count":"1B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":true},"model_name":"lightonai/LightOnOCR-2-1B"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.35,"description":"Deprecated in favour of GLM 5.2 - will reroute all requests to GLM 5.2. Targeting complex systems engineering and long-horizon agentic tasks.","display_tags":["code"],"huggingface_id":"zai-org/GLM-5.1-FP8","id":"019d785d-c7ef-7353-a8b9-3673f33fbc24","input_cost_per_1m_tokens":1.47,"is_preview":false,"key":"zai-org/GLM-5.1-FP8","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png","max_input_tokens":202752,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":4.62,"parameters_count":"754B","precision":"FP8","superseded_by_model_name":"zai-org/GLM-5.3","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"zai-org/GLM-5.1-FP8"},{"model_info":{"description":"Mistral's flagship merged dense model.","huggingface_id":"mistralai/Mistral-Medium-3.5-128B","id":"01a0678f-fa5f-7552-be5a-0c8ae0d50396","input_cost_per_1m_tokens":1.65,"is_preview":false,"key":"mistralai/Mistral-Medium-3.5-128B","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","model_version":"22b2b868a156","output_cost_per_1m_tokens":8.25,"parameters_count":"127.7B","reasoning_efforts":["low","medium","high","max"],"supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":true,"supports_response_schema":false,"supports_vision":true},"model_name":"mistralai/Mistral-Medium-3.5-128B"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.35,"display_name":"meta-models/muse-glimmer-30b","huggingface_id":"meta-models/Muse-Glimmer-30B","id":"01a03d49-9da2-7b91-910e-a8ce4408f0da","input_cost_per_1m_tokens":0.7,"is_preview":true,"key":"meta-models/muse-glimmer-30b","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/64c115d1f661ace7c4022432/EbzfQisFJBEcKWDWLyV5O.png","max_input_tokens":131072,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":3.5,"parameters_count":"30B","precision":"FP8","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":false,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":true},"model_name":"meta-models/muse-glimmer-30b"},{"model_info":{"description":" ","display_name":"Qwen/Qwen3Guard-Gen-8B","display_tags":["Content Safety","Guard Model"],"huggingface_id":"Qwen/Qwen3Guard-Gen-8B","id":"01a02415-0361-78e3-933a-2c9d4917c451","is_preview":false,"key":"Qwen/Qwen3Guard-Gen-8B","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png","max_input_tokens":32768,"mode":"chat","model_type":"llm","parameters_count":"8.2B","precision":"bfloat16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"Qwen/Qwen3Guard-Gen-8B"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.05,"description":"Multimodal dense Qwen model with coding, professional work, research, and long-horizon capabilities.","huggingface_id":"Qwen/Qwen3.8-27B","id":"01a019e3-8ce0-7c4f-a73c-4d7835f0245c","input_cost_per_1m_tokens":0.21,"is_preview":false,"key":"Qwen/Qwen3.8-27B-FP8","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":0.74,"parameters_count":"27B","precision":"FP8","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":true},"model_name":"Qwen/Qwen3.8-27B-FP8"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.5,"description":"NVIDIA Nemotron-3-Nano-30B-A3B-BF16 is a commercially ready 30B-parameter hybrid MoE model optimized for efficient reasoning and non-reasoning tasks, with configurable reasoning and multilingual support.","huggingface_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","id":"01a01548-9cd3-75dc-96b1-77f2928e466a","input_cost_per_1m_tokens":1,"is_preview":true,"key":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":3,"parameters_count":"30B","precision":"FP8","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":false},"model_name":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},{"model_info":{"description":"Multilingual, streaming Automatic Speech Recognition (ASR) model engineered to deliver high-quality multilingual transcription across both low-latency streaming and high-throughput batch workloads.","huggingface_id":"nvidia/nemotron-3.5-asr-streaming-0.6b","id":"019f9a4c-d61e-7a2e-8b55-4454f9a7358e","input_cost_per_1m_tokens":0,"is_preview":false,"key":"nvidia/nemotron-3.5-asr-streaming-0.6b","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png","max_input_tokens":0,"mode":null,"model_type":"audio","output_cost_per_1m_tokens":0.25,"parameters_count":"600M","precision":"BF16","reasoning_efforts":[],"supports_audio_input":true,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"nvidia/nemotron-3.5-asr-streaming-0.6b"},{"model_info":{"description":"Specialized for document OCR and structured text extraction.","huggingface_id":"zai-org/GLM-OCR","id":"019e2268-1f08-76c7-b26b-03e58fa582ce","input_cost_per_1m_tokens":0.13,"is_preview":true,"key":"zai-org/GLM-OCR","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png","max_input_tokens":8192,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":0.56,"parameters_count":"0.9B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":true},"model_name":"zai-org/GLM-OCR"},{"model_info":{"description":"Fast, cost-efficient generation and inpainting model for high-throughput workflows.","huggingface_id":"Tongyi-MAI/Z-Image-Turbo","id":"019b7f81-b1d5-7600-a767-0bbdc6a032ef","input_cost_per_1m_tokens":0,"is_preview":true,"key":"Tongyi-MAI/Z-Image-Turbo","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/64379d79fac5ea753f1c10f3/fxHO6QoYjdv9_LTyiUD3g.jpeg","max_input_tokens":512,"mode":"image_generation","model_type":"image","output_cost_per_1m_tokens":0.25,"parameters_count":"6B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":true},"model_name":"Tongyi-MAI/Z-Image-Turbo"},{"model_info":{"description":"Cross-lingual relevance scoring to refine search results.","huggingface_id":"BAAI/bge-reranker-v2-m3","id":"019b333b-fd8b-74fa-bd02-0e32f8384b12","input_cost_per_1m_tokens":0.1,"key":"BAAI/bge-reranker-v2-m3","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664511063789-632c234f42c386ebd2710434.png","max_input_tokens":8192,"mode":"rerank","model_type":"reranker","output_cost_per_1m_tokens":0.51,"parameters_count":"568M","precision":"FP16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"BAAI/bge-reranker-v2-m3"},{"model_info":{"description":"Versatile multi-retrieval supporting dense, sparse, and ColBERT methods.","huggingface_id":"BAAI/bge-m3","id":"019aeb47-82b3-771d-907a-ef52fb6ea376","input_cost_per_1m_tokens":0.12,"key":"BAAI/bge-m3","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664511063789-632c234f42c386ebd2710434.png","max_input_tokens":8192,"mode":"embedding","model_type":"embedding","output_cost_per_1m_tokens":0.6,"parameters_count":"567M","precision":"FP16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"BAAI/bge-m3"},{"model_info":{"description":"This model is in private preview, we are constantly adjusting it and taking it offline, please do not rely on it. Reasoning model with configurable thinking mode and 256K context window.","display_tags":["Private"],"huggingface_id":"google/gemma-4-31B-it","id":"019d5212-5bab-748c-b768-e1c6cc1e405e","input_cost_per_1m_tokens":0.42,"is_preview":false,"key":"google/gemma-4-31B-it","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/WtA3YYitedOr9n02eHfJe.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":1.05,"parameters_count":"31B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":true},"model_name":"google/gemma-4-31B-it"},{"model_info":{"description":"Best-in-class ASR model with 5.42 WER on Open ASR Leaderboard. Supports 14 languages.","huggingface_id":"CohereLabs/cohere-transcribe-03-2026","id":"019d4e59-fc8f-73ca-a39e-8a4da0200310","input_cost_per_1m_tokens":0,"is_preview":true,"key":"CohereLabs/cohere-transcribe-03-2026","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png","max_input_tokens":32768,"mode":null,"model_type":"audio","output_cost_per_1m_tokens":0.15,"parameters_count":"2B","precision":"BF16","supports_audio_input":true,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"CohereLabs/cohere-transcribe-03-2026"},{"model_info":{"id":"019be5e1-505f-7072-9a8a-b1617c0f878f","input_cost_per_1m_tokens":0,"key":"ResembleAI/chatterbox-multilingual","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/6000a0456a2a91af974298cf/qmxSbcVBCwUtVez918IkQ.png","max_input_tokens":4000,"mode":null,"model_type":"audio","output_cost_per_1m_tokens":0.15,"parameters_count":"500M","precision":"FP16","supports_audio_input":false,"supports_audio_output":true,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"ResembleAI/chatterbox-multilingual"},{"model_info":{"description":"Fast and reliable model across 25 languages for production workloads.","huggingface_id":"nvidia/parakeet-tdt-0.6b-v3","id":"019b0d03-1350-74ea-a4e8-0e0826ae6b3f","input_cost_per_1m_tokens":0,"is_preview":false,"key":"nvidia/parakeet-tdt-0.6b-v3","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png","max_input_tokens":4096,"mode":null,"model_type":"audio","output_cost_per_1m_tokens":0.15,"parameters_count":"0.6B","precision":"FP16","supports_audio_input":true,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"nvidia/parakeet-tdt-0.6b-v3"},{"model_info":{"description":"Fast and reliable model across 25 languages for production workloads.","huggingface_id":"nvidia/parakeet-tdt-0.6b-v3","id":"019aeb47-828d-75f6-88b2-cef87791eec2","input_cost_per_1m_tokens":0,"is_preview":false,"key":"nvidia/parakeet-tdt-0.6b-v2","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png","max_input_tokens":4096,"mode":null,"model_type":"audio","output_cost_per_1m_tokens":0.15,"parameters_count":"0.6B","precision":"FP16","supports_audio_input":true,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":false,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"nvidia/parakeet-tdt-0.6b-v2"},{"model_info":{"description":"Leading open-source text embedding and ranking model, currently #1 on MTEB leaderboard.","display_tags":["48"],"huggingface_id":"Qwen/Qwen3-Embedding-8B","id":"019c044e-0ba1-73c0-b999-9e3c087fbe7c","input_cost_per_1m_tokens":0.26,"key":"Qwen/Qwen3-Embedding-8B","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png","max_input_tokens":12288,"mode":"embedding","model_type":"embedding","output_cost_per_1m_tokens":0.1,"parameters_count":"8B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"Qwen/Qwen3-Embedding-8B"},{"model_info":{"description":"Balances speed and cost for general-purpose tasks. Supports fine-tuning.","display_tags":["Internal"],"id":"019be5e1-5002-75ee-82ef-5dfc18e0dd7a","input_cost_per_1m_tokens":0.73,"is_preview":true,"key":"mistralai/Ministral-3-14B-Instruct-2512","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":3.63,"parameters_count":"14B","precision":"FP8","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":true},"model_name":"mistralai/Ministral-3-14B-Instruct-2512"},{"model_info":{"description":"Lightweight, retrieval-focused model for search applications.","huggingface_id":"infly/inf-retriever-v1","id":"019be5e1-519a-73b3-b053-5886d4e13910","input_cost_per_1m_tokens":0.09,"key":"infly/inf-retriever-v1","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ed9862679c2cc40abb55d2/0n6g0jngiKkRjaEoAvPmM.png","max_input_tokens":512,"mode":"embedding","model_type":"embedding","output_cost_per_1m_tokens":0.45,"parameters_count":"110M","precision":"FP16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"infly/inf-retriever-v1"},{"model_info":{"description":"Task-prefixed queries improve retrieval accuracy across 94 languages.","huggingface_id":"intfloat/multilingual-e5-large-instruct","id":"019aeb47-8281-77da-8235-2a3840e7a724","input_cost_per_1m_tokens":0.12,"key":"intfloat/multilingual-e5-large-instruct","logo_url":"https://huggingface.co/avatars/5a1ee74c2dbe349a6ec9843a1599d281.svg","max_input_tokens":8192,"mode":"embedding","model_type":"embedding","output_cost_per_1m_tokens":0.6,"parameters_count":"560M","precision":"FP16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"intfloat/multilingual-e5-large-instruct"},{"model_info":{"description":"Fastest, lowest-cost option for English similarity tasks.","huggingface_id":"sentence-transformers/all-MiniLM-L6-v2","id":"019aeb47-82a6-73ba-8bba-f0c05b69b583","input_cost_per_1m_tokens":0.09,"key":"sentence-transformers/all-MiniLM-L6-v2","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/1609621322398-5eff4688ff69163f6f59e66c.png","max_input_tokens":512,"mode":"embedding","model_type":"embedding","output_cost_per_1m_tokens":0.45,"parameters_count":"22M","precision":"FP16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"sentence-transformers/all-MiniLM-L6-v2"},{"model_info":{"description":"Specialized for document OCR and structured text extraction.","huggingface_id":"deepseek-ai/DeepSeek-OCR","id":"019be5e1-5079-760d-ad9a-62f2b5d83949","input_cost_per_1m_tokens":0.11,"is_preview":true,"key":"deepseek-ai/DeepSeek-OCR","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png","max_input_tokens":8192,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":0.54,"parameters_count":"3B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":false,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":true},"model_name":"deepseek-ai/DeepSeek-OCR"},{"model_info":{"deprecation_date":"2026-08-31","description":"","huggingface_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","id":"019aeb47-824e-77e3-acc0-ec956a8f7db1","input_cost_per_1m_tokens":1.08,"is_preview":true,"key":"Qwen/Qwen3-VL-235B-A22B-Thinking","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png","max_input_tokens":262144,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":5.38,"parameters_count":"235B","precision":"FP8","reasoning_efforts":[],"superseded_by_model_name":"Qwen/Qwen3.5-397B-A17B","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":true,"supports_vision":true},"model_name":"Qwen/Qwen3-VL-235B-A22B-Thinking"},{"model_info":{"cache_read_input_cost_per_1m_tokens":0.05,"description":"Reasoning and fast MoE model with configurable thinking depth.","huggingface_id":"openai/gpt-oss-120b","id":"019aeb47-8269-7544-932a-394f62cd12c2","input_cost_per_1m_tokens":0.17,"is_preview":false,"key":"openai/gpt-oss-120b","logo_url":"https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png","max_input_tokens":131072,"mode":"chat","model_type":"llm","output_cost_per_1m_tokens":0.63,"parameters_count":"120B","precision":"BF16","supports_audio_input":false,"supports_audio_output":false,"supports_function_calling":true,"supports_multilingual":true,"supports_reasoning":false,"supports_response_schema":false,"supports_vision":false},"model_name":"openai/gpt-oss-120b"}]}