{"deepseek-ai/DeepSeek-R1-0528":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"DeepSeek R1 0528 model."},"deepseek-ai/DeepSeek-R1":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"DeepSeek R1 model."},"deepseek-ai/DeepSeek-V3":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-V3"},"deepseek-ai/DeepSeek-V3.1":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"DeepSeek V3.1 model."},"deepseek-ai/DeepSeek-V3.1-Terminus":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.23,"outputPrice":0.9,"description":"DeepSeek‑V3.1‑Terminus is an update to V3.1 that improves language consistency by reducing CN/EN mix‑ups and eliminating random characters, while strengthening agent capabilities with notably better Code Agent and Search Agent performance."},"deepseek-ai/DeepSeek-V3.1-turbo":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1,"outputPrice":3,"description":"DeepSeek-V3.1-turbo is an FP8, speculative-decoding turbo variant optimized for ultra-fast single-shot queries (~200 TPS), with outputs close to the originals and solid function calling/reasoning/structured output, priced at $1/M input and $3/M output tokens, using 2× quota per request and not intended for bulk workloads."},"deepseek-ai/DeepSeek-V3.2-Exp":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":0.35,"description":"DeepSeek-V3.2-Exp is an experimental LLM that introduces DeepSeek Sparse Attention to improve long‑context training and inference efficiency while maintaining performance comparable to V3.1‑Terminus."},"unsloth/Llama-3.3-70B-Instruct":{"maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Unsloth Llama 3.3 70B Instruct model."},"chutesai/Llama-4-Scout-17B-16E-Instruct":{"maxTokens":32768,"contextWindow":512000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"ChutesAI Llama 4 Scout 17B Instruct model, 512K context."},"unsloth/Mistral-Nemo-Instruct-2407":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: unsloth/Mistral-Nemo-Instruct-2407"},"unsloth/gemma-3-12b-it":{"maxTokens":1048576,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: unsloth/gemma-3-12b-it"},"NousResearch/DeepHermes-3-Llama-3-8B-Preview":{"maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Nous DeepHermes 3 Llama 3 8B Preview model."},"unsloth/gemma-3-4b-it":{"maxTokens":1048576,"contextWindow":96000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: unsloth/gemma-3-4b-it"},"nvidia/Llama-3_3-Nemotron-Super-49B-v1":{"maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Nvidia Llama 3.3 Nemotron Super 49B model."},"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1":{"maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Nvidia Llama 3.1 Nemotron Ultra 253B model."},"chutesai/Llama-4-Maverick-17B-128E-Instruct-FP8":{"maxTokens":32768,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"ChutesAI Llama 4 Maverick 17B Instruct FP8 model."},"deepseek-ai/DeepSeek-V3-Base":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"DeepSeek V3 Base model."},"deepseek-ai/DeepSeek-R1-Zero":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"DeepSeek R1 Zero model."},"deepseek-ai/DeepSeek-V3-0324":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"DeepSeek V3 (0324) model."},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Qwen3 235B A22B Instruct 2507 model with 262K context window."},"Qwen/Qwen3-235B-A22B":{"maxTokens":40960,"contextWindow":40960,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-235B-A22B"},"Qwen/Qwen3-32B":{"maxTokens":40960,"contextWindow":40960,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-32B"},"Qwen/Qwen3-30B-A3B":{"maxTokens":40960,"contextWindow":40960,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-30B-A3B"},"Qwen/Qwen3-14B":{"maxTokens":40960,"contextWindow":40960,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-14B"},"Qwen/Qwen3-8B":{"maxTokens":32768,"contextWindow":40960,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Qwen3 8B model."},"microsoft/MAI-DS-R1-FP8":{"maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Microsoft MAI-DS-R1 FP8 model."},"tngtech/DeepSeek-R1T-Chimera":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: tngtech/DeepSeek-R1T-Chimera"},"zai-org/GLM-4.5-Air":{"maxTokens":32768,"contextWindow":151329,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"GLM-4.5-Air model with 151,329 token context window and 106B total parameters with 12B activated."},"zai-org/GLM-4.5-FP8":{"maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"GLM-4.5-FP8 model with 128k token context window, optimized for agent-based applications with MoE architecture."},"zai-org/GLM-4.5-turbo":{"maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1,"outputPrice":3,"description":"GLM-4.5-turbo model with 128K token context window, optimized for fast inference."},"zai-org/GLM-4.6-FP8":{"maxTokens":202752,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-4.6-FP8"},"zai-org/GLM-4.6-turbo":{"maxTokens":202752,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1.15,"outputPrice":3.25,"description":"GLM-4.6-turbo model with 200K-token context window, optimized for fast inference."},"meituan-longcat/LongCat-Flash-Thinking-FP8":{"maxTokens":32768,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"LongCat Flash Thinking FP8 model with 128K context window, optimized for complex reasoning and coding tasks."},"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8":{"maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Qwen3 Coder 480B A35B Instruct FP8 model, optimized for coding tasks."},"moonshotai/Kimi-K2-Instruct-75k":{"maxTokens":32768,"contextWindow":75000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.1481,"outputPrice":0.5926,"description":"Moonshot AI Kimi K2 Instruct model with 75k context window."},"moonshotai/Kimi-K2-Instruct-0905":{"maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.1999,"outputPrice":0.8001,"description":"Moonshot AI Kimi K2 Instruct 0905 model with 256k context window."},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-235B-A22B-Thinking-2507"},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-Next-80B-A3B-Instruct"},"Qwen/Qwen3-Next-80B-A3B-Thinking":{"maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Reasoning-first model with structured thinking traces for multi-step problems, math proofs, and code synthesis."},"Qwen/Qwen3-VL-235B-A22B-Thinking":{"maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.16,"outputPrice":0.65,"description":"Qwen3‑VL‑235B‑A22B‑Thinking is an open‑weight MoE vision‑language model (235B total, ~22B activated) optimized for deliberate multi‑step reasoning with strong text‑image‑video understanding and long‑context capabilities."},"deepseek-ai/DeepSeek-V3-0324-TEE":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-V3-0324-TEE"},"chutesai/Mistral-Small-3.1-24B-Instruct-2503":{"maxTokens":131072,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: chutesai/Mistral-Small-3.1-24B-Instruct-2503"},"deepseek-ai/DeepSeek-V3.2-TEE":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-V3.2-TEE"},"Qwen/Qwen3-235B-A22B-Instruct-2507-TEE":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-235B-A22B-Instruct-2507-TEE"},"openai/gpt-oss-120b-TEE":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: openai/gpt-oss-120b-TEE"},"zai-org/GLM-4.6-TEE":{"maxTokens":202752,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-4.6-TEE"},"tngtech/DeepSeek-TNG-R1T2-Chimera":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: tngtech/DeepSeek-TNG-R1T2-Chimera"},"zai-org/GLM-4.7-TEE":{"maxTokens":202752,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-4.7-TEE"},"moonshotai/Kimi-K2.5-TEE":{"maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: moonshotai/Kimi-K2.5-TEE"},"NousResearch/Hermes-4-70B":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: NousResearch/Hermes-4-70B"},"deepseek-ai/DeepSeek-V3.1-TEE":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-V3.1-TEE"},"zai-org/GLM-5-TEE":{"maxTokens":202752,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-5-TEE"},"unsloth/gemma-3-27b-it":{"maxTokens":1048576,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: unsloth/gemma-3-27b-it"},"deepseek-ai/DeepSeek-R1-0528-TEE":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-R1-0528-TEE"},"NousResearch/Hermes-4-405B-FP8-TEE":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: NousResearch/Hermes-4-405B-FP8-TEE"},"chutesai/Mistral-Small-3.2-24B-Instruct-2506":{"maxTokens":131072,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: chutesai/Mistral-Small-3.2-24B-Instruct-2506"},"deepseek-ai/DeepSeek-V3.1-Terminus-TEE":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-V3.1-Terminus-TEE"},"OpenGVLab/InternVL3-78B-TEE":{"maxTokens":32768,"contextWindow":32768,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: OpenGVLab/InternVL3-78B-TEE"},"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE"},"Qwen/Qwen2.5-Coder-32B-Instruct":{"maxTokens":32768,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen2.5-Coder-32B-Instruct"},"Qwen/Qwen3-Coder-Next":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-Coder-Next"},"Qwen/Qwen3-30B-A3B-Instruct-2507":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-30B-A3B-Instruct-2507"},"Qwen/Qwen2.5-72B-Instruct":{"maxTokens":32768,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen2.5-72B-Instruct"},"Qwen/Qwen2.5-VL-72B-Instruct-TEE":{"maxTokens":32768,"contextWindow":32768,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen2.5-VL-72B-Instruct-TEE"},"Qwen/Qwen2.5-VL-32B-Instruct":{"maxTokens":128000,"contextWindow":16384,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen2.5-VL-32B-Instruct"},"zai-org/GLM-4.6V":{"maxTokens":131072,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-4.6V"},"deepseek-ai/DeepSeek-R1-Distill-Llama-70B":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B"},"unsloth/Mistral-Small-24B-Instruct-2501":{"maxTokens":32768,"contextWindow":32768,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: unsloth/Mistral-Small-24B-Instruct-2501"},"zai-org/GLM-4.5-TEE":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-4.5-TEE"},"NousResearch/DeepHermes-3-Mistral-24B-Preview":{"maxTokens":32768,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: NousResearch/DeepHermes-3-Mistral-24B-Preview"},"moonshotai/Kimi-K2-Thinking-TEE":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: moonshotai/Kimi-K2-Thinking-TEE"},"deepseek-ai/DeepSeek-R1-TEE":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-R1-TEE"},"MiniMaxAI/MiniMax-M2.1-TEE":{"maxTokens":196608,"contextWindow":196608,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: MiniMaxAI/MiniMax-M2.1-TEE"},"openai/gpt-oss-20b":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: openai/gpt-oss-20b"},"zai-org/GLM-4.7-FP8":{"maxTokens":202752,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-4.7-FP8"},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: Qwen/Qwen3-VL-235B-A22B-Instruct"},"zai-org/GLM-4.7-Flash":{"maxTokens":202752,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: zai-org/GLM-4.7-Flash"},"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16":{"maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},"tngtech/R1T2-Chimera-Speed":{"maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: tngtech/R1T2-Chimera-Speed"},"deepseek-ai/DeepSeek-V3.2-Speciale-TEE":{"maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: deepseek-ai/DeepSeek-V3.2-Speciale-TEE"},"NousResearch/Hermes-4-14B":{"maxTokens":40960,"contextWindow":40960,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: NousResearch/Hermes-4-14B"},"rednote-hilab/dots.ocr":{"maxTokens":131072,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Chutes AI model: rednote-hilab/dots.ocr"}}