HASTATModel price explorer Models
Model catalogue
Search source-reported prices, limits, capabilities, and provider availability. Every provider offer stays available.
Fresh · fetched 2026-08-17T20:45:39.427Z · Models.dev(opens in a new tab)
2160 distinct modelsLowest positive metered provider price in USD per 1M tokens; unavailable and not metered are not free-price claims.
| Model | Context / output | Capabilities | Lowest input | Providers |
|---|---|---|---|---|
| DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 · deepseek | 160KOutput 64K | $0.27out $1.12 | 2fresh | |
| Magistral Mediummistral/magistral-medium · magistral-medium | 128KOutput 16K | $2.00out $5.00 | 1fresh | |
| Mistral Sabamistralai/mistral-saba · mistral | 32KOutput 32K | $0.20out $0.59 | 3fresh | |
| DeepSeek R1 Distill Qwen 14Bdeepseek-r1-distill-qwen-14b · qwen | 32KOutput 16K | $0.14out $0.15 | 2fresh | |
| Llama 3.2 1b Instructmeta/llama-3.2-1b-instruct | 128KOutput 4K | $0.010out $0.010 | 2fresh | |
| NVIDIA Nemotron Nano 12B v2 VL BF16nvidia.nemotron-nano-12b-v2 · nemotron | 128KOutput 4K | $0.20out $0.60 | 1fresh | |
| Qwen2.5-VL 72B Instructqwen2-5-vl-72b-instruct · qwen | 128KOutput 8K | $0.25out $0.75 | 3fresh | |
| Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b · llama | 128KOutput 16K | $0.85out $0.85 | 2fresh | |
| OpenAI GPT-4oopenai-gpt-4o · gpt | 128KOutput 16K | $2.50out $10.00 | 1fresh | |
| Azure gpt-4o-miniazure-gpt-4o-mini · gpt | 128KOutput 16K | $0.15out $0.60 | 1fresh | |
| GPT-4o minigpt-4o-mini@eu · gpt-mini | 128KOutput 16K | $0.17out $0.66 | 1fresh | |
| Hermes 2 Pro Llama 3 8Bhermes-2-pro-llama-3-8b · llama | 128KOutput 128K | $0.14out $0.14 | 2fresh | |
| Azure gpt-4oazure-gpt-4o · gpt | 128KOutput 16K | $2.50out $10.00 | 1fresh | |
| Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | 64KOutput 64K | $2.00out $6.00 | 3fresh | |
| Claude 3 Haikuanthropic/claude-3-haiku · claude | 200KOutput 4K | $0.25out $1.25 | 3fresh | |
| Mistral Large 2411mistralai/mistral-large · mistral-large | 128KOutput 256K | $2.00out $6.00 | 3fresh | |
| GPT-4 Turbo Previewopenai/gpt-4-turbo-preview · gpt | 128KOutput 4K | $10.00out $30.00 | 3fresh | |
| DeepSeek V4 Flash 0731deepseek-v4-flash:0731 · deepseek-flash | 1.05MOutput 1.05M | Unavailableper 1M tokens | 1fresh | |
| Gemini Omni Flash Previewgemini-omni-flash-preview · gemini | 1MOutput 64K | $1.50out $9.00 | 2fresh | |
| GLM 5.2z-ai/glm-5.2-free · glm | 1MOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Mistral Code Latestmistral-code-latest · mistral | 256KOutput 32K | $0.30out $0.90 | 1fresh | |
| Mellum2 12B A2.5Bjetbrains/mellum2-12b-a2.5b-instruct | 128KOutput 128K | $0.050out $0.10 | 1fresh | |
| DeepSeek V4 Prodeepseek-v4-pro:free · deepseek-thinking | 1MOutput 384K | Unavailableper 1M tokens | 1fresh | |
| Kimi K2.6 Fastkimi-k2.6-fast · kimi-k2 | 256KOutput 256K | $0.69out $3.22 | 1fresh | |
| Qwen3.6 35B-A3Bqwen3-6-35b · qwen | 16KOutput 16K | $5.00out $10.00 | 1fresh | |
| Grok 4.20 Non-Reasoningxai/grok-4.20-non-reasoning · grok | 2MOutput 2M | $1.25out $2.50 | 1fresh | |
| Grok 4.2 Fast Non Reasoningx-ai/grok-4.2-fast-non-reasoning | 2MOutput 30K | $3.00out $9.00 | 1fresh | |
| Agentic Chatduo-chat-gpt-5-4-mini · gpt-mini | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Agentic Chatduo-chat-gpt-5-4-nano · gpt-nano | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Mistral Small 3.2mistral-small · mistral-small | 128KOutput 16K | $0.075out $0.20 | 2fresh | |
| grok-4.20-beta-0309-non-reasoninggrok-4.20-beta-0309-non-reasoning | 2MOutput 30K | $2.00out $6.00 | 1fresh | |
| Grok 4.20 Beta Non-Reasoningxai/grok-4.20-non-reasoning-beta · grok | 2MOutput 2M | $1.25out $2.50 | 1fresh | |
| Agentic Chatduo-chat-gpt-5-3-codex · gpt-codex | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Llama-3.1-Nemotron-Ultra-253B-v1nvidia/llama-3_1-nemotron-ultra-253b-v1 · nemotron | 128KOutput 4K | $0.60out $1.80 | 1fresh | |
| Kimi K2.5 Fastkimi-k2.5-fast · kimi-k2 | 256KOutput 256K | $0.52out $2.59 | 1fresh | |
| Agentic Chatduo-chat-gpt-5-2 · gpt | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Agentic Chatduo-chat-gpt-5-2-codex · gpt-codex | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Agentic Chatduo-chat-gpt-5-1 · gpt | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Agentic Chatduo-chat-gpt-5-codex · gpt-codex | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Agentic Chatduo-chat-gpt-5-mini · gpt-mini | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Palmyra X5writer/palmyra-x5 · palmyra | 1.04MOutput 250K | $0.60out $6.00 | 3fresh | |
| GPT Audioopenai/gpt-audio · gpt | 128KOutput 16K | $2.50out $10.00 | 2fresh | |
| GPT Audio Miniopenai/gpt-audio-mini · o-mini | 128KOutput 16K | $0.60out $2.40 | 2fresh | |
| ERNIE 4.5 300B A47Bbaidu/ernie-4.5-300b-a47b-paddle · ernie | 123KOutput 12K | $0.28out $1.10 | 2fresh | |
| baidu/ERNIE-4.5-300B-A47Bbaidu/ernie-4.5-300b-a47b · ernie | 131KOutput 131K | $0.28out $1.10 | 2fresh | |
| inclusionAI/Ling-flash-2.0inclusionai/ling-flash-2.0 · ling | 131KOutput 131K | $0.14out $0.57 | 2fresh | |
| Qwen/Qwen3-Next-80B-A3B-Instructqwen.qwen3-next-80b-a3b · qwen | 262KOutput 262K | $0.14out $1.40 | 1fresh | |
| GPT-5.1openai-gpt-5.1 · gpt | 400KOutput 128K | Unavailableper 1M tokens | 1fresh | |
| Granite-4.0-H-Smallibm/granite-4-h-small · granite | 128KOutput 128K | $0.064out $0.27 | 1fresh | |
| DeepSeek V3.1 Terminusdeepseek-ai/deepseek-v3.1-terminus:thinking · deepseek-thinking | 128KOutput 64K | $0.25out $0.70 | 1fresh |