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 |
|---|---|---|---|---|
| MiniMax-M2.7accounts/fireworks/models/minimax-m2p7 · minimax | 192KOutput 192K | $0.30out $1.20 | 1fresh | |
| Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it:free · gemma | 256KOutput 32K | Unavailableper 1M tokens | 1fresh | |
| Gemma 4 31B IT FP8gemma-4-31b-it-fp8 · gemma | 256KOutput 32K | Unavailableper 1M tokens | 1fresh | |
| Agnes 1.5 Prosapiens-ai/agnes-1.5-pro | 256KOutput 256K | $0.16out $0.80 | 1fresh | |
| MiniMax M2.5minimax.minimax-m2.5 · minimax | 192KOutput 96K | $0.30out $1.20 | 1fresh | |
| Nemotron 3 Super 120B A12Bnemotron-3-super-120b-a12b:free · nemotron | 256KOutput 256K | Unavailableper 1M tokens | 3fresh | |
| Nemotron 3 Super 120Bnemotron-3-super-120b · nemotron | 256KOutput 256K | $0.30out $0.90 | 1fresh | |
| Agentic Chatduo-chat-gpt-5-4 · gpt | 1.05MOutput 128K | Unavailableper 1M tokens | 1fresh | |
| GPT-5.4gpt-5.4:free · gpt | 1.05MOutput 128K | Unavailableper 1M tokens | 1fresh | |
| GPT OSS 120B High Throughputopenai/chat-completion/models/gpt-oss-120b-high-throughput · gpt-oss | 128KOutput 16K | $0.090out $0.36 | 1fresh | |
| Trinity Miniarcee_ai/afm/models/trinity-mini · trinity | 128KOutput 128K | $0.045out $0.15 | 1fresh | |
| Devstral 2 123Bmistral.devstral-2-123b · devstral | 256KOutput 8K | $0.40out $2.00 | 1fresh | |
| Qwen3.5 397B-A17Bqwen3.5-397b-a17b:free · qwen | 256KOutput 64K | Unavailableper 1M tokens | 1fresh | |
| MiniMax-M2.5minimax-m2.5-230b · minimax | 192KOutput 64K | $0.25out $1.20 | 1fresh | |
| Free Models Routerfree | 256KOutput 32K | Unavailableper 1M tokens | 2fresh | |
| MiniMax-M2 Herminimax/m2-her · minimax | 200KOutput 131K | $0.30out $1.20 | 1fresh | |
| Kat Coder Prokwaipilot/kat-coder-pro | 256KOutput 128K | $0.30out $1.20 | 1fresh | |
| solar-pro3solar-pro3 · solar-pro | 128KOutput 8K | $0.15out $0.25 | 2fresh | |
| Seed 1.8volcengine/doubao-seed-1-8 · seed | 256KOutput 64K | $0.12out $0.29 | 1fresh | |
| GLM 4.6 Derestricted v5glm-4.6-derestricted-v5 · glm | 128KOutput 8K | $0.40out $1.50 | 1fresh | |
| Ministral 3 14B Instruct 2512mistralai/ministral-14b-instruct-2512 · ministral | 256KOutput 32K | $0.10out $0.40 | 2fresh | |
| Mistral Large 3mistral-large-3 · mistral-large | 256KOutput 256K | $0.50out $1.50 | 2fresh | |
| Devstral 2mistral/devstral-medium-latest · devstral | 256KOutput 256K | $0.40out $2.00 | 1fresh | |
| DeepSeek-V3.2-Thinkingdeepseek-v3.2-thinking | 128KOutput 128K | $0.29out $0.43 | 2fresh | |
| DeepSeek V3.2nvidia/deepseek-v3.2-nvfp4 · deepseek | 128KOutput 128K | $0.55out $1.65 | 1fresh | |
| Qwen/Qwen2.5-7B-Instructqwen/qwen2.5-7b-instruct · qwen | 33KOutput 32K | $0.050out $0.050 | 3fresh | |
| ByteDance-Seed/Seed-OSS-36B-Instructbytedance-seed/seed-oss-36b-instruct · seed | 262KOutput 262K | $0.21out $0.57 | 2fresh | |
| Grok-4.1-Fast-Non-Reasoningxai/grok-4.1-fast-non-reasoning · grok | 2MOutput 1M | $0.20out $0.50 | 2fresh | |
| Nova Premier 1.0amazon/nova-premier-v1 · nova | 1MOutput 32K | $2.50out $12.50 | 2fresh | |
| Seed 1.6volcengine/doubao-seed-1-6 · seed | 256KOutput 64K | $0.12out $0.29 | 1fresh | |
| glm-for-codingglm-for-coding · glm | 200KOutput 128K | $0.086out $0.34 | 1fresh | |
| Qwen3 Omni 30B A3B Instructqwen/qwen3-omni-30b-a3b-instruct · qwen | 64KOutput 16K | $0.25out $0.97 | 1fresh | |
| Qwen3 235B A22B 2507qwen.qwen3-235b-a22b-2507-v1:0 · qwen | 256KOutput 128K | $0.22out $0.88 | 1fresh | |
| Apertus 70Bapertus-70b | 64KOutput 64K | $0.46out $2.23 | 2fresh | |
| Perplexity Reasoning Prosonar-reasoning-pro · sonar-reasoning | 128KOutput 128K | $2.00out $8.00 | 9fresh | |
| LucidQuery Nexus Coderlucidquery-nexus-coder · lucid | 250KOutput 60K | $2.00out $5.00 | 1fresh | |
| Gemini 2.0 Flashgemini-2.0-flash | 1.05MOutput 8K | $0.10out $0.42 | 2fresh | |
| GPT OSS 120Bopenai/gpt-oss-120b-maas · gpt-oss | 128KOutput 32K | $0.090out $0.36 | 1fresh | |
| Qwen3 4B Instructqwen/qwen3-4b-instruct-2507 | 256KOutput 128K | $0.20out $0.20 | 1fresh | |
| GLM 4.5 FP8zai-org/glm-4.5-fp8 · glm | 128KOutput 128K | $0.20out $0.80 | 1fresh | |
| Gemini 2.5 Flashgemini-2-5-flash · gemini-flash | 1.05MOutput 64K | Unavailableper 1M tokens | 1fresh | |
| Gemini 2.5 Flash-Litegemini-2-5-flash-lite · gemini-flash-lite | 1.05MOutput 64K | Unavailableper 1M tokens | 1fresh | |
| DeepSeek-R1us.deepseek.r1-v1:0 · deepseek-thinking | 128KOutput 32K | $1.35out $5.40 | 1fresh | |
| xAI Grok 3 Minigrok-3-mini · grok | 128KOutput 128K | $0.30out $0.50 | 2fresh | |
| Llama 4 Maverick 17B Instructus.meta.llama4-maverick-17b-instruct-v1:0 · llama | 1MOutput 16K | $0.24out $0.97 | 1fresh | |
| Llama 4 Maverick 17B Instructmeta.llama4-maverick-17b-instruct-v1:0 · llama | 1MOutput 16K | $0.24out $0.97 | 1fresh | |
| Llama 4 Scout 17B Instructus.meta.llama4-scout-17b-instruct-v1:0 · llama | 3.5MOutput 16K | $0.17out $0.66 | 1fresh | |
| Llama 4 Scout 17B Instructmeta.llama4-scout-17b-instruct-v1:0 · llama | 3.5MOutput 16K | $0.17out $0.66 | 1fresh | |
| Qwen 3 Coder 30B A3B Instructalibaba/qwen3-coder-30b-a3b · qwen | 256KOutput 8K | $0.15out $0.60 | 1fresh | |
| Qwen3 235B A22B Instruct 2507alibaba/qwen-3-235b · qwen | 256KOutput 16K | $0.22out $0.88 | 1fresh |