Models
Model catalogue
Search source-reported prices, limits, capabilities, and provider availability. Every provider offer stays available.
Fresh · fetched 2026-08-18T02:45:42.818Z · Models.dev(opens in a new tab)
2161 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 |
|---|---|---|---|---|
| Apertus 70B Instructpublicai/apertus-70b-instruct | 64KOutput 8K | $0.82out $2.92 | 1fresh | |
| Apertus 8B Instructpublicai/apertus-8b-instruct | 64KOutput 8K | $0.10out $0.20 | 1fresh | |
| Command A Translatecommand-a-translate-08-2025 · command-a | 8KOutput 8K | $2.50out $10.00 | 1fresh | |
| Nemotron Nano 9B v2amazon/nvidia.nemotron-nano-9b-v2@us · nemotron | 128KOutput 128K | $0.060out $0.23 | 1fresh | |
| GLM-4.5-Flashglm-4.5-flash · glm-flash | 128KOutput 96K | Unavailableper 1M tokens | 2fresh | |
| GLM 4.5zai-org/glm-4.5:thinking · glm | 128KOutput 64K | $0.30out $1.30 | 1fresh | |
| DeepSeek TNG R1T2 Chimeradeepseek-tng-r1t2-chimera · deepseek-thinking | 130KOutput 160K | $0.30out $1.20 | 1fresh | |
| ERNIE 4.5 21B A3Bbaidu/ernie-4.5-21b-a3b · ernie | 120KOutput 8K | $0.070out $0.28 | 1fresh | |
| Gemma 3n E2b Itgoogle/gemma-3n-e2b-it | 128KOutput 4K | Unavailableper 1M tokens | 1fresh | |
| DeepSeek R1 0528 Qwen3 8Bdeepseek/deepseek-r1-0528-qwen3-8b | 128KOutput 32K | $0.060out $0.090 | 1fresh | |
| Llama-3.1-8B-CScerebras/llama-3.1-8b-cs | 128K | $0.10out $0.10 | 1fresh | |
| Qwen3 4Bqwen/qwen3-4b-fp8 | 128KOutput 20K | $0.030out $0.030 | 1fresh | |
| Qwen3 8Bqwen/qwen3-8b-fp8 | 128KOutput 20K | $0.035out $0.14 | 1fresh | |
| Llama 3.1 Nemotron Nano VL 8B v1llama-3.1-nemotron-nano-vl-8b-v1 · nemotron | 32KOutput 16K | Unavailableper 1M tokens | 1fresh | |
| Llama 4 Maverick 17B Instructllama-4-maverick-17b-instruct · llama | 1.05MOutput 2K | $0.27out $0.85 | 1fresh | |
| Llama 4 Maverick 17b 128e Instructmeta/llama-4-maverick-17b-128e-instruct | 128KOutput 4K | Unavailableper 1M tokens | 1fresh | |
| GPT-4o Mini Transcribegpt-4o-mini-transcribe · gpt | 16KOutput 16K | $1.25out $5.00 | 2fresh | |
| GPT-4o Transcribegpt-4o-transcribe · gpt | 16KOutput 16K | $2.50out $10.00 | 2fresh | |
| GPT-4o-mini-Searchopenai/gpt-4o-mini-search · gpt-mini | 128KOutput 8K | $0.14out $0.54 | 1fresh | |
| GPT-4o-Searchopenai/gpt-4o-search · gpt | 128KOutput 8K | $2.20out $9.00 | 1fresh | |
| TheDrummer Skyfall 36B V2thedrummer/skyfall-36b-v2 | 32KOutput 32K | $0.55out $0.80 | 3fresh | |
| DeepSeek V3 (Turbo) deepseek/deepseek-v3-turbo | 64KOutput 16K | $0.40out $1.30 | 1fresh | |
| Mercury Coder Smallmercury-coder-small · mercury | 32KOutput 16K | $0.25out $1.00 | 2fresh | |
| MiniMax-M2.5minimax-m2-5 · minimax | 192KOutput 8K | $0.30out $1.20 | 1fresh | |
| Qwen-Max-Latestqwen-max-latest · qwen | 128KOutput 8K | $0.34out $1.37 | 1fresh | |
| Magnum v4 72Banthracite-org/magnum-v4-72b · llama | 32KOutput 8K | $2.01out $2.99 | 3fresh | |
| ReMM SLERP 13Bundi95/remm-slerp-l2-13b · llama | 6KOutput 6K | $0.45out $0.65 | 3fresh | |
| DeepSeek V3.1deepseek-v3-1 · deepseek | 128KOutput 64K | $0.57out $1.72 | 1fresh | |
| DeepSeek V3.2 Expdeepseek-v3-2-exp · deepseek | 128KOutput 64K | $0.29out $0.43 | 1fresh | |
| Kimi K2kimi-k2-0711 · kimi-k2 | 128KOutput 16K | $0.57out $2.30 | 1fresh | |
| Mistral Nemo 12B Instructmistral/mistral-nemo-12b-instruct · mistral-nemo | 16KOutput 4K | $0.038out $0.10 | 1fresh | |
| Osmosis Structure 0.6Bosmosis/osmosis-structure-0.6b · osmosis | 4KOutput 2K | $0.10out $0.50 | 1fresh | |
| Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b · llama | 128KOutput 16K | $0.65out $0.75 | 2fresh | |
| Phi-4-reasoningphi-4-reasoning · phi | 32KOutput 4K | $0.13out $0.50 | 2fresh | |
| Phi-4-reasoning-plusphi-4-reasoning-plus · phi | 32KOutput 4K | $0.13out $0.50 | 2fresh | |
| Llama 3.3 70B Instruct fp8 Fast@cf/meta/llama-3.3-70b-instruct-fp8-fast · llama | 24KOutput 24K | $0.29out $2.25 | 1fresh | |
| Llama 3.3 70B Instruct fp8 Fastworkers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast · llama | 24KOutput 24K | $0.29out $2.25 | 1fresh | |
| amazon--nova-microamazon--nova-micro · nova-micro | 128KOutput 8K | $0.030out $0.10 | 1fresh | |
| Nova Microamazon.nova-micro-v1:0 · nova-micro | 128KOutput 8K | $0.035out $0.14 | 1fresh | |
| Nova Microamazon/nova-micro · nova-micro | 128KOutput 8K | $0.035out $0.14 | 1fresh | |
| Google Gemma 3 12Bgoogle.gemma-3-12b-it · gemma | 128KOutput 8K | $0.050out $0.100 | 1fresh | |
| Palmyra X4writer/palmyra-x4 · palmyra | 128KOutput 32K | $2.50out $10.00 | 1fresh | |
| L31 70B Euryale V2.2sao10k/l31-70b-euryale-v2.2 | 8KOutput 8K | $1.48out $1.48 | 1fresh | |
| Qwen2.5-Math 72B Instructqwen2-5-math-72b-instruct · qwen | 4KOutput 3K | $0.57out $1.72 | 1fresh | |
| Qwen2.5-Math 7B Instructqwen2-5-math-7b-instruct · qwen | 4KOutput 3K | $0.14out $0.29 | 1fresh | |
| Llama 3.1 70B Instructmeta/llama-3.1-70b · llama | 128KOutput 8K | $0.72out $0.72 | 1fresh | |
| Llama 3.1 8B Instructmeta/llama-3.1-8b · llama | 128KOutput 8K | $0.22out $0.22 | 1fresh | |
| Meta Llama 3.1 8B Instruct Turbollama-3.1-8b-instruct-turbo · llama | 128KOutput 128K | $0.020out $0.030 | 1fresh | |
| L3 70B Euryale V2.1 sao10k/l3-70b-euryale-v2.1 | 8KOutput 8K | $1.48out $1.48 | 1fresh | |
| Mixtral 8x22Bopen-mixtral-8x22b · mixtral | 64KOutput 64K | $2.00out $6.00 | 1fresh |