← All providers
Deep Infra
60 models · routes through the @ai-sdk/deepinfra adapter
Required environment variables
- DEEPINFRA_API_KEY
Models
| Model | Context | Input | Output | Capabilities |
|---|---|---|---|---|
| Qwen/Qwen3.8-27B | 262k | $0.40 / 1M | $3.00 / 1M | tools, reasoning, open-weights, vision |
| deepseek-ai/DeepSeek-V4-Pro-0813 | 1049k | $1.30 / 1M | $2.60 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.8-2.4T-A95B | 262k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.8-Max | 256k | $1.65 / 1M | $4.95 / 1M | tools, vision |
| deepseek-ai/DeepSeek-V4-Flash-0731 | 1049k | $0.08 / 1M | $0.18 / 1M | tools, reasoning, open-weights |
| thinkingmachines/Inkling-Small | 524k | $0.45 / 1M | $1.20 / 1M | tools, reasoning, open-weights, vision |
| moonshotai/Kimi-K3 | 1049k | $2.85 / 1M | $14.25 / 1M | tools, reasoning, open-weights, vision |
| thinkingmachines/Inkling | 524k | $0.95 / 1M | $4.05 / 1M | tools, reasoning, open-weights, vision |
| tencent/Hy3 | 262k | $0.14 / 1M | $0.58 / 1M | tools, reasoning, open-weights |
| zai-org/GLM-5.2 | 1049k | $0.75 / 1M | $2.40 / 1M | tools, reasoning, open-weights |
| moonshotai/Kimi-K2.7-Code | 262k | $0.68 / 1M | $3.40 / 1M | tools, reasoning, open-weights, vision |
| MiniMaxAI/MiniMax-M3 | 524k | $0.28 / 1M | $1.10 / 1M | tools, reasoning, open-weights, vision |
| stepfun-ai/Step-3.7-Flash | 262k | $0.20 / 1M | $1.15 / 1M | tools, reasoning, open-weights, vision |
| Qwen/Qwen3.7-Max | 256k | $2.50 / 1M | $7.50 / 1M | tools |
| nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoningdeprecated | 262k | $0.20 / 1M | $0.80 / 1M | tools, reasoning, open-weights, vision |
| deepseek-ai/DeepSeek-V4-Flash | 1049k | $0.09 / 1M | $0.18 / 1M | tools, reasoning, open-weights |
| deepseek-ai/DeepSeek-V4-Pro | 1049k | $1.30 / 1M | $2.60 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.6-27B | 262k | $0.32 / 1M | $3.20 / 1M | tools, reasoning, open-weights, vision |
| XiaomiMiMo/MiMo-V2.5 | 262k | $0.40 / 1M | $2.00 / 1M | tools, reasoning, open-weights, vision |
| XiaomiMiMo/MiMo-V2.5-Pro | 1049k | $1.00 / 1M | $3.00 / 1M | tools, reasoning, open-weights |
| moonshotai/Kimi-K2.6 | 262k | $0.75 / 1M | $3.50 / 1M | tools, reasoning, open-weights, vision |
| zai-org/GLM-5.1 | 203k | $1.05 / 1M | $3.50 / 1M | tools, reasoning, open-weights |
| google/gemma-4-26B-A4B-it | 262k | $0.07 / 1M | $0.34 / 1M | tools, reasoning, open-weights, vision |
| google/gemma-4-31B-it | 262k | $0.13 / 1M | $0.38 / 1M | tools, reasoning, open-weights, vision |
| google/gemma-4-E4B-it | 131k | $0.02 / 1M | $0.10 / 1M | tools, reasoning, open-weights, vision |
| Qwen/Qwen3.6-35B-A3B | 262k | $0.10 / 1M | $0.95 / 1M | tools, reasoning, open-weights, vision |
| MiniMaxAI/MiniMax-M2.7 | 197k | $0.25 / 1M | $1.00 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.5-122B-A10B | 262k | $0.29 / 1M | $2.40 / 1M | tools, reasoning, open-weights, vision |
| Qwen/Qwen3.5-27B | 262k | $0.26 / 1M | $2.60 / 1M | tools, reasoning, open-weights, vision |
| Qwen/Qwen3.5-9B | 262k | $0.10 / 1M | $0.15 / 1M | tools, reasoning, open-weights, vision |
| ByteDance/Seed-2.0-code | 256k | $0.50 / 1M | $3.00 / 1M | tools, reasoning, vision |
| ByteDance/Seed-2.0-mini | 256k | $0.10 / 1M | $0.40 / 1M | tools, reasoning, vision |
| ByteDance/Seed-2.0-pro | 256k | $0.50 / 1M | $3.00 / 1M | tools, reasoning, vision |
| MiniMaxAI/MiniMax-M2.5deprecated | 197k | $0.15 / 1M | $1.15 / 1M | tools, reasoning, open-weights |
| zai-org/GLM-5 | 203k | $0.60 / 1M | $2.08 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.5-35B-A3B | 262k | $0.14 / 1M | $1.00 / 1M | tools, reasoning, open-weights, vision |
| Qwen/Qwen3.5-397B-A17B | 262k | $0.45 / 1M | $3.00 / 1M | tools, reasoning, open-weights, vision |
| moonshotai/Kimi-K2.5 | 262k | $0.45 / 1M | $2.25 / 1M | tools, reasoning, open-weights, vision |
| zai-org/GLM-4.7-Flash | 203k | $0.06 / 1M | $0.40 / 1M | tools, reasoning, open-weights |
| zai-org/GLM-4.7 | 203k | $0.40 / 1M | $1.75 / 1M | tools, reasoning, open-weights |
| nvidia/Nemotron-3-Nano-30B-A3B | 262k | $0.05 / 1M | $0.20 / 1M | tools, reasoning, open-weights |
| deepseek-ai/DeepSeek-V3.2 | 164k | $0.26 / 1M | $0.38 / 1M | tools, reasoning |
| zai-org/GLM-4.6 | 203k | $0.50 / 1M | $2.00 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3-Max | 256k | $1.20 / 1M | $6.00 / 1M | tools |
| Qwen/Qwen3-VL-235B-A22B-Instruct | 262k | $0.20 / 1M | $0.88 / 1M | tools, open-weights, vision |
| Qwen/Qwen3-Next-80B-A3B-Instruct | 262k | $0.09 / 1M | $1.10 / 1M | tools, open-weights |
| deepseek-ai/DeepSeek-V3.1 | 164k | $0.25 / 1M | $0.95 / 1M | tools, reasoning, open-weights |
| openai/gpt-oss-120b | 131k | $0.04 / 1M | $0.17 / 1M | tools, reasoning, open-weights |
| openai/gpt-oss-20b | 131k | $0.03 / 1M | $0.14 / 1M | tools, reasoning, open-weights |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1.5deprecated | 131k | $0.40 / 1M | $0.40 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | 262k | $0.30 / 1M | $1.00 / 1M | tools, open-weights |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 262k | $0.09 / 1M | $0.55 / 1M | tools, open-weights |
| deepseek-ai/DeepSeek-R1-0528 | 164k | $0.50 / 1M | $2.15 / 1M | tools, reasoning |
| Qwen/Qwen3-30B-A3B | 41k | $0.12 / 1M | $0.50 / 1M | tools, reasoning, open-weights |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 1049k | $0.20 / 1M | $0.80 / 1M | open-weights, vision |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | 328k | $0.10 / 1M | $0.30 / 1M | tools, open-weights, vision |
| Qwen/Qwen3-32B | 41k | $0.08 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| deepseek-ai/DeepSeek-V3-0324 | 164k | $0.24 / 1M | $0.90 / 1M | tools, open-weights |
| deepseek-ai/DeepSeek-V3 | 164k | $0.32 / 1M | $0.89 / 1M | tools, open-weights |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | 131k | $0.10 / 1M | $0.32 / 1M | tools, open-weights |
Sourced from models.dev. Pricing reflects the catalog at the time this page was rendered.