DeepInfra
deepinfra, the name to use in providers=
- Models offered
- 77
- Billing currency
- USD
- Runs
- hosted
- Fees
- none
Models
| Model | Model id here | Status | Input per 1M | Output per 1M |
|---|---|---|---|---|
| Claude Fable 5 | anthropic/claude-fable-5 | ga | $10 | $50 |
| DeepSeek R1 0528 | deepseek-ai/DeepSeek-R1-0528 | ga | $0.5 | $2.15 |
| DeepSeek V3 0324 | deepseek-ai/DeepSeek-V3-0324 | deprecated | $0.24unverified | $0.9 |
| DeepSeek V3.2 | deepseek-ai/DeepSeek-V3.2 | ga | $0.26 | $0.38 |
| DeepSeek V4 Flash | deepseek-ai/DeepSeek-V4-Flash | ga | $0.09unverified | $0.18 |
| DeepSeek V4 Flash | deepseek-ai/DeepSeek-V4.1-Flash-1017 | ga | $0.2unverified | $0.6 |
| DeepSeek V4 Flash 0731 | deepseek-ai/DeepSeek-V4-Flash-0731 | ga | $0.06 | $0.18 |
| DeepSeek V4 Flash Vision Exp | deepseek-ai/DeepSeek-V4-Flash-Vision-Exp | ga | $0.44 | $1.32 |
| DeepSeek V4 Pro | deepseek-ai/DeepSeek-V4-Pro | ga | $1.3 | $2.6 |
| DeepSeek V4 Pro | deepseek-ai/DeepSeek-V4-Pro-0813 | ga | $1.3 | $2.6 |
| DeepSeek V4.1 Flash | deepseek-ai/DeepSeek-V4.1-Flash | ga | $0.2unverified | $0.6 |
| DeepSeek-V3 | deepseek-ai/DeepSeek-V3 | ga | $0.32 | $0.89 |
| DeepSeek-V3.1 | deepseek-ai/DeepSeek-V3.1 | ga | $0.25unverified | $0.95 |
| Gemma 3 12B IT | google/gemma-3-12b-it | ga | $0.05unverified | $0.15 |
| Gemma 3 27B IT | google/gemma-3-27b-it | ga | $0.08 | $0.16 |
| Gemma 3 4B IT | google/gemma-3-4b-it | ga | $0.05unverified | $0.1 |
| Gemma 4 26B A4B (free) | google/gemma-4-26B-A4B-it | ga | $0.07 | $0.34 |
| Gemma 4 31B IT | google/gemma-4-31B-it | ga | $0.2unverified | $0.4 |
| Gemma 4 E4B IT | google/gemma-4-E4B-it | deprecated | $0.02 | $0.1 |
| GLM-4.6 | zai-org/GLM-4.6 | ga | $0.5unverified | $2 |
| GLM-4.7 | zai-org/GLM-4.7 | ga | $0.4 | $1.75 |
| GLM-4.7-Flash | zai-org/GLM-4.7-Flash | deprecated | $0.06 | $0.4 |
| GLM-5 | zai-org/GLM-5 | deprecated | $0.6 | $2.08 |
| GLM-5.1 | zai-org/GLM-5.1 | deprecated | $1.05 | $3.5 |
| GLM-5.2 | zai-org/GLM-5.2 | ga | $0.75 | $2.4 |
| GLM-5.3 | zai-org/GLM-5.3 | ga | $0.9 | $4 |
| GLM-5.3-Flash | zai-org/GLM-5.3-Flash | ga | $0.15 | $0.5 |
| GPT OSS 120B | openai/gpt-oss-120b | ga | $0.037unverified | $0.17 |
| GPT OSS 20B | openai/gpt-oss-20b | ga | $0.03 | $0.14 |
| Hy3 | tencent/Hy3 | deprecated | $0.13unverified | $0.53 |
| Hy4 preview | tencent/Hy4-preview | ga | $0.834 | $2.501 |
| Inkling | thinkingmachines/Inkling | deprecated | $0.95 | $4.05 |
| Inkling Small | thinkingmachines/Inkling-Small | ga | $0.45 | $1.2 |
| Kimi K2.5 | moonshotai/Kimi-K2.5 | deprecated | $0.45 | $2.25 |
| Kimi K2.6 | moonshotai/Kimi-K2.6 | ga | $0.75 | $3.5 |
| Kimi K2.7 Code | moonshotai/Kimi-K2.7-Code | deprecated | $0.68unverified | $3.4 |
| Kimi K3 | moonshotai/Kimi-K3 | ga | $2.85 | $14.25 |
| Llama 3.3 Nemotron Super 49B v1.5 | nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | deprecated | $0.4unverified | $0.4 |
| Llama 4 Maverick | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | deprecated | $0.2unverified | $0.8 |
| Llama 4 Scout | meta-llama/Llama-4-Scout-17B-16E-Instruct | ga | $0.1unverified | $0.3 |
| Llama Guard 4 12B | meta-llama/Llama-Guard-4-12B | ga | $0.18 | $0.18 |
| Llama-3.3-70B-Instruct | meta-llama/Llama-3.3-70B-Instruct-Turbo | ga | $0.1 | $0.32 |
| MiMo-V2.5 | XiaomiMiMo/MiMo-V2.5 | deprecated | $0.14unverified | $0.28 |
| MiMo-V2.5-Pro | XiaomiMiMo/MiMo-V2.5-Pro | deprecated | $1 | $3 |
| MiMo-V2.6-Flash | XiaomiMiMo/MiMo-V2.6-Flash | ga | $0.14 | $0.28 |
| MiMo-V2.6-Pro | XiaomiMiMo/MiMo-V2.6-Pro | ga | $0.43 | $0.87 |
| MiniMax-M2.5 | MiniMaxAI/MiniMax-M2.5 | deprecated | $0.15 | $1.15 |
| MiniMax-M2.7 | MiniMaxAI/MiniMax-M2.7 | deprecated | $0.25 | $1 |
| MiniMax-M3 | MiniMaxAI/MiniMax-M3 | ga | $0.28 | $1.1 |
| Mistral Small 3 | mistralai/Mistral-Small-24B-Instruct-2501 | ga | $0.05 | $0.08 |
| Nemotron 3 Nano 30B A3B | nvidia/Nemotron-3-Nano-30B-A3B | deprecated | $0.05 | $0.2 |
| Nemotron 3 Nano Omni (free) | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | deprecated | $0.2 | $0.8 |
| Qwen3 235B A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | ga | $0.09unverified | $0.55 |
| Qwen3 30B A3B | Qwen/Qwen3-30B-A3B | ga | $0.12unverified | $0.5 |
| Qwen3 32B | Qwen/Qwen3-32B | ga | $0.08 | $0.28 |
| Qwen3 Coder 480B A35B | Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | ga | $0.3 | $1 |
| Qwen3 Max | Qwen/Qwen3-Max | deprecated | $1.2 | $6 |
| Qwen3 VL 235B A22B Instruct | Qwen/Qwen3-VL-235B-A22B-Instruct | ga | $0.2 | $0.88 |
| Qwen3 VL 30B A3B Instruct | Qwen/Qwen3-VL-30B-A3B-Instruct | ga | $0.15 | $0.6 |
| Qwen3-Next 80B-A3B Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | ga | $0.09 | $1.1 |
| Qwen3.5 122B-A10B | Qwen/Qwen3.5-122B-A10B | deprecated | $0.29 | $2.4 |
| Qwen3.5 27B | Qwen/Qwen3.5-27B | ga | $0.26 | $2.6 |
| Qwen3.5 35B-A3B | Qwen/Qwen3.5-35B-A3B | ga | $0.14 | $1 |
| Qwen3.5 397B-A17B | Qwen/Qwen3.5-397B-A17B | ga | $0.45unverified | $3 |
| Qwen3.5 9B | Qwen/Qwen3.5-9B | ga | $0.1unverified | $0.15 |
| Qwen3.6 27B | Qwen/Qwen3.6-27B | ga | $0.32 | $3.2 |
| Qwen3.6 35B-A3B | Qwen/Qwen3.6-35B-A3B | ga | $0.1unverified | $0.95 |
| Qwen3.7 Max | Qwen/Qwen3.7-Max | ga | $2.5 | $7.5 |
| Qwen3.8 2.4T A95B | Qwen/Qwen3.8-2.4T-A95B | deprecated | $2 | $6 |
| Qwen3.8 27B | Qwen/Qwen3.8-27B | ga | $0.2unverified | $2.5 |
| Qwen3.8 Flash | Qwen/Qwen3.8-Flash | ga | $0.113 | $0.382 |
| Qwen3.8 Max | Qwen/Qwen3.8-Max | ga | $1.65 | $4.951 |
| Seed 2.0 Code | ByteDance/Seed-2.0-code | ga | $0.5 | $3 |
| Seed 2.0 Mini | ByteDance/Seed-2.0-mini | ga | $0.1 | $0.4 |
| Seed 2.0 Pro | ByteDance/Seed-2.0-pro | ga | $0.5 | $3 |
| Step 3.7 Flash | stepfun-ai/Step-3.7-Flash | deprecated | $0.2 | $1.15 |
| Step 5 Preview | stepfun-ai/Step-5-Preview | deprecated | $1 | $2.7 |
Built from catalog version 2026-11-04.3 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).