DeepInfra
Inference providerUS Westprices checked Oct 23, 06:00 UTC
DeepInfra serves 82 models at a verified price. It is the cheapest host on 39 of the 76 it shares with others; its median price matches the cheapest.
Models served8278 with open weights
Cheapest input, per M$0.02Llama 3.1 8B
Uptime, last 24 h97.8%average of its 77 OpenRouter endpoints
Sign-upNot checked yetno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017cheapest | fp8 | 1M | ✓ | $0.098 | $0.29 | $0.0029 |
| Nemotron 3.5 Super VL | fp4 | 256K | ✓ | $0.15 | $0.50 | $0.02 |
| Ling 3.1 Flashcheapest | fp4 | 256K | ✓ | $0.075 | $0.23 | $0.015 |
| MiMo-V2.6-Flash | fp8 | 1M | ✓ | $0.13 | $0.27 | $0.0027 |
| MiMo-V2.6-Procheapest | fp8 | 1M | ✓ | $0.39 | $0.78 | $0.0032 |
| DeepSeek V4.1 Flash | fp8 | 1M | ✓ | $0.14 | $0.42 | $0.0042 |
| Ling 3.0 Flash VL (inclusionAI)cheapest | fp16 | 128K | ✓ | $0.06 | $0.18 | $0.012 |
| Granite 4.2 8B | bf16 | 128K | ✓ | $0.06 | $0.25 | $0.015 |
| GLM-5.3-Flash | fp4 | 1M | ✓ | $0.15 | $0.50 | $0.03 |
| DeepSeek V4 Flash Vision Expcheapest | fp8 | 1M | ✓ | $0.22 | $0.65 | $0.0069 |
| GLM-5.3 | fp4 | 1M | — | $1.20 | $4.00 | — |
| Qwen3.8 27B | bf16 | 256K | ✓ | $0.15 | $1.88 | $0.0375 |
| DeepSeek V4 Pro 0813 | fp8 | 1M | ✓ | $1.30 | $2.60 | $0.10 |
| Qwen3.8 2.4T A95Bcheapest | fp4 | 256K | ✓ | $2.00 | $6.00 | $0.20 |
| Nemotron 3.5 Lightning | bf16 | 256K | ✓ | $0.06 | $0.16 | $0.03 |
| Muse Glimmer 30B (Meta)cheapest | bf16 | 128K | ✓ | $0.30 | $1.20 | $0.04 |
| DeepSeek V4 Flash 0731 | fp8 | 1M | ✓ | $0.06 | $0.18 | $0.015 |
| Inkling Smallcheapest | fp8 | 512K | ✓ | $0.45 | $1.20 | $0.10 |
| Ling 3.0 Flashcheapest | bf16 | 128K | ✓ | $0.06 | $0.18 | $0.012 |
| Kimi K3 | mxfp4 | 1M | ✓ | $2.85 | $14.25 | $0.28 |
| Inklingcheapest | fp8 | 512K | ✓ | $0.95 | $4.05 | $0.16 |
| Hunyuan 3cheapest | fp4 | 256K | — | $0.13 | $0.53 | $0.033 |
| GLM 5.2cheapest | fp4 | 1M | ✓ | $0.56 | $1.80 | $0.10 |
| Kimi K2.7 Code | fp4 | 256K | — | $0.68 | $3.40 | $0.14 |
| Nemotron 3 Ultracheapest | fp4 | 256K | ✓ | $0.50 | $2.20 | $0.10 |
| Nemotron 3.5 Content Safety | bf16 | 128K | — | $0.20 | $0.20 | — |
| MiniMax-M3 | fp8 | 512K | ✓ | $0.28 | $1.10 | $0.056 |
| DeepSeek V4 Flash 0423 | fp8 | 1M | ✓ | $0.09 | $0.18 | $0.018 |
| DeepSeek V4 Pro 0423 | fp8 | 1M | ✓ | $1.30 | $2.60 | $0.10 |
| MiMo-V2.5cheapest | — | 1.05M | — | $0.13 | $0.27 | $0.0027 |
| MiMo-V2.5-Pro | — | 1.05M | — | $0.39 | $1.17 | $0.078 |
| Qwen3.6 27B | fp8 | 256K | ✓ | $0.32 | $3.20 | — |
| Kimi K2.6 | fp4 | 256K | ✓ | $0.75 | $3.50 | $0.15 |
| Qwen3.6 35B A3B | fp8 | 256K | ✓ | $0.10 | $0.95 | $0.10 |
| GLM 5.1 | fp4 | 198K | — | $1.05 | $3.50 | $0.20 |
| Gemma 4 26B A4B | fp8 | 256K | ✓ | $0.07 | $0.34 | — |
| Gemma 4 31B | fp8 | 256K | ✓ | $0.20 | $0.40 | — |
| MiniMax M2.7 | fp8 | 192K | — | $0.38 | $1.70 | $0.07 |
| Nemotron 3 Supercheapest | bf16 | 256K | ✓ | $0.085 | $0.40 | — |
| Qwen3.5 122B A10B | fp4 | 256K | — | $0.29 | $2.40 | — |
| Qwen3.5 9Bcheapest | bf16 | 256K | ✓ | $0.10 | $0.15 | — |
| Qwen3.5-27B | fp8 | 256K | ✓ | $0.26 | $2.60 | — |
| Qwen3.5-35B-A3Bcheapest | fp8 | 256K | — | $0.14 | $1.00 | $0.05 |
| Qwen3.5 397B A17Bcheapest | fp8 | 256K | ✓ | $0.45 | $3.00 | $0.22 |
| GLM 5 | fp4 | 198K | — | $0.60 | $2.08 | $0.12 |
| Kimi K2.5cheapest | fp4 | 256K | — | $0.45 | $2.25 | $0.07 |
| GLM 4.7 Flashcheapest | bf16 | 198K | — | $0.06 | $0.40 | $0.01 |
| GLM 4.7cheapest | fp4 | 198K | ✓ | $0.40 | $1.75 | $0.08 |
| Nemotron 3 Nano 30B A3Bcheapest | fp4 | 256K | — | $0.05 | $0.20 | $0.025 |
| Qwen3 VL 30B A3B Instructcheapest | fp8 | 256K | ✓ | $0.15 | $0.60 | — |
| GLM 4.6 | fp4 | 198K | ✓ | $0.50 | $2.00 | $0.10 |
| DeepSeek V3.2 | fp4 | 160K | ✓ | $0.26 | $0.38 | $0.13 |
| Qwen3 VL 235B A22B Instructcheapest | fp8 | 256K | ✓ | $0.20 | $0.88 | $0.11 |
| DeepSeek V3.1cheapest | fp4 | 160K | ✓ | $0.25 | $0.95 | $0.13 |
| gpt-oss-120b | bf16 | 128K | ✓ | $0.037 | $0.17 | — |
| gpt-oss-20b | bf16 | 128K | ✓ | $0.03 | $0.14 | — |
| Qwen3 Codercheapest | fp8 | 256K | ✓ | $0.30 | $1.00 | $0.10 |
| Qwen3 235B A22B Instruct 2507 | fp8 | 256K | ✓ | $0.09 | $0.55 | — |
| Mistral Small 3.2 24Bcheapest | fp8 | 125K | ✓ | $0.075 | $0.20 | — |
| DeepSeek R1cheapest | fp4 | 160K | — | $0.50 | $2.15 | $0.35 |
| Llama Guard 4 12B | bf16 | 160K | — | $0.18 | $0.18 | — |
| Qwen3 32Bcheapest | fp8 | 40K | ✓ | $0.08 | $0.28 | — |
| Qwen3 14B | fp8 | 40K | ✓ | $0.12 | $0.24 | — |
| Qwen3 30B A3B | fp8 | 40K | ✓ | $0.12 | $0.50 | — |
| Llama 4 Maverickcheapest | not checked yet | 1M | — | $0.20 | $0.80 | — |
| Llama 4 Scoutcheapest | fp8 | 320K | — | $0.10 | $0.30 | — |
| DeepSeek V3 0324cheapest | fp4 | 160K | — | $0.24 | $0.90 | $0.14 |
| Gemma 3 12B | bf16 | 128K | ✓ | $0.05 | $0.15 | — |
| Gemma 3 27Bcheapest | fp8 | 128K | ✓ | $0.08 | $0.16 | — |
| Gemma 3 4B | bf16 | 128K | — | $0.05 | $0.10 | — |
| Mistral Small 3 | fp8 | 32K | — | $0.05 | $0.08 | — |
| DeepSeek Chatcheapest | fp4 | 160K | ✓ | $0.32 | $0.89 | — |
| DeepSeek V3cheapest | fp4 | 160K | ✓ | $0.32 | $0.89 | — |
| Phi 4 | bf16 | 16K | — | $0.07 | $0.14 | — |
| Llama 3.3 70Bcheapest | fp8 | 128K | ✓ | $0.10 | $0.32 | — |
| Qwen3 Next 80B A3B | fp8 | 256K | ✓ | $0.09 | $1.10 | — |
| Qwen 2.5 72Bcheapest | fp8 | 32K | ✓ | $0.36 | $0.40 | — |
| Hermes 3 70B Instruct | fp8 | 128K | — | $0.70 | $0.70 | — |
| Hermes 3 405B Instruct | fp8 | 128K | — | $1.00 | $1.00 | — |
| Llama 3.1 70B Instructcheapest | fp8 | 128K | ✓ | $0.40 | $0.40 | — |
| Llama 3.1 8Bcheapest | fp8 | 128K | — | $0.02 | $0.04 | — |
| Mistral Nemo | fp8 | 128K | ✓ | $0.029 | $0.03 | — |
10 of 82 models · prices per million tokens · precision and context: read at DeepInfra's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as DeepInfra declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | Not checked yet | docs.deepinfra.com |
| Free credits | None stated | — |
| Where data goes | Data may be transferred, stored and processed in the United States | deepinfra.com |
| Headquarters region | US West | — |
| Price list | Where its per-token prices are published | deepinfra.com |
| API documentation | Its own docs | docs.deepinfra.com |
| Status page | Outages and incidents, as DeepInfra reports them | status.deepinfra.com |
| Terms of service | Its terms | deepinfra.com |
Links checked Oct 8.