SF·SIX / PROVIDER PRICING
DeepInfra API pricing
Live prices for every model DeepInfra serves: its own per-1M-token prices, or per image, second or character, next to the cheapest price elsewhere.
DeepInfra serves 71 models with live API prices on SF·SIX, 71 models priced per 1M tokens. The cheapest is Llama 3.1 8B Instruct at $0.02 per 1M input and $0.04 per 1M output tokens. The most used on OpenRouter is DeepSeek V4.1 Flash (5.41T tokens on 2026-10-16).
- Models with live prices
- 71
- Cheapest language model
- Llama 3.1 8B Instruct$0.02 / $0.04 per 1M tokens
- Most used on OpenRouter (2026-10-16)
- DeepSeek V4.1 Flash5.41T tokens
- Newest model
- DeepSeek V4.1 Flash 10172026-10-17
- Cheapest standard host for
- 33 models of 71
DeepInfra token prices (USD per 1M tokens)
| Model | Input / 1M | Output / 1M | Terms | Cheapest standard price anywhere | Context (tokens) | OpenRouter tokens / day |
|---|---|---|---|---|---|---|
| GLM 5.3 | $0.5625 | $2.50 | Standard · fp4 | $0.50 / $1.51Sail Research (fp8) | 1,048,576 | 942.62B |
| DeepSeek V4.1 Flash | $0.14 | $0.42 | Standard · fp8 | $0.09 / $0.18Decart (fp4) | 1,048,576 | 5.41T |
| GLM 5.3 Flash | $0.075 | $0.25 | Standard · fp4 | DeepInfracheapest standard host | 1,048,576 | 1.73T |
| GLM 5.2 | $0.5625 | $1.80 | Standard · fp4 | $0.189 / $0.594Baidu (fp8) | 1,048,576 | 140.87B |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | Standard · fp8 | $0.0598 / $0.1795Baidu (fp8) | 1,048,576 | 620.6B |
| DeepSeek V4 Pro 0813 | $1.30 | $2.60 | Standard · fp8 | $0.1333 / $0.40Baidu (fp8) | 1,048,576 | 161.08B |
| gpt-oss-120b | $0.037 | $0.17 | Standard · bf16 | $0.03 / $0.15Near AI (fp4) | 131,072 | 86.23B |
| Qwen3.8 27B | $0.15 | $1.88 | Standard · bf16 | $0.02 / $0.50Tenstorrent (fp4) | 1,000,000 | 62.19B |
| Kimi K3 | $2.85 | $14.25 | Standard · mxfp4 | $0.504 / $8.10Sail Research (fp4) | 1,048,576 | 203.41B |
| Kimi K2.6 | $0.75 | $3.50 | Standard · fp4 | $0.4323 / $1.82Baidu (fp4) | 262,144 | Not in named rows |
| DeepSeek V4 Pro 0423 | $1.30 | $2.60 | Standard · fp8 | $0.1775 / $0.3549Baidu (fp8) | 1,048,576 | 85.51B |
| DeepSeek V4 Flash 0423 | $0.09 | $0.18 | Standard · fp8 | $0.0181 / $0.0361Baidu (fp8) | 1,048,576 | 423.23B |
| MiniMax M3 | $0.28 | $1.10 | Standard · fp8 | $0.23 / $0.96CoreWeave (fp4) | 1,048,576 | 210.13B |
| Gemma 4 26B A4B | $0.07 | $0.34 | Standard · fp8 | $0.042 / $0.22Darkbloom | 262,144 | Not in named rows |
| DeepSeek V3.2 | $0.26 | $0.38 | Standard · fp4 | $0.2088 / $0.3096GMI Cloud (fp8) | 163,840 | Not in named rows |
| Gemma 4 31B | $0.20 | $0.40 | Standard · fp8 | $0.10 / $0.34CoreWeave (fp4) | 262,144 | 73.13B |
| Qwen3.6 35B A3B | $0.10 | $0.95 | Standard · fp8 | $0.05 / $0.70Darkbloom (fp4) | 262,144 | 386.14B |
| gpt-oss-20b | $0.03 | $0.14 | Standard · bf16 | $0.018 / $0.09Darkbloom (fp8) | 131,072 | Not in named rows |
| Llama 3.3 70B Instruct | $0.10 | $0.32 | Turbo tier · fp8 | $0.135 / $0.40Novita AI (bf16) | 131,072 | Not in named rows |
| MiMo-V2.6-Flash | $0.133 | $0.266 | Standard · fp8 | $0.10 / $0.28Darkbloom (fp4) | 1,050,000 | 1.44T |
| Qwen3.6 27B | $0.32 | $3.20 | Standard · fp8 | $0.25 / $2.00Chutes (fp8) | 262,144 | Not in named rows |
| Qwen3.5-35B-A3B | $0.14 | $1.00 | Standard · fp8 | $0.065 / $0.75Darkbloom (fp4) | 262,144 | Not in named rows |
| Qwen3.5-27B | $0.26 | $2.60 | Standard · fp8 | $0.195 / $1.56Alibaba | 262,144 | Not in named rows |
| GLM 4.7 | $0.40 | $1.75 | Standard · fp4 | DeepInfracheapest standard host | 204,800 | Not in named rows |
| Qwen3 235B A22B Instruct 2507 | $0.09 | $0.55 | Standard · fp8 | $0.0875 / $0.35GMI Cloud (fp8) | 262,144 | Not in named rows |
| Qwen3.5-9B | $0.10 | $0.15 | Standard · bf16 | $0.08 / $0.13Darkbloom (fp4) | 262,144 | Not in named rows |
| Gemma 3 27B | $0.08 | $0.16 | Standard · fp8 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Llama 3.1 8B Instruct | $0.02 | $0.04 | Standard · fp8 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Mistral Nemo | $0.029 | $0.03 | Standard · fp8 | $0.0166 / $0.0216IO.NET (fp16) | 131,072 | Not in named rows |
| Step 5 Preview | $1.00 | $2.70 | Standard · fp8 | $1.00 / $2.70StepFun (fp8) | 1,048,576 | 179.04B |
| MiMo-V2.6-Pro | $0.43 | $0.87 | Standard · fp8 | DeepInfracheapest standard host | 1,050,000 | 209.34B |
| Hy4 preview | $0.834 | $2.50 | Standard · fp4 | $0.834 / $2.50Tencent (fp8) | 1,048,576 | 1.24T |
| Nemotron 3.5 Lightning | $0.06 | $0.16 | Standard · bf16 | $0.025 / $0.12Darkbloom (int4) | 262,144 | 90.07B |
| GLM 4.6 | $0.50 | $2.00 | Standard · fp4 | $0.43 / $1.75Venice AI (fp4) | 204,800 | Not in named rows |
| DeepSeek V3.1 | $0.25 | $0.95 | Standard · fp4 | DeepInfracheapest standard host | 163,840 | Not in named rows |
| Mistral Small 3.2 24B | $0.075 | $0.20 | Standard · fp8 | DeepInfracheapest standard host | 256,000 | Not in named rows |
| R1 0528 | $0.50 | $2.15 | Standard · fp4 | DeepInfracheapest standard host | 163,840 | Not in named rows |
| DeepSeek V4.1 Flash 1017 | $0.14 | $0.42 | Standard · fp8 | $0.10 / $0.50InferenceNet (fp8) | 1,048,576 | Not in named rows |
| Nemotron 3.5 Super VL | $0.10 | $0.40 | Standard · fp4 | DeepInfracheapest standard host | 1,048,576 | 287.58B |
| DeepSeek V4 Flash Vision Exp | $0.2156 | $0.6468 | Standard · fp8 | DeepInfracheapest standard host | 1,048,576 | Not in named rows |
| Nemotron 3 Ultra | $0.50 | $2.20 | Standard · fp4 | DeepInfracheapest standard host | 262,144 | 83.11B |
| Nemotron 3 Super | $0.085 | $0.40 | Standard · bf16 | DeepInfracheapest standard host | 262,144 | 105.18B |
| Qwen3 VL 235B A22B Instruct | $0.20 | $0.88 | Standard · fp8 | DeepInfracheapest standard host | 262,144 | Not in named rows |
| Qwen3 Next 80B A3B Instruct | $0.09 | $1.10 | Standard · fp8 | DeepInfracheapest standard host | 262,144 | Not in named rows |
| Qwen3 Coder 480B A35B | $0.30 | $1.00 | Turbo tier · fp4 | $0.35 / $1.50Venice AI (fp8) | 262,144 | Not in named rows |
| Qwen3 32B | $0.08 | $0.28 | Standard · fp8 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| MythoMax 13B | $0.40 | $0.40 | Standard · fp16 | $0.08 / $0.11Parasail (fp16) | 8,192 | Not in named rows |
| Ling 3.1 Flash | $0.075 | $0.225 | Standard · fp4 | DeepInfracheapest standard host | 262,144 | Not in named rows |
| Granite 4.2 8B | $0.06 | $0.25 | Standard · bf16 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Muse Glimmer 30B | $0.30 | $1.20 | Standard · bf16 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Ling 3.0 Flash | $0.06 | $0.18 | Standard · bf16 | $0.021 / $0.063Novita AI | 262,144 | Not in named rows |
| Inkling | $0.95 | $4.05 | Standard · fp8 | DeepInfracheapest standard host | 524,288 | Not in named rows |
| Qwen3 VL 30B A3B Instruct | $0.15 | $0.60 | Standard · fp8 | DeepInfracheapest standard host | 262,144 | Not in named rows |
| Qwen3 14B | $0.12 | $0.24 | Standard · fp8 | $0.10 / $0.22NextBit (int4) | 40,960 | Not in named rows |
| Llama 4 Scout | $0.10 | $0.30 | Standard · fp8 | DeepInfracheapest standard host | 1,310,720 | Not in named rows |
| Gemma 3 4B | $0.05 | $0.10 | Standard · bf16 | $0.04 / $0.05Parasail (bf16) | 131,072 | Not in named rows |
| Gemma 3 12B | $0.05 | $0.15 | Standard · bf16 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| DeepSeek V3 | $0.256 | $0.712 | Flex tier · fp4 | $0.2574 / $1.03StreamLake | 163,840 | Not in named rows |
| Llama 3 8B Lunaris | $0.04 | $0.05 | Turbo tier · fp8 | $0.04 / $0.05Parasail (bf16) | 8,192 | Not in named rows |
| Llama 3.1 70B Instruct | $0.40 | $0.40 | Turbo tier · fp8 | $0.72 / $0.72Amazon Bedrock | 131,072 | Not in named rows |
| Ling 3.0 Flash VL | $0.06 | $0.18 | Standard · fp16 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Inkling Small | $0.45 | $1.20 | Standard · fp8 | DeepInfracheapest standard host | 524,288 | Not in named rows |
| Nemotron 3.5 Content Safety | $0.20 | $0.20 | Standard · bf16 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Llama Guard 4 12B | $0.18 | $0.18 | Standard · bf16 | DeepInfracheapest standard host | 163,840 | Not in named rows |
| Qwen3 30B A3B | $0.12 | $0.50 | Standard · fp8 | DeepInfracheapest standard host | 40,960 | Not in named rows |
| Mistral Small 3 | $0.05 | $0.08 | Standard · fp8 | DeepInfracheapest standard host | 32,768 | Not in named rows |
| Phi 4 | $0.07 | $0.14 | Standard · bf16 | DeepInfracheapest standard host | 16,384 | Not in named rows |
| Qwen2.5 72B Instruct | $0.36 | $0.40 | Standard · fp8 | DeepInfracheapest standard host | 32,768 | Not in named rows |
| Llama 3.1 Euryale 70B v2.2 | $0.85 | $0.85 | Standard · fp8 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Hermes 3 70B Instruct | $0.70 | $0.70 | Standard · fp8 | DeepInfracheapest standard host | 131,072 | Not in named rows |
| Hermes 3 405B Instruct | $1.00 | $1.00 | Standard · fp8 | DeepInfracheapest standard host | 131,072 | Not in named rows |
DeepInfra’s own endpoint for each model (standard tier and default region first), next to the cheapest standard price from any provider. Most widely served first.
Method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.