PROVIDER PRICING
DeepInfra API Pricing
DeepInfra API pricing: rates for 27 models, how they compare to official pricing, and what it costs to run.
MODEL PRICING
API model pricing
27 models · prices per million tokens
| Model | Input / 1M | Output / 1M |
|---|---|---|
| bge-base-en-v1.5 | $0.0050 | — |
| bge-large-en-v1.5 | $0.010 | — |
| e5-large-v2 | $0.010 | — |
| Mistral-Nemo-Instruct-2407 | $0.019 | $0.030 |
| Meta-Llama-3.1-8B-Instruct-Turbo | $0.020 | $0.040 |
| Phi-4 | $0.070 | $0.140 |
| DeepSeek-V4-Flash | $0.090 | $0.180 |
| Llama-3.3-70B-Instruct-Turbo | $0.100 | $0.320 |
| Llama-4-Scout-17B-16E | $0.100 | $0.300 |
| Gemma-4-31B-it-turbo | $0.120 | $0.370 |
| DeepSeek-V3.2 | $0.260 | $0.380 |
| Claude Haiku 4.5 | $1.00 | $5.00 |
| DeepSeek-V4-Pro | $1.30 | $2.60 |
| Gemini 3.5 Flash | $1.50 | $9.00 |
| Claude Sonnet 5 | $2.00 | $10.00 |
| Qwen3.7-Max | $2.50 | $7.50 |
| FLUX-1-schnell | — | — |
| FLUX-2-dev | — | — |
| FLUX-2-max | — | — |
| FLUX-2-pro | — | — |
| Voxtral-Mini-3B | — | — |
| Voxtral-Small-24B | — | — |
Prices change frequently; confirm current rates on the provider’s official pricing page.