Provider
DeepInfra API Pricing
DeepInfra pricing across 27 models.
- Provider type+32
- Official price source+8
- Price level-4
- Model coverage+5
- 1Create an account and get an API key
- 2Point your SDK at this base URL
- 3Call it with your usual model names
Model pricing
| Provider | Model | Input | Output | Cached input | Price | vs official | |
|---|---|---|---|---|---|---|---|
DeepInfraInference platform | bge-base-en-v1.5 bge-base-en-v1.5 | $0.0050 | — | — | — | — | Use |
DeepInfraInference platform | bge-large-en-v1.5 bge-large-en-v1.5 | $0.010 | — | — | — | — | Use |
DeepInfraInference platform | e5-large-v2 e5-large-v2 | $0.010 | — | — | — | — | Use |
DeepInfraInference platform | Mistral-Nemo-Instruct-2407 mistral-nemo-instruct-2407 | $0.019 | $0.030 | — | — | — | Use |
DeepInfraInference platform | Meta-Llama-3.1-8B-Instruct-Turbo meta-llama-3.1-8b-instruct-turbo | $0.020 | $0.040 | — | — | — | Use |
DeepInfraInference platform | Phi-4 phi-4 | $0.070 | $0.140 | — | — | — | Use |
DeepInfraInference platform | DeepSeek-V4-Flash deepseek-v4-flash | $0.090 | $0.180 | — | — | 0.64× | Use |
DeepInfraInference platform | Llama-3.3-70B-Instruct-Turbo llama-3.3-70b-instruct-turbo | $0.100 | $0.320 | — | — | — | Use |
DeepInfraInference platform | Llama-4-Scout-17B-16E llama-4-scout-17b-16e | $0.100 | $0.300 | — | — | — | Use |
DeepInfraInference platform | Gemma-4-31B-it-turbo gemma-4-31b-it-turbo | $0.120 | $0.370 | — | — | — | Use |
DeepInfraInference platform | DeepSeek-V3.2 deepseek-v3.2 | $0.260 | $0.380 | — | — | — | Use |
DeepInfraInference platform | Claude Haiku 4.5 claude-haiku-4-5 | $1.00 | $5.00 | — | — | 1.00× | Use |
DeepInfraInference platform | DeepSeek-V4-Pro deepseek-v4-pro | $1.30 | $2.60 | — | — | 2.99× | Use |
DeepInfraInference platform | Gemini 3.5 Flash gemini-3.5-flash | $1.50 | $9.00 | — | — | 2.00× | Use |
DeepInfraInference platform | Claude Sonnet 5 claude-sonnet-5 | $2.00 | $10.00 | — | — | 0.67× | Use |
DeepInfraInference platform | Qwen3.7-Max qwen3.7-max | $2.50 | $7.50 | — | — | 1.69× | Use |
DeepInfraInference platform | A100-80GB A100-80GB | — | — | — | $0.890/hr | — | Use |
DeepInfraInference platform | B200-180GB B200-180GB | — | — | — | $3.69/hr | — | Use |
DeepInfraInference platform | B300-270GB B300-270GB | — | — | — | $4.89/hr | — | Use |
DeepInfraInference platform | H100-80GB H100-80GB | — | — | — | $2.20/hr | — | Use |
DeepInfraInference platform | H200-141GB H200-141GB | — | — | — | $2.69/hr | — | Use |
DeepInfraInference platform $0.0005 × (w/1024) × (h/1024) × steps | FLUX-1-schnell flux-1-schnell | — | — | — | $0.00050/image | — | Use |
DeepInfraInference platform $0.01 × (w/1024) × (h/1024) × (steps/28) | FLUX-2-dev flux-2-dev | — | — | — | $0.010/image | — | Use |
DeepInfraInference platform | FLUX-2-max flux-2-max | — | — | — | $0.070/image | — | Use |
DeepInfraInference platform | FLUX-2-pro flux-2-pro | — | — | — | $0.015/image | — | Use |
DeepInfraInference platform | Voxtral-Mini-3B voxtral-mini-3b-2507 | — | — | — | $0.0010/min | — | Use |
DeepInfraInference platform | Voxtral-Small-24B voxtral-small-24b-2507 | — | — | — | $0.0030/min | — | Use |
Prices captured Jul 26, 2026
Prices change frequently and promotional rates expire — always confirm on the provider's own pricing page before committing. Rates far below official pricing often indicate shared or resold accounts.