DeepInfra
DeepInfra is an inference cloud: open models and a few partner models sold per token through an OpenAI-compatible API, with priority and flex tiers and a batch API, plus dedicated GPU deployments for a customer's own model, billed per GPU-hour. It names no region.
- Website: https://deepinfra.com
- Headquarters: Palo Alto, United States
- Kind: Inference provider, Per-token API, GPU cloud
DeepInfra sells 36 of the compared models per token and prices 5 kinds of GPU for hosting your own.
Models sold per token
| Model | Input, per 1M tokens | Output, per 1M tokens |
|---|---|---|
| Claude Fable 5 | $10.00 | $50.00 |
| Claude Haiku 4.5 | $1.00 | $5.00 |
| Claude Opus 4.7 | $5.00 | $25.00 |
| Claude Opus 4.8 | $5.00 | $25.00 |
| Claude Opus 5 | $5.00 | $25.00 |
| Claude Opus 5.5 | $4.00 | $20.00 |
| Claude Sonnet 4.6 | $3.00 | $15.00 |
| Claude Sonnet 5 | $3.00 | $15.00 |
| Claude Sonnet 5.5 | $2.00 | $10.00 |
| DeepSeek V3.1 | $0.25 | $0.95 |
| DeepSeek V3.2 | $0.26 | $0.38 |
| DeepSeek V4 Flash | $0.09 | $0.18 |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 |
| DeepSeek V4 Pro | $1.30 | $2.60 |
| DeepSeek V4 Pro 0813 | $1.30 | $2.60 |
| DeepSeek V4.1 Flash | $0.14 | $0.42 |
| Gemini 2.5 Flash | $0.30 | $2.50 |
| Gemini 2.5 Pro | $1.25 | $10.00 |
| Gemma 3 27B | $0.08 | $0.16 |
| Gemma 4 26B A4B | $0.07 | $0.34 |
| GLM 5.2 | $0.5625 | $1.80 |
| GLM 5.3 | $0.5625 | $2.50 |
| GLM 5.3 Flash | $0.15 | $0.50 |
| Kimi K2.6 | $0.75 | $3.50 |
| Kimi K3 | $2.85 | $14.25 |
| Llama 3.3 70B | $0.10 | $0.32 |
| Llama 4 Scout 17B | $0.10 | $0.30 |
| MiniMax M3 | $0.28 | $1.10 |
| Mistral Small | $0.05 | $0.08 |
| OpenAI gpt-oss 120B | $0.037 | $0.17 |
| OpenAI gpt-oss 20B | $0.03 | $0.14 |
| Phi-4 | $0.07 | $0.14 |
| Qwen3 235B A22B Instruct 2507 | $0.09 | $0.55 |
| Qwen3 32B | $0.08 | $0.28 |
| Qwen3.5 397B A17B | $0.45 | $3.00 |
| Qwen3.8 27B | $0.15 | $1.88 |
GPUs for hosting your own
| GPU | From, per GPU-hour | Cheapest instance | GPUs in it |
|---|---|---|---|
| A100 | $1.49 | a100.1x | 1 × 80 GB |
| H100 | $2.90 | h100.1x | 1 × 80 GB |
| H200 | $3.49 | h200.1x | 1 × 141 GB |
| B200 | $4.89 | b200.1x | 1 × 180 GB |
| B300 | $5.89 | b300.1x | 1 × 270 GB |
Where it runs
One global price; DeepInfra chooses where a request is processed.
No place stated for 36 models: one global price, and DeepInfra does not say where a request is processed.
Where the prices come from
- Per-token prices: deepinfra.com/pricing
- GPU servers: deepinfra.com/pricing
Sources
List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.