DeepInfra API pricing
by DeepInfraper 1M tokens
$0.18 / 1M outputDeepSeek V4 Flash (DeepInfra) · the cheapest model
DeepInfra API costs $0.09–$2.85 per 1M input tokens and $0.18–$14.25 per 1M output tokens. Output tokens cost several times more than input, so long answers drive the bill. DeepInfra sells API access only; there is no chat subscription.
Cheapest output$0.18DeepSeek V4 Flash (DeepInfra) · per 1M
Top model$14.25Kimi K3 (DeepInfra) · per 1M output
Every model, per 1M tokens
USD list price, before batch or volume discounts| Model | Input | Output | Cached input | Context |
|---|---|---|---|---|
| DeepSeek V4.1 Flash (DeepInfra) | $0.20 | $0.60 | $0.006 | 1M |
| DeepSeek V4 Pro (DeepInfra) | $1.30 | $2.60 | $0.10 | 1M |
| DeepSeek V4 Flash (DeepInfra) | $0.09 | $0.18 | $0.018 | 1M |
| DeepSeek V3.2 (DeepInfra) | $0.26 | $0.38 | $0.13 | 160K |
| DeepSeek R1 0528 (DeepInfra) | $0.50 | $2.15 | $0.35 | 160K |
| Kimi K3 (DeepInfra) | $2.85 | $14.25 | $0.285 | 1M |
| Kimi K2.6 (DeepInfra) | $0.75 | $3.50 | $0.15 | 256K |
| GLM-5.3 (DeepInfra) | $0.90 | $4.00 | $0.20 | 1M |
| GLM-5.2 (DeepInfra) | $0.75 | $2.40 | $0.14 | 1M |
| GLM-4.7 (DeepInfra) | $0.40 | $1.75 | $0.08 | 198K |
| Qwen3.5 397B A17B (DeepInfra) | $0.45 | $3.00 | $0.22 | 256K |
| Qwen3 Coder 480B A35B Turbo (DeepInfra) | $0.30 | $1.00 | $0.10 | 256K |
| Llama 4 Scout 17B 16E (DeepInfra) | $0.10 | $0.30 | — | 320K |
| Llama 3.3 70B Instruct Turbo (DeepInfra) | $0.10 | $0.32 | — | 128K |
| NVIDIA Nemotron 3 Ultra 550B A55B (DeepInfra) | $0.50 | $2.20 | $0.10 | 256K |
What will you pay?
$228.00
per month on Kimi K3 (DeepInfra)
Prices from deepinfra.com/pricing How we collect prices Some links are affiliate links; they never change the prices or the order shown. Disclosure