DeepSeek-V4-Pro pricing
DeepSeek-V4-Pro, Flagship-tier from DeepInfra, costs $1.30 per 1M input tokens and $2.60 per 1M output tokens.
Input$1.30per 1M tokens
Output$2.60per 1M tokens
Context window1.02Mtokens
TierFlagshipDeepInfra
Price your own workload against DeepSeek-V4-Pro in the calculator →
Specs and pricing
| Provider | DeepInfra |
| Tier | Flagship |
| Context window | 1.02M tokens |
| Max output | — |
| Input price | $1.30 / 1M tokens |
| Output price | $2.60 / 1M tokens |
| Cache read | $0.10 / 1M tokens |
| Modalities | text |
Note. Context listed on page as '1024k'.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $1.30 | $0.65 | $1.95 |
| 10,000,000 in / 2,500,000 out | $13.00 | $6.50 | $19.50 |
| 100,000,000 in / 25,000,000 out | $130.00 | $65.00 | $195.00 |
Cheaper alternatives
Same tier (Flagship), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Qwen3 235B A22B Instruct 2507 | Novita AI | $0.09 | $0.58 | 87.9% cheaper blended |
| GPT-OSS 120B | Groq | $0.15 | $0.60 | 84.6% cheaper blended |
| Qwen3 235B-A22B (2507) | Parasail | $0.14 | $0.80 | 82.6% cheaper blended |
| Llama 4 Maverick | Together AI | $0.27 | $0.85 | 75.3% cheaper blended |
| Llama 4 Maverick Instruct | Novita AI | $0.27 | $0.85 | 75.3% cheaper blended |