DeepSeek V4 Pro pricing
DeepSeek V4 Pro, Flagship-tier from OpenRouter, costs $0.680862 per 1M input tokens and $1.36 per 1M output tokens.
Input$0.680862per 1M tokens
Output$1.36per 1M tokens
Context window1.05Mtokens
TierFlagshipOpenRouter
Price your own workload against DeepSeek V4 Pro in the calculator →
Specs and pricing
| Provider | OpenRouter |
| Tier | Flagship |
| Context window | 1.05M tokens |
| Max output | 384K tokens |
| Input price | $0.680862 / 1M tokens |
| Output price | $1.36 / 1M tokens |
| Cache read | $0.056739 / 1M tokens |
| Modalities | text |
Note. OpenRouter's default route for this model. DeepSeek itself is not one of the backends OpenRouter lists for it, so this is a third-party host's price, not DeepSeek's own -- compare against DeepSeek's own direct pricing if that distinction matters for you.
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 | $0.68 | $0.34 | $1.02 |
| 10,000,000 in / 2,500,000 out | $6.81 | $3.40 | $10.21 |
| 100,000,000 in / 25,000,000 out | $68.09 | $34.04 | $102.13 |
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 | 77% cheaper blended |
| GPT-OSS 120B | Groq | $0.15 | $0.60 | 70.6% cheaper blended |
| Qwen3 235B-A22B (2507) | Parasail | $0.14 | $0.80 | 66.7% cheaper blended |
| Llama 4 Maverick | Together AI | $0.27 | $0.85 | 52.8% cheaper blended |
| Llama 4 Maverick Instruct | Novita AI | $0.27 | $0.85 | 52.8% cheaper blended |