DeepSeek V4 Pro 0813 pricing & benchmarks
DeepSeek V4 Pro 0813 is available from DeepSeek at $1.32 per million input tokens and $3.96 per million output tokens ($1.98 blended at 3:1). It accepts up to 1,048,576 tokens of context. DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Pricing
Per million tokens · OpenRouter
Input$1.32
Output$3.96
Blended (3:1)$1.98
Specification
deepseek/deepseek-v4-pro-0813
Context window1.0M
Max output393K
ReleasedAug 2026
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for DeepSeek V4 Pro 0813 yet. We show nothing rather than reprinting an unverified figure.
Where to run DeepSeek V4 Pro 0813
23 options across 21 providers · 4.6× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Sail Research (us) | $0.537 | $0.450 / $0.800 | 1.0M | fp4 | 100.0% |
| Sail Research | $0.537 | $0.450 / $0.800 | 1.0M | fp4 | 100.0% |
| StreamLake | $0.990 | $0.660 / $1.98 | 1.0M | — | 100.0% |
| DeepSeek | $0.990 | $0.660 / $1.98 | 1.0M | — | 100.0% |
| Ionstream | $1.01 | $0.370 / $2.93 | 1.0M | — | 100.0% |
| Wafer | $1.44 | $0.250 / $5.00 | 1.0M | mxfp4 | 99.9% |
| Novita | $1.48 | $0.990 / $2.97 | 1.0M | fp8 | 100.0% |
| GMICloud | $1.58 | $1.06 / $3.17 | 1.0M | fp8 | 100.0% |
| DekaLLM | $1.61 | $0.880 / $3.80 | 1.0M | — | 99.6% |
| DeepInfra | $1.63 | $1.30 / $2.60 | 1.0M | fp8 | 100.0% |
| Alibaba | $1.68 | $1.12 / $3.37 | 1M | — | 99.8% |
| CoreWeave | $1.97 | $1.31 / $3.96 | 1.0M | fp8 | 100.0% |
| Alibaba (us-east-1) | $1.98 | $1.32 / $3.96 | 1M | — | 99.7% |
| AtlasCloud | $1.98 | $1.32 / $3.96 | 1.0M | fp8 | 99.8% |
| Baidu | $1.98 | $1.32 / $3.96 | 1.0M | fp8 | 100.0% |
| Parasail | $1.98 | $1.32 / $3.96 | 1.0M | fp8 | 99.8% |
| Together | $1.98 | $1.32 / $3.96 | 1.0M | — | 99.9% |
| DigitalOcean | $1.98 | $1.32 / $3.96 | 1.0M | — | 100.0% |
| SiliconFlow | $1.98 | $1.32 / $3.96 | 1.0M | fp8 | 99.9% |
| Cloudflare | $1.98 | $1.32 / $3.96 | 1.0M | — | 100.0% |
| Relace | $2.17 | $0.224 / $8.00 | 1.0M | fp4 | 100.0% |
| Phala | $2.18 | $1.45 / $4.36 | 1.0M | — | 100.0% |
| Venice | $2.48 | $1.65 / $4.95 | 1M | — | 94.6% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 vs Gemini 3.7 Flash
DeepSeek V4 Pro 0813 vs Grok 4.6
DeepSeek V4 Pro 0813 vs Inkling Small
DeepSeek V4 Pro 0813 vs Qwen3.7 Flash
DeepSeek V4 Pro 0813 vs Claude Opus 5
DeepSeek V4 Pro 0813 vs Gemini 3.6 Flash
DeepSeek V4 Pro 0813 vs Gemini 3.5 Flash Lite
DeepSeek V4 Pro 0813 vs Inkling
FAQ
How much does DeepSeek V4 Pro 0813 cost?
DeepSeek V4 Pro 0813 costs $1.32 per million input tokens and $3.96 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $1.98 per million tokens.
What is DeepSeek V4 Pro 0813's context window?
DeepSeek V4 Pro 0813 accepts up to 1,048,576 tokens of context, and can generate up to 393,216 output tokens.