DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
DeepSeek V4 Pro 0813 costs $0.1333 per 1M input tokens and $0.40 per 1M output tokens at the standard tier, the lowest default-region price among the 21 providers SF·SIX tracks, from Baidu (fp8). On DeepSeek’s own API it costs $0.66 / $1.98. Cached input reads cost $0.004242 per 1M tokens. Updated ; prices checked .
- Developer
- DeepSeek
- Input modalities
- text
- Output modalities
- text
- Context tokens
- 1,048,576
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.1333 input / $0.40 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| BaiduOpenRouter | $0.1333 | $0.40 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Sail ResearchOpenRouter | $0.448 | $1.16 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| WaferOpenRouter | $0.25 | $2.50 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepSeekOpenRouter | $0.66 | $1.98 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| StreamLakeOpenRouter | $0.66 | $1.98 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| IonstreamOpenRouter | $0.37 | $2.93 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| PhalaOpenRouter | $0.957 | $2.88 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Novita AIOpenRouter | $0.99 | $2.97 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| GMI CloudOpenRouter | $1.06 | $3.17 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DekaLLMOpenRouter | $0.88 | $3.80 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepInfraOpenRouter | $1.30 | $2.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AlibabaOpenRouter | $1.12 | $3.37 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| CoreWeaveOpenRouter | $1.31 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AtlasCloudOpenRouter | $1.32 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| CloudflareOpenRouter | $1.32 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DigitalOceanOpenRouter | $1.32 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| ParasailOpenRouter | $1.32 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| SiliconFlowOpenRouter | $1.32 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Together AIOpenRouter | $1.32 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| RelaceOpenRouter | $0.12 | $8.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Venice AIOpenRouter | $1.65 | $4.95 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Sail ResearchOpenRouter · US region | $0.448 | $1.16 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AlibabaOpenRouter · us-east-1 region | $1.32 | $3.96 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
Prices by service tier
| Tier | Input / 1M | Output / 1M | Cache read / 1M | Cheapest provider | vs standard (blended) |
|---|---|---|---|---|---|
| Standard | $0.1333 | $0.40 | $0.004242 | Baidu | 100% |
Each tier’s cheapest endpoint. Standard is the default-region headline; flex and batch trade speed or latency for a lower price, priority and fast cost more for faster service.
Regional endpoints
| Provider and region | Input / 1M | Output / 1M |
|---|---|---|
| Sail ResearchUS regionfp4 | $0.448 | $1.16 |
| Alibabaus-east-1 region | $1.32 | $3.96 |
Data-residency endpoints in a named region; they are never used as the headline while a default-region price exists.
Speed by provider
| Provider and terms | Throughput | Latency | Uptime | Input / 1M |
|---|---|---|---|---|
| Together AI | 110 tok/s | 938 ms | 100.0% | $1.32 |
| Wafermxfp4 | 96 tok/s | 466 ms | 100.0% | $0.25 |
| DekaLLM | 88 tok/s | 1.32 s | 100.0% | $0.88 |
| CoreWeavefp8 | 69 tok/s | 608 ms | 100.0% | $1.31 |
| Novita AIfp8 | 68 tok/s | 1.98 s | 100.0% | $0.99 |
| Relacefp4 | 68 tok/s | 1.11 s | 100.0% | $0.12 |
| DeepInfrafp8 | 67 tok/s | 972 ms | 100.0% | $1.30 |
| Alibabaus-east-1 region | 62 tok/s | 1.97 s | Not reported | $1.32 |
| Ionstream | 61 tok/s | 739 ms | 100.0% | $0.37 |
| Alibaba | 59 tok/s | 1.28 s | 100.0% | $1.12 |
| SiliconFlowfp8 | 57 tok/s | 1.37 s | 100.0% | $1.32 |
| Cloudflare | 52 tok/s | 886 ms | Not reported | $1.32 |
Previous 30 minutes; reported by OpenRouter. Fastest first.
Usage on OpenRouter
| UTC day | Tokens |
|---|---|
| 2026-10-10 | 172,178,630,129 |
| 2026-10-11 | 169,667,499,626 |
| 2026-10-12 | 119,932,050,940 |
| 2026-10-13 | 114,622,309,392 |
| 2026-10-14 | 128,425,150,504 |
| 2026-10-15 | 158,193,665,454 |
| 2026-10-16 | 161,086,111,445 |
OpenRouter rankings (CC BY 4.0), named daily rows. Most-used AI models
Benchmarks
Artificial Analysis Intelligence Index 36.0, coding index 68.8, agentic index 41.3 (Artificial Analysis via OpenRouter, CC BY 4.0; not an SF·SIX measurement).
Prediction markets
DeepSeek V4 Pro 0813 meets the rule for SF·SIX price and usage ladders; the current average standard input price across qualifying OpenRouter endpoints is $0.9797 per 1M tokens. Open DeepSeek V4 Pro 0813 markets (Hedera testnet, test funds only) · How AI prediction markets work
Compare and estimate
Sources and method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Prices from OpenRouter; each row below links its source and observation date. Methodology and editorial policy.
Frequently asked questions
How much does DeepSeek V4 Pro 0813 cost per 1M tokens?
$0.1333 per 1M input tokens and $0.40 per 1M output tokens at the standard tier, the lowest default-region price SF·SIX tracks, from Baidu (fp8). On DeepSeek’s own API it costs $0.66 / $1.98.
Which providers offer DeepSeek V4 Pro 0813?
21 providers with 23 priced endpoints: Alibaba, AtlasCloud, Baidu, Cloudflare, CoreWeave, DeepInfra, DeepSeek, DekaLLM and others.
What is the context window of DeepSeek V4 Pro 0813?
1,048,576 tokens.
How fast is DeepSeek V4 Pro 0813?
The fastest measured endpoint is Together AI at 110 tok/s, as reported by OpenRouter for the previous 30 minutes.
How much is DeepSeek V4 Pro 0813 used?
161,086,111,445 tokens on 2026-10-16 (UTC) through OpenRouter, per OpenRouter’s public rankings. This is OpenRouter traffic only, not all usage.
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.