DeepSeek
DeepSeek V4 Pro 0813
Launched 2026-08-13 · Listed on OpenRouter 2026-08-12
Prices updated . Benchmarks updated .
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
You send / 1M
$0.111
tokens in
It replies / 1M
$4.44
tokens out
Context
1M
tokens it can read at once
Typical request
$0.0024
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 155.9 | Independent | 2026-08-13 | Epoch AI |
| GPQA DiamondMax effort | 91.7% | Independent | 2026-08-18 | Epoch AI |
| OTIS Mock AIMEMax effort | 98.6% | Independent | 2026-08-18 | Epoch AI |
| SimpleQA VerifiedMax effort | 52.9% | Independent | 2026-08-27 | Epoch AI |
| ARC-AGI-2Max effort | 61.3% | Independent | 2026-08-13 | ARC Prize, republished by Epoch AI |
| CritPtMax effort | 18.0% | Independent | 2026-08-13 | CritPt, republished by Epoch AI |
Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp8 | $1.04 | $2.08 | 100% | Read |
| Sail Research · fp4 | $1.35 | $2.40 | 100% | Read |
| Sail Research · fp4 | $1.35 | $2.40 | 100% | Read |
| DeepInfra · fp8 | $1.30 | $2.60 | 100% | Read |
| Novita · fp8 | $0.990 | $2.97 | 100% | Read |
| DeepInfra · fp8 | $1.95 | $3.90 | 98% | Read |
| BaseTen · fp4 | $1.32 | $3.96 | 100% | Read |
| Nebius · fp8 | $1.32 | $3.96 | 99% | Read |
| CoreWeave · fp8 | $1.31 | $3.96 | 100% | Read |
| Parasail · fp8 | $1.32 | $3.96 | 99% | Read |
| Together | $1.32 | $3.96 | 99% | Read |
| DigitalOcean | $1.32 | $3.96 | 100% | Read |
| SiliconFlow · fp8 | $1.32 | $3.96 | 99% | Read |
| Cloudflare | $1.32 | $3.96 | 69% | Read |
| Wafer · mxfp4 | $0.285 | $4.30 | 100% | Read |
| Wafer · mxfp4 | $0.111 | $4.44 | 100% | Read |
| Venice | $1.65 | $4.95 | 99% | Read |
| Parasail · fp8 | $1.98 | $5.94 | 100% | Read |
| Relace · fp4 | $0.100 | $8.00 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Weights: Open weights
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 384K tokens
- Repeated text is billed at $0.097 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with DeepSeek V4 Pro 0813
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
