DeepSeek
DeepSeek V4 Pro 0423
Launched 2026-04-24 · Knowledge up to 2025-05 · Listed on OpenRouter 2026-04-24
Prices updated . Benchmarks updated .
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
You send / 1M
$0.900
tokens in
It replies / 1M
$1.50
tokens out
Context
1M
tokens it can read at once
Typical request
$0.0019
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 149.1 | Independent | 2026-04-24 | Epoch AI |
| GPQA DiamondHigh effort | 90.9% | Independent | 2026-08-06 | Epoch AI |
| OTIS Mock AIMEMax effort | 96.7% | Independent | 2026-06-17 | Epoch AI |
| SimpleQA VerifiedMax effort | 47.0% | Independent | 2026-08-27 | Epoch AI |
| SWE-bench VerifiedMax effort | 77.6% | Independent | 2026-06-18 | Epoch AI |
| CritPtMax effort | 12.9% | Independent | 2026-04-24 | CritPt, republished by Epoch AI |
| Arena Elo (text) | 1,451 | Independent | 2026-10-28 | LMArena |
| Arena Elo (webdev) | 1,447 | Independent | 2026-10-28 | LMArena |
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 |
|---|---|---|---|---|
| Relace · fp4 | $0.900 | $1.50 | 100% | Read |
| SiliconFlow · fp8 | $1.00 | $1.50 | 100% | Read |
| DeepInfra · fp8 | $1.04 | $2.08 | 100% | Read |
| DigitalOcean | $1.04 | $2.09 | 100% | Read |
| DeepInfra · fp8 | $1.30 | $2.60 | 100% | Read |
| Novita · fp8 | $1.60 | $3.20 | 100% | Read |
| Venice | $1.65 | $3.30 | 99% | Read |
| Azure | $1.91 | $3.83 | 100% | Read |
| DeepInfra · fp8 | $1.95 | $3.90 | 99% | 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: 393K tokens
- Repeated text is billed at $0.250 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with DeepSeek V4 Pro 0423
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.
