DeepSeek V4 Pro (model version DeepSeek-V4-Pro-0813) is DeepSeek's top API model. It supports thinking and non-thinking modes, JSON output and tool calls, and accepts both OpenAI- and Anthropic-format requests. Prices shown are peak rates; off-peak rates are half.
DeepSeek V4 Pro
DeepSeek's most capable API model, with a 1M-token context
Checked 2026-11-12 against DeepSeek's documentation
| Provider | DeepSeek |
| Status | Current |
| Context window | 1M tokens |
| Pricing | Paid |
| Input price | $1.32/M |
| Output price | $3.96/M |
| Capabilities | textcodefunction-callingreasoning |
| API docs | Docs ↗ |
Benchmarks
Benchmark data not yet available for this model.
Loading…
Compare with similar models
| DeepSeek V4 Pro | Claude Opus 4.6 | Gemini 2.5 Pro | Claude Fable 5.2 | |
|---|---|---|---|---|
| Context | 1M | 200K | 1.05M | 1M |
| MMLU | — | 92.0 | 91.0 | — |
| HumanEval | — | 94.5 | — | — |
| MATH | — | 97.1 | 97.0 | — |
| GPQA | — | 79.9 | 84.0 | — |
| Pricing | Paid | Paid | Paid | Paid |
| Input $/M | $1.32 | $15.00 | $1.25 | $8.00 |