DeepSeek V4 Pro
| Maker | DeepSeek |
|---|---|
| Released | 2026-04-24 |
| Context | 1M |
| Max output | 384K |
| Open weights | MIT |
|---|---|
| Modalities | text → text |
| Input / 1M | $1.32 |
| Output / 1M | $3.96 |
| Review call | $0.0442 |
|---|---|
| Reasoning efforts | none, low, high, max |
| Hosts | DeepSeek, OpenRouter |
| Model id | deepseek-v4-pro |
CodePanel's benchmark has not run DeepSeek V4 Pro as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
The same model is ranked on Workers AI, as DeepSeek V4 Pro (Workers AI): it caught 54% [43%–65%] of the known bugs at rank 4 of 17, with a measured review cost of $0.0643. Those results are for that host's copy, not for this listing. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0442 on DeepSeek V4 Pro and $0.0442 on DeepSeek V4 Pro (Workers AI), so this model's call is about the same as that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| DeepSeek | deepseek-v4-pro | $1.32 | $3.96 |
Source: DeepSeek pricing, Oct 16, 2026
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| Muse Spark 1.2 | Meta | $1.25 | $4.25 | $0.043 | 1M | – |
| Mistral Large 4 | Mistral | $1.36 | $4.18 | $0.0457 | 1M | – |
| GLM-5.3 (Workers AI) | Z.ai | $1.40 | $4.40 | $0.0473 | 1M | 61% |
| Qwen3.7 Max | Qwen | $1.475 | $4.425 | $0.0494 | 1M | – |
Updated Oct 23, 2026