DeepSeek Flash
| Maker | DeepSeek |
|---|---|
| Released | 2026-09-10 |
| Context | 1M |
| Max output | 384K |
| Open weights | MIT |
|---|---|
| Modalities | text, image → text |
| Input / 1M | $0.30 |
| Output / 1M | $1.20 |
| Review call | $0.0108 |
|---|---|
| Reasoning efforts | none, low, high, max |
| Hosts | DeepSeek |
| Model id | deepseek-flash |
CodePanel's benchmark has not run DeepSeek Flash 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 newest ranked model in the DeepSeek Flash line is DeepSeek V4 Flash (Workers AI). It caught 49% [37%–60%] of the known bugs at rank 5 of 17, with a measured review cost of $0.0178. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0108 on DeepSeek Flash and $0.0147 on DeepSeek V4 Flash (Workers AI), so this model's call is 27% less than that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| DeepSeek | deepseek-flash | $0.30 | $1.20 |
Source: DeepSeek pricing, Oct 16, 2026
| Version | Released | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| DeepSeek V4 Flash | 2026-10-17 | $0.30 | $1.20 | 1M |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| GPT-OSS 120B (Workers AI) | OpenAI | $0.35 | $0.75 | $0.011 | 128K | 40% |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | $0.0102 | 1M | – | |
| Codestral 25.08 | Mistral | $0.30 | $0.90 | $0.01 | 128K | – |
| MiMo-V2.6-Pro (OpenRouter) | Xiaomi | $0.435 | $0.87 | $0.0135 | 1.1M | – |
Updated Oct 23, 2026