DeepSeek: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task... 1M-token context window for long documents and agent traces Sparse MoE design keeps inference cost low at $0.15/$0.60 per million tokens Text and image input for coding and technical tasks New release with limited independent benchmark coverage OpenRouter pricing varies by time-of-day schedule Long-context coding and repository analysis Cost-sensitive agents with large prompts Mixed text-and-image technical tasks
Specifications
| Lab | DeepSeek |
|---|---|
| Context window | 1,048,576 |
| Input price | $0.15/1M |
| Output price | $0.60/1M |
| Release | 2026-09-01 00:00:00 |
Strengths
- 1M-token context window for long documents and agent traces
- Sparse MoE design keeps inference cost low at $0.15/$0.60 per million tokens
- Text and image input for coding and technical tasks
Weaknesses
- New release with limited independent benchmark coverage
- OpenRouter pricing varies by time-of-day schedule
Best for
- Long-context coding and repository analysis
- Cost-sensitive agents with large prompts
- Mixed text-and-image technical tasks
In Depth: DeepSeek V4.1 Flash
Summary
DeepSeek V4.1 Flash is an AI model from DeepSeek.
Released 2026-09-01 00:00:00. It supports Text, image input and produces Text output, with a context window of 1M tokens. Input pricing is $0.15 per 1M tokens and output is $0.60 per 1M tokens on OpenRouter.