DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
Specifications
| Lab | DeepSeek |
|---|---|
| Context window | 1.3M tokens |
| Input price | $0.02/1M |
| Output price | $0.32/1M |
| Release | Jul 2026 |
Strengths
- Million-token context window for very long tasks
- Low input pricing for cost-sensitive production workloads
- Tool-use support for agentic workflows
- Structured output support for reliable application integration
Weaknesses
- Newer listing with limited independent benchmark coverage
- Text-only inputs limit multimodal application coverage
Best for
- Agentic workflows and tool-using applications
- Long-context document and codebase processing
In Depth: DeepSeek V4 Flash 0731
Summary
DeepSeek V4 Flash 0731 is an AI model from DeepSeek.
Released in Jul 2026. It takes text input and produces text output, with a context window of 1.3M tokens. Input pricing is $0.02 per 1M tokens and output is $0.32 per 1M tokens on OpenRouter.