DeepSeek: 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
| Attribute | Value |
|---|---|
| Lab | DeepSeek |
| Tags | Intelligent Open Weight Coding Reasoning Agentic Fast |
| Release Date | 2026-07 |
| Context Window | 1,048,576 tokens |
| Input Price / 1M | $0.09 |
| Output Price / 1M | $0.18 |
| Input Modalities | Text |
| Output Modalities | Text |
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 2026-07. It supports Text input and produces Text output, with a context window of 1,048,576 tokens. Input pricing is $0.09 per 1M tokens and output is $0.18 per 1M tokens on OpenRouter.