DeepSeek V4 Flash Latest
DeepSeek V4 Flash Latest is a large language model made by DeepSeek, added to the catalog on 1 Aug 2026. It has a context window of 1,048,576 tokens and costs $0.044 per 1M input tokens and $0.132 per 1M output tokens. It accepts text and produces text. Typical uses: summarising lengthy documents, drafting extended text and extracting key points from supplied material.
Price checked ยท source: OpenRouter
What DeepSeek V4 Flash Latest is
DeepSeek V4 Flash Latest is a text-in, text-out model identifier that redirects to the latest model in the DeepSeek V4 Flash family. It accepts text and produces text. Its context window holds up to 1,048,576 tokens, and it can generate up to 131,072 output tokens. This capacity suits workflows built around lengthy source material, extensive prompts, or longer responses, including document analysis, summarisation, and drafting. The listed input and output modalities are text only; the catalog does not describe image, audio, or other non-text capabilities.
The model supports reasoning, tool use, structured outputs, and response formats. These features suit tasks that call for stepwise reasoning, a tool-supported text workflow, or content returned in a defined structure. The large context can accommodate multiple passages or a long document alongside task instructions, while the output limit leaves room for detailed responses. Because the identifier redirects to the latest model in the family, it does not name a fixed underlying version in the supplied facts. No particular tools, schema formats, languages, or specialist domains are specified, so selection should be based on the documented text handling and supported capabilities. Potential work includes extracting key points, organizing information into structured responses, and producing longer-form text from supplied material.
Key features
- Accepts text and produces text
- Context window of up to 1,048,576 tokens
- Supports up to 131,072 output tokens
- Supports reasoning, tools, structured outputs, and response formats
Typical uses
- Summarising lengthy documents
- Drafting extended text
- Extracting key points from supplied material
- Producing structured responses
DeepSeek V4 Flash Latest pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.044 |
| Output, per 1M tokens | $0.132 |
| Cached input read, per 1M tokens | $0.0014 |
No price change since it was added on 1 Aug 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0012 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0016 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0068 |
DeepSeek V4 Flash Latest specifications
| Model id | ~deepseek/deepseek-v4-flash-latest |
|---|---|
| Version | deepseek-v4-flash-latest |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 1 Aug 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for DeepSeek V4 Flash Latest yet.
Compare DeepSeek V4 Flash Latest
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.