DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a large language model made by DeepSeek, added to the catalog on 31 Jul 2026. It has a context window of 1,048,576 tokens and costs $0.0443 per 1M input tokens and $0.30 per 1M output tokens. It accepts text and produces text. Typical uses: drafting and reviewing code, reasoning through written problems and working with long text inputs.
Price checked ยท source: OpenRouter
What DeepSeek V4 Flash 0731 is
DeepSeek V4 Flash 0731 is a text-in, text-out model from DeepSeek, described as a sparse mixture-of-experts revision intended for coding, reasoning, and agent workflows. It accepts text and produces text. Its context window holds up to 1,048,576 tokens, and its maximum output is 943,718 tokens. These limits make it suitable for interactions that need room for extensive supplied material, long instructions, or large generated responses. The context figure describes the available input context, while the output limit describes the maximum generated response; actual use depends on the request and configuration.
The model supports reasoning, tools, structured outputs, and response formats. Tool support can fit workflows in which a text model uses available tools as part of a task, while structured outputs and response-format support are relevant when a result needs a specified format. Coding work may include reading or drafting code, examining a technical description, and explaining a proposed change; reasoning work may include working through a written problem or organizing supplied information. Its text-only input and output make it a fit for text-based tasks rather than image or audio handling. It can also be considered for multi-step text tasks where the prompt and relevant context need to remain available across a longer exchange. The catalog does not specify particular programming languages or tool integrations, so those details depend on the environment in which it is used.
Key features
- Accepts text and produces text
- Supports a context of up to 1,048,576 tokens
- Maximum output of 943,718 tokens
- Supports tools, structured outputs, and response formats
- Includes support for reasoning
Typical uses
- Drafting and reviewing code
- Reasoning through written problems
- Working with long text inputs
- Generating structured responses
- Text-based tool workflows
DeepSeek V4 Flash 0731 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.0443 | $0.048 |
| Output, per 1M tokens | $0.30 | $0.144 |
| Cached input read, per 1M tokens | $0.035 | $0.012 |
| Variant | Model id |
|---|---|
| Batch | deepseek/deepseek-v4-flash-0731:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 31 Jul 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0013 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0019 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0071 |
DeepSeek V4 Flash 0731 specifications
| Model id | deepseek/deepseek-v4-flash-0731 |
|---|---|
| Version | deepseek-v4-flash-20260731 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 31 Jul 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 0731 yet.
Compare DeepSeek V4 Flash 0731
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.