DeepSeek Flash Latest
DeepSeek Flash Latest is a large language model made by DeepSeek, added to the catalog on 14 Sep 2026. It has a context window of 1,048,576 tokens and costs $0.036 per 1M input tokens and $0.50 per 1M output tokens. It accepts text and images and produces text. Typical uses: working with long documents, answering questions about image input and generating structured text responses.
Price checked · source: OpenRouter
What DeepSeek Flash Latest is
DeepSeek: DeepSeek Flash Latest is an endpoint that redirects requests to the latest model in the DeepSeek Flash family. Its underlying model can therefore change as the family’s latest version changes. The catalog lists text and images as accepted inputs and text as the output. This makes it a multimodal model for workflows that combine written prompts with image input and receive a text response.
The model has a context window of 1,048,576 tokens and a maximum output of 943,718 tokens. Its listed context capacity can accommodate extensive source material, such as long documents or substantial collections of notes, in a single context. The output limit supports lengthy responses. The endpoint’s redirecting behavior means that the exact model version is not fixed.
Supported options include tools, structured outputs, response formats, and reasoning. These features suit requests that require a prescribed response structure or interaction with tools, as well as tasks involving analysis of text or images. The catalog does not specify particular tools, output schemas, image types, or domain specialties, so those details should not be assumed. DeepSeek Flash Latest is described as a family endpoint that follows the latest version, rather than as one fixed model version. These capabilities cover varied text-and-image tasks.
Key features
- Accepts text and image input and produces text
- Has a context window of 1,048,576 tokens
- Supports tools, structured outputs, response formats, and reasoning
- Redirects to the latest model in the DeepSeek Flash family
Typical uses
- Working with long documents
- Answering questions about image input
- Generating structured text responses
- Tool-supported tasks
DeepSeek Flash Latest pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.036 |
| Output, per 1M tokens | $0.50 |
| Cached input read, per 1M tokens | $0.01 |
No price change since it was added on 14 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0013 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0021 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0062 |
DeepSeek Flash Latest specifications
| Model id | ~deepseek/deepseek-flash-latest |
|---|---|
| Version | deepseek-flash-latest |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 14 Sep 2026 |
| Input types | text, image |
|---|---|
| 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 Flash Latest yet.
Compare DeepSeek Flash Latest
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.