DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is a large language model made by DeepSeek, added to the catalog on 17 Oct 2026. It has a context window of 1,048,576 tokens and costs $0.15 per 1M input tokens and $0.60 per 1M output tokens. It accepts text and images and produces text. Typical uses: long-document analysis, text generation and reasoning over text.
Price checked · source: OpenRouter
What DeepSeek V4.1 Flash 1017 is
DeepSeek V4.1 Flash 1017 is a snapshot of DeepSeek V4.1 Flash, a sparse mixture-of-experts model served by DeepSeek under the API name deepseek-flash. The snapshot is dated October 17, 2026. It accepts text and image inputs and produces text. Its supported capabilities include reasoning, tool use, structured outputs and response-format options, which can be used to shape interactions in applications.
The model has a context length of 1,048,576 tokens and supports up to 393,216 output tokens. Its large context window can accommodate substantial input material in an interaction, while the output limit allows for long text responses. The model accepts both written and visual input, but its listed output modality is text. The catalog does not specify image formats or further details about how image inputs are handled.
These features suit tasks involving long documents, text generation, reasoning and coding, as well as questions that combine written and visual material. Tool support is relevant to applications that connect model interactions with tools, though the catalog does not name particular tools. Structured outputs and response-format support can be useful when an application needs text returned in a defined format. The listed facts establish these capabilities but do not identify specialized domains or particular workflows. The model’s API model name is deepseek-flash, while its catalog listing identifies the specific snapshot as DeepSeek V4.1 Flash 1017.
Key features
- Accepts text and image inputs and produces text
- Supports a context length of 1,048,576 tokens
- Supports up to 393,216 output tokens
- Supports reasoning and tool use
- Supports structured outputs and response formats
Typical uses
- Long-document analysis
- Text generation
- Reasoning over text
- Coding assistance
- Questions about text and images
DeepSeek V4.1 Flash 1017 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.15 | $0.035 |
| Output, per 1M tokens | $0.60 | $0.149 |
| Cached input read, per 1M tokens | $0.003 | $0.0029 |
| Variant | Model id |
|---|---|
| Batch | deepseek/deepseek-v4.1-flash-1017: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.
The price last changed on 21 Nov 2026. 2 price changes have been recorded since DeepSeek V4.1 Flash 1017 was added.
| Date | Input /1M | Output /1M | Change |
|---|---|---|---|
| $0.15 | $0.60 | Price raised | |
| $0.036 | $0.50 | Price lowered | |
| $0.15 | $0.60 | Added at this price |
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0003 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0042 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0057 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.023 |
DeepSeek V4.1 Flash 1017 specifications
| Model id | deepseek/deepseek-v4.1-flash-1017 |
|---|---|
| Version | deepseek-v4.1-flash-20261017 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 393,216 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 17 Oct 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 V4.1 Flash 1017 yet.
Compare DeepSeek V4.1 Flash 1017
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.