DeepSeek: DeepSeek V4.1 Flash 1017
The October 17, 2026 update to DeepSeek V4.1 Flash. DeepSeek's official API serves this version under the deepseek-flash model name.
- Model lab
- DeepSeek
- Model family
- deepseek-flash
Model resources
Quickstart
For this model’s request parameters and format, see its API documentation.
DeepSeek V4.1 Flash 1017 API Pricing
The Moduck prices shown here are calculated from OpenInference (OpenRouter) rates for model version 2026-10-17, collected on 2026-11-03. View rate source
| Type | Price information |
|---|---|
| Input · Quantization fp4 | USD 0.028 / 1M tokens |
| Output · Quantization fp4 | USD 0.4 / 1M tokens |
| Cached input · Quantization fp4 | USD 0.004 / 1M tokens |
Benchmarks
Performance
Measured on the Moduck gateway across live traffic, hour by hour over the last 24 hours. Time to first token is how long before anything appears; throughput is how fast the answer is written after that; end-to-end latency is the whole round trip. Figures are medians unless the card says otherwise.
Performance trends
Availability
Uptime is the share of time at least one provider serving this model responded. Availability is stricter: the share of requests actually served. A provider that answers but fails part of the traffic lowers availability without lowering uptime. Both cover the last three days.
DeepSeek V4.1 Flash 1017 Compare models
| Model | Input price | Output price | Context window | Capabilities |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017This page | USD 0.028 / 1M tokens · Quantization fp4 | USD 0.4 / 1M tokens · Quantization fp4 | 1,000,000 | Text output · Reasoning · Tool calling |
| DeepSeek V4.1 Flash (2026-09-10) | USD 0.03776 / 1M tokens · Quantization fp4 | USD 0.096 / 1M tokens · Quantization fp4 | 1,000,000 | Text output · Reasoning · Tool calling |
| DeepSeek V4 Flash Vision Exp | USD 0.112 / 1M tokens | USD 0.224 / 1M tokens | 1,000,000 | Text output · Reasoning · Tool calling |
| DeepSeek V4 Flash 0731 | USD 0.028 / 1M tokens | USD 0.056 / 1M tokens | 1,000,000 | Text output · Reasoning · Tool calling |
| DeepSeek V4 Flash | USD 0.032 / 1M tokens · Quantization fp4 | USD 0.1088 / 1M tokens · Quantization fp4 | 1,000,000 | Text output · Reasoning · Tool calling |
Model specifications
- Input
- text, image
- Output
- text
- Context window
- 1,000,000
- Maximum output
- 384,000
- Release date
- 2026-10-17
- Attachments
- Yes
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Open weights
- Yes
Frequently asked questions
What is DeepSeek V4.1 Flash 1017 for?
The October 17, 2026 update to DeepSeek V4.1 Flash. DeepSeek's official API serves this version under the deepseek-flash model name.
What inputs and outputs does DeepSeek V4.1 Flash 1017 support?
Recorded inputs: text, images; outputs: text.
How is DeepSeek V4.1 Flash 1017 priced?
The pricing table shows the current recorded Moduck price. For example: Input · Quantization fp4 USD 0.028 / 1M tokens; Output · Quantization fp4 USD 0.4 / 1M tokens. See the pricing table for all units, variants, and conditions.
What specifications are recorded for DeepSeek V4.1 Flash 1017?
Current model records list Context window 1,000,000 tokens; Maximum output 384,000 tokens.
What model parameter does the Quickstart use?
The example uses deepseek/deepseek-v4.1-flash-1017. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.
Can I call this model through the Moduck API now?
This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.