D
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017, a language model from DeepInfra.
modelOverride: { model: "deepseek-v4.1-flash-1017" }
DeepSeek·served via
DeepInfra·Released October 2026Pricing
- Input
- $0.20 / 1M
- Output
- $0.60 / 1M
- Cached input
- $0.0060 / 1M
Specifications
- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Released
- October 2026
- Model string
- deepseek-ai/DeepSeek-V4.1-Flash-1017
- Capabilities
- VisionMultimodal
Parameters
Model options, passed in
modelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
reasoning_effortNon-think for fast responses, High for everyday work, Max to push reasoning to its fullest extent. | Select | high | nonelowhighxhighmax |
top_pNucleus sampling. Official default is 0.95. | Number | 0.95 | 0–1, step 0.01 |
seed | Seed | — | -1–2147483647 |
Use this model
await mindstudio.generateText({ message: "...", modelOverride: { model: "deepseek-v4.1-flash-1017", config: { reasoning_effort: "high", top_p: 0.95, }, }, });