> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek V4.1 Flash 1017 Ultrafast API

> DeepSeek V4.1 Flash 1017 Ultrafast API on Venice: 1M context, $3.00 input and $12.00 output per 1M tokens. Private, with zero data retention.

> [accordion] Plain-text specification
>
> ## DeepSeek V4.1 Flash 1017 Ultrafast API
>
> DeepSeek V4.1 Flash 1017 Ultrafast is a large language model by DeepSeek, available on the Venice API as `deepseek-v4-1-flash-1017-ultrafast`. It runs privately, with zero data retention.
>
> DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
>
> ### DeepSeek V4.1 Flash 1017 Ultrafast API pricing
>
> | Model ID | Variant | Privacy | Price |
> | - | - | - | - |
> | `deepseek-v4-1-flash-1017-ultrafast` | Standard | Private | $3.00 / $12.00 per 1M |
>
> ### DeepSeek V4.1 Flash 1017 Ultrafast specifications
>
> | Spec | Value |
> | - | - |
> | Provider | DeepSeek |
> | Released | Oct 23, 2026 |
> | Privacy | Private |
> | Status | Stable |
> | Open weights | Yes |
> | Context window | 1M tokens |
> | Max output | 128K tokens |
> | Reasoning effort | none, low, high, max |
> | Served precision | FP8 |
>
> ### How to use the DeepSeek V4.1 Flash 1017 Ultrafast API
>
> Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "deepseek-v4-1-flash-1017-ultrafast"` and your API key.
>
> ```bash theme={"system"}
> curl https://api.venice.ai/api/v1/chat/completions \
>   -H "Authorization: Bearer $VENICE_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "deepseek-v4-1-flash-1017-ultrafast",
>     "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
>     "reasoning_effort": "high"
>   }'
> ```
>
> ### Related models
>
> * [Gemini 4 Argon API](https://docs.venice.ai/models/gemini-4-argon.md): $2.50 / $12.50 per 1M
> * [Aion 3.5 API](https://docs.venice.ai/models/aion-3-5.md): $3.75 / $7.50 per 1M
> * [Aion 3.0 API](https://docs.venice.ai/models/aion-3-0.md): $3.75 / $7.50 per 1M
> * [Kimi K3.1 Pro API](https://docs.venice.ai/models/kimi-k3-1-pro.md): $2.00 / $10.00 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.