Official DeepSeek API

DeepSeek V4.1 Flash

DeepSeek's own stock Flash model, run by DeepSeek through its official API.

These are DeepSeek's stock models, served through DeepSeek's official API. They are not abliterated and keep DeepSeek's own refusals.

DeepSeek may also decline some requests on its side under its own terms of use. See the DeepSeek Terms of Use.

Prompts and outputs for these models are sent to DeepSeek, processed and stored in the People's Republic of China under DeepSeek's privacy policy, and may be used by DeepSeek to train its models. Our no-storage promise covers our own systems only. See the DeepSeek Privacy Policy and our privacy policy.

Specs

Model id: deepseek-v4.1-flash
Context length: 1,048,576 tokens
Max output: 393,216 tokens (4,096 on trial accounts)
Input: Text only. Image, audio, video and file inputs are rejected.
Runs on: DeepSeek's own servers, through the official DeepSeek API.
Reasoning: Per request: reasoning_effort on Chat Completions, thinking on Messages, reasoning.effort on Responses. Thinking is on by default: send reasoning_effort: "none" or thinking: {"type": "disabled"} to turn it off. While it thinks, DeepSeek ignores sampling settings such as temperature.
Endpoints: /v1/chat/completions, /v1/messages, /v1/responses (stateless)
Model: DeepSeek-V4.1-Flash-1017 as of 2026-11-03 (deepseek-ai/DeepSeek-V4.1-Flash-1017). DeepSeek can move this model to a newer version without notice.

Price

Input: $0.30
Cached input: $0.006
Output: $1.20

USD per 1M tokens, billed from prepaid credit.

Uptime, last 30 days

Status page

100%

15 of 15 canary checks passed (one every 5 minutes).

Last canary: passed, time to first token 636 ms, total 709 ms.

Speed, last 24 h

—

Speed is measured, not guaranteed: the median output tokens per second after the first token, and the median time to first token (TTFT), over streamed requests in the last 24 h. "—" until a model has 20 of them.

Quickstart

Create a key in the dashboard, then call deepseek-v4.1-flash from any OpenAI or Anthropic client.

curl https://api.abliteratedllm.dev/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "stream": true,
    "messages": [{"role": "user", "content": "Write the opening line of a noir detective story."}]
  }'