GeniusRelay
EN中文Sign up

DeepSeek: DeepSeek V4.1 Flash Heretic

deepseek-v4.1-flash-heretic

CompareAPIGet an API key

Heretic checkpoint of DeepSeek V4.1 Flash 1017, served by Sable at original mixed precision (FP8 dense/Engram and MXFP4 experts). Supports text and image input, tools, structured output, and optional reasoning. Separate from the DeAlign uncensored checkpoint.

Modalities

Text + Image → Text

Input / output price

$0.257 / $1.03 per 1M

Context

512K · max output 128K

Capabilities

UncensoredReasoningVisionTool callingLong contextOpen weightsCoding

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.257
Output$1.03
Cached input$0.0172

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00160
Per day
$0.7979
Per month (30 days)
$23.94

DeepSeek V4.1 Flash Heretic: input $0.2574/M · output $1.0296/M · cached input $0.0172/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4.1-flash-heretic", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to deepseek-v4.1-flash-heretic.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash-heretic",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is DeepSeek V4.1 Flash Heretic billed?
Input is $0.257 and output is $1.03 per million tokens; cached input is $0.0172. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
512K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.