GeniusRelay
Sign upConsole

DeepSeek: DeepSeek R1 Qwen Abliterated

deepseek-r1-distill-qwen-32b-abliterated

CompareAPIGet an API keyGet an API key

DeepSeek R1 Qwen Abliterated costs $1.82 per million input tokens and $1.82 per million output tokens, supports 16K context, and is available through the OpenAI-compatible API.

Uncensored version of the Deepseek R1 Qwen 32B model

Modalities

Text → Text

Input / output price

$1.82 / $1.82 per 1M

Context

16K · max output 8K

Capabilities

UncensoredReasoningOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$1.82
Output$1.82
Cached input$0.910

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00692
Per day
$3.46
Per month (30 days)
$103.74

DeepSeek R1 Qwen Abliterated: input $1.82/M · output $1.82/M · cached input $0.91/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-r1-distill-qwen-32b-abliterated", "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-r1-distill-qwen-32b-abliterated.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-r1-distill-qwen-32b-abliterated",
    "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 R1 Qwen Abliterated billed?
Input is $1.82 and output is $1.82 per million tokens; cached input is $0.910. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
16K 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.
DeepSeek R1 Qwen Abliterated API pricing · GeniusRelay