GeniusRelay
Sign upConsole

DeepSeek: DeepSeek V3.2

deepseek-v3.2

CompareAPIGet an API keyGet an API key

DeepSeek V3.2 costs $0.338 per million input tokens and $0.494 per million output tokens, supports 163K context, and is available through the OpenAI-compatible API.

DeepSeek V3.2 (non-thinking mode) — official successor to V3.2-Exp. Reasoning-first model built for agents with GPT-5 level performance. Balanced inference vs. output length for everyday use. First DeepSeek model with thinking-in-tool-use capability. FP8.

Modalities

Text → Text

Input / output price

$0.338 / $0.494 per 1M

Context

163K · max output 66K

Capabilities

Tool callingOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.338
Output$0.494
Cached input$0.169

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00141
Per day
$0.7046
Per month (30 days)
$21.14

DeepSeek V3.2: input $0.338/M · output $0.494/M · cached input $0.169/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-v3.2", "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-v3.2.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2",
    "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 V3.2 billed?
Input is $0.338 and output is $0.494 per million tokens; cached input is $0.169. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
163K 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 V3.2 API pricing · GeniusRelay