DeepSeek V3.2 API

Use the version-explicit V3.2 route for short text conversations and concise drafting within the input and output limits below. Treat V3.2-Exp and Speciale as distinct variants, and check the current protocol contract before enabling advanced options.

deepseek/deepseek-v3.2 · DeepSeek · Text

Availability and pricing

Published contract · ready

$0.24672 per 1 million input tokens; $0.37008 per 1 million output tokens

Prices shown use the public default price group. Your account price and the request quote determine the amount reserved and charged.

Published verification: 2026-10-05T20:34:54.146Z

Pricing revision: rev_0ea5914a-62e6-46d3-9f87-7ab942dbd929

Supported inputs and limits

chat

max Input Tokens: 2048
max Output Tokens: 512
default Output Tokens: 256
tools: Not enabled
multimodal Input: Not enabled
reasoning: Not enabled
cache: Not enabled
conversation: Enabled
structured Output: Not enabled
compact: Not enabled
streaming: Enabled

{
  "kind": "chat",
  "modes": [
    "chat"
  ],
  "qualities": [
    "standard"
  ],
  "units": [
    1
  ],
  "aspects": [],
  "resolutions": [],
  "maxReferences": 0,
  "maxInputTokens": 2048,
  "maxOutputTokens": 512,
  "defaultOutputTokens": 256,
  "protocols": [
    "chat"
  ]
}

Limitations

Draft only until live verification and actual cost reconciliation pass. Tools, vision, explicit reasoning, structured output and compaction are disabled pending dedicated live evidence.

API request example

Use your own API key. This is a request body; asynchronous tasks also require checking their status and output.

POST /v1/chat/completions
{
  "model": "deepseek/deepseek-v3.2",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 256
}

Open API examples

Can I replace the ID with deepseek-chat?

Use the OneAster model ID shown above. Dynamic aliases on the original provider’s service are not this page’s version-specific request identifier.

Try this model

Open Playground Compare models API documentation