DeepSeek V3.2 API

Model details

Context window

131K tokens

Max output

33K tokens

Input

Text

Output

Text

Capabilities

Reasoning, Tool calling, Streaming

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• DeepSeek V3.2 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call DeepSeek V3.2

DeepSeek V3.2 answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v3.2",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v3.2",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v3.2",
  "input": "Hello"
}'

Use DeepSeek V3.2 in your tools

Every coding agent below has a setup guide. Set the model to deepseek-v3.2.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from DeepSeek

Alternatives to DeepSeek V3.2

• Llama 4 Scout 17B InstructLlama 4 Scout 17B Instruct for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Meta
• Qwen3 VL 30B A3B InstructQwen3 VL 30B A3B Instruct for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Alibaba
• GPT OSS 120BGPT OSS 120B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.OpenAI

Questions about this model

How much does the DeepSeek V3.2 API cost?

DeepSeek V3.2 costs $0.28 per 1M input tokens and $0.42 per 1M output tokens on Inferray, and cached input is $0.028 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for DeepSeek V3.2?

No. You add credit and pay DeepSeek V3.2's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is DeepSeek V3.2 included in Token Plans?

No. DeepSeek V3.2 is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use DeepSeek V3.2 in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to deepseek-v3.2. The same key works in Codex, opencode, Cline, and other agents.

Does DeepSeek V3.2 support tool calling and vision?

DeepSeek V3.2 supports tool calling, reasoning and streaming on Inferray. It does not take image input.

Is it the real DeepSeek V3.2?

Yes. A request for deepseek-v3.2 is answered by DeepSeek V3.2 from DeepSeek, billed at its published list price. Inferray never substitutes a different or smaller model.