# DeepSeek v3.2:thinking API

DeepSeek's DeepSeek v3.2:thinking, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send deepseek-v3.2:thinking as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: deepseek-v3.2:thinking
- Maker: DeepSeek
- Context window: 163K tokens
- Input price: $0.208 per million tokens
- Output price: $0.309 per million tokens
- Providers: 1 independent provider
- Regions: us

## Providers

- [Architect](https://liquidinference.ai/providers/805445a7-0e40-4c1b-9baf-7b3b01e30e42.md): us, $0.208 input and $0.309 output per million tokens, $0.022 cache read per million tokens, 163K tokens of context

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2:thinking",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is DeepSeek v3.2:thinking?

DeepSeek v3.2:thinking is a model from DeepSeek.

### How much does DeepSeek v3.2:thinking cost?

Offers now ask $0.208 per million input tokens and $0.309 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of DeepSeek v3.2:thinking?

The largest offer takes 163,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can DeepSeek v3.2:thinking do?

Its providers list Documents, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.

### What inputs and outputs does DeepSeek v3.2:thinking support?

Text · Files → Text.

### Which providers serve DeepSeek v3.2:thinking?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call DeepSeek v3.2:thinking?

Send "deepseek-v3.2:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was DeepSeek v3.2:thinking listed?

The exchange first listed it on 10/10/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/deepseek-v3.2%3Athinking)
- [DeepSeek V4 Flash 0731](https://liquidinference.ai/models/deepseek-v4-flash-0731.md)
- [DeepSeek V4 Flash](https://liquidinference.ai/models/deepseek-v4-flash.md)
- [DeepSeek V4.1 Flash](https://liquidinference.ai/models/deepseek-v4.1-flash.md)
- [DeepSeek V4.1 Flash:thinking](https://liquidinference.ai/models/deepseek-v4.1-flash%3Athinking.md)
- [DeepSeek V4.1 Flash 1017:thinking](https://liquidinference.ai/models/deepseek-v4.1-flash-1017%3Athinking.md)
- [DeepSeek V4.1 Flash 1017](https://liquidinference.ai/models/deepseek-v4.1-flash-1017.md)
- [Set up a client](https://liquidinference.ai/connect/deepseek-v3.2%3Athinking)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)