We’ve launched one new models, doubao-seedance-2-5 — try them now.

DeepSeek

V3.2 Thinking API

Built for reasoning, coding, and agentic tool use, with stronger long-context, thinking-mode, and complex-task execution than DeepSeek V3.1. Compared with Chinese peers such as Qwen, GLM, and Kimi, it is especially competitive for math, programming, and logical reasoning tasks.

  • Long context
  • Tool use
  • Reasoning
  • Structured output
Use in ConsoleDeepSeek-V3.2-Thinking

USD

Pricing

default
Standard Rate
Input$0.31/1M tokensCompletion Price$0.469991/1M tokensCache Read$0.030008/1M tokens

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

API

Code examples

curl --location --request POST 'https://api.tokenhot.ai/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "DeepSeek-V3.2-Thinking",
    "messages": [
        {
            "role": "user",
            "content": "What model are you"
        }
    ]
}'

DeepSeek

Related models

DeepSeekDeepSeekV3.2

Built for reasoning, coding, and agentic tool use, with stronger long-context, thinking-mode, and complex-task execution than DeepSeek V3.1. Compared with Chinese peers such as Qwen, GLM, and Kimi, it is especially competitive for math, programming, and logical reasoning tasks.

$0.21/1M tokensDeepSeekDeepSeekV4 PRO

Built for reasoning, coding, and agentic tool use, with stronger long-context, thinking-mode, and complex-task execution than DeepSeek V3.2. Compared with Chinese peers such as Qwen, GLM, and Kimi, it is especially competitive for math, programming, and logical reasoning tasks.

$1.71/1M tokensDeepSeekDeepSeekV4 Flash

Built for reasoning, coding, and agentic tool use, with stronger long-context, thinking-mode, and complex-task execution than DeepSeek V3.2. Compared with Chinese peers such as Qwen, GLM, and Kimi, it is especially competitive for math, programming, and logical reasoning tasks.

$0.142/1M tokensMinimaxMiniMaxM2.5

A cost-efficient model for real productivity agents, strongest in coding, tool use, search, and office-style deliverables rather than casual chat alone. It fits agents that plan and execute cross-file changes, research retrieval, and document/spreadsheet/presentation workflows; versus more expensive flagships, the main tradeoff is lower cost for near-frontier execution efficiency.

$0.302/1M tokens

FAQ

Frequently asked questions

What is V3.2 Thinking best suited for?

V3.2 Thinking is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is V3.2 Thinking priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call V3.2 Thinking?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Get started

Build with V3.2 Thinking

Use in Console