DeepSeek V3.2 Thinking
DeepSeek V3.2 Thinking is a reasoning model from DeepSeek released on Dec 1, 2025. It reads text and writes text, with a 128K token context window and up to 8K tokens per reply.
Show moreShow less
It costs $0.62 per million input tokens and $1.85 per million output tokens.
It supports tool calling.
2 providers serve it, including Vercel AI Gateway and 302.AI. The lowest input price is $0.29 per million tokens at 302.AI.
- Modalities
- In / out price
- $0.62 / $1.85 per 1M
- Context
- 128K
- Max output
- 8K
- Released
- Dec 1, 2025
- Knowledge cutoff
- Jul 2024
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
DeepSeek V3.2 Thinking pricing
USD, as listed on Oct 19, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.62 / 1M tokens | |
|---|---|---|
| Output | $1.85 / 1M tokens |
DeepSeek V3.2 Thinking providers
2 providers serve it, including Vercel AI Gateway and 302.AI. The lowest input price is $0.29 per million tokens at 302.AI. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Vercel AI Gateway | $0.62 | $1.85 | n/a | 128K | 8K |
| 302.AI | $0.29 | $0.43 | n/a | 128K | 128K |
What DeepSeek V3.2 Thinking costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call DeepSeek V3.2 Thinking through an OpenAI compatible API.
- Tools
tools - Reasoning
reasoning - Temperature
temperature
Alternatives to DeepSeek V3.2 Thinking
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 22.2
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 27 providers.
by googleJul 9, 20261.05M context$0.30/M input tokens$2.50/M output tokens27 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 31 providers.
by googleMar 20, 2025$0.30/M input tokens$2.50/M output tokens31 providers
- Index 25.2
Reads text, images and video. Tool calling, structured output, reasoning. Served by 25 providers.
by qwenJun 2, 20261M context$0.40/M input tokens$1.60/M output tokens25 providers
- Index 17.5
Reads text and images. Tool calling, structured output, reasoning. Served by 12 providers.
by metaAug 10, 2026131K context$0.35/M input tokens$1.50/M output tokens12 providers
- 200K context
Reads text. Tool calling, structured output, reasoning.
by z-aiFeb 11, 2026$0.60/M input tokens$1.90/M output tokens
- 1M context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 14 providers.
by qwenFeb 1, 2026$0.40/M input tokens$2.40/M output tokens14 providers
More from DeepSeek
- 1M context
Reads text and images. Tool calling, structured output, reasoning. Served by 16 providers.
by deepseekOct 17, 2026$0.15/M input tokens$0.60/M output tokens16 providers
- 1.05M context
Reads text and images. Tool calling, reasoning.
by deepseekOct 13, 2026$0.15/M input tokens$0.60/M output tokens
- Index 39.5
Reads text. Tool calling, structured output, reasoning. Served by 59 providers.
by deepseekSep 10, 20261.05M context$0.30/M input tokens$1.20/M output tokens59 providers
- 1M context
Reads text and images. Tool calling, structured output, reasoning. Served by 15 providers.
by deepseekAug 21, 2026$0.44/M input tokens$1.32/M output tokens15 providers
- 1M context
Reads text. Tool calling, structured output, reasoning. Served by 34 providers.
by deepseekAug 12, 2026$1.32/M input tokens$3.96/M output tokens34 providers
- 1M context
Reads text. Tool calling, structured output, reasoning. Served by 46 providers.
by deepseekJul 31, 2026$0.14/M input tokens$0.28/M output tokens46 providers
DeepSeek V3.2 Thinking questions
How much does the DeepSeek V3.2 Thinking API cost?
$0.62 per million input tokens and $1.85 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of DeepSeek V3.2 Thinking?
128,000 tokens of input, and it can write up to 8,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve DeepSeek V3.2 Thinking?
2 providers serve it, including Vercel AI Gateway and 302.AI. The lowest input price is $0.29 per million tokens at 302.AI. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does DeepSeek V3.2 Thinking support tool calling?
Yes. It accepts tool definitions, which is what an agent needs to call your APIs.
Is DeepSeek V3.2 Thinking open source?
No. DeepSeek serves it through an API only, so you cannot download the weights or host it yourself.
When was DeepSeek V3.2 Thinking released?
Dec 1, 2025, with training data up to Jul 2024.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 19, 2026. The summary is written from these facts.