DeepSeek V3.2 Thinking
DeepSeek V3.2 Thinking is a reasoning model from DeepSeek released on Jan 1, 2025. It reads text and files and writes text, with a 163K token context window and up to 66K tokens per reply.
Show moreShow less
It costs $0.28 per million input tokens and $0.42 per million output tokens. Cached input bills at $0.14, 50% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
24 providers serve it, including Friendli, Azure and Amazon Bedrock. The lowest input price is $0.18 per million tokens at CrofAI.
- Modalities
- In / out price
- $0.28 / $0.42 per 1M
- Context
- 163K
- Max output
- 66K
- Released
- Jan 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 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.28 / 1M tokens | |
|---|---|---|
| Output | $0.42 / 1M tokens | |
| Cached input (read) | $0.14 / 1M tokens | 50% off input |
DeepSeek V3.2 Thinking providers
24 providers serve it, including Friendli, Azure and Amazon Bedrock. The lowest input price is $0.18 per million tokens at CrofAI. 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 |
|---|---|---|---|---|---|
| Friendli | $0.50 | $1.50 | $0.25 | 164K | 64K |
| Azure | $0.58 | $1.68 | – | 128K | 128K |
| Amazon Bedrock | $0.62 | $1.85 | – | 164K | 82K |
| Vercel AI Gateway | $0.62 | $1.85 | – | 128K | 8K |
| SambaNova | $3 | $4.50 | – | 33K | 7K |
| CrofAI | $0.18 | $0.35 | $0.04 | 164K | 164K |
| TokenGo | $0.2174 | $0.326 | $0.06 | 128K | 64K |
| Kilo Gateway | $0.259 | $0.80 | $0.14 | 164K | 147K |
| DevPass (LLM Gateway) | $0.26 | $0.38 | $0.13 | 164K | 16K |
| LLM Gateway | $0.26 | $0.38 | $0.13 | 160K | 66K |
| Helicone | $0.27 | $0.41 | – | 164K | 66K |
| Merge Gateway | $0.28 | $0.40 | $0.13 | 128K | 33K |
Showing 12 of 24 providers: the lab first, then the major clouds, then the cheapest resellers.
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 - Structured outputs
structured_outputs - 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 41.8
Reads text, images, files and video. Tool calling, structured output, reasoning. Served by 65 providers.
by z-aiAug 21, 20261M context$0.15/M input tokens$0.50/M output tokens65 providers
- Index 43.4
Reads text, images and files. Tool calling, structured output, reasoning. Served by 26 providers.
by anthropicOct 7, 20261M context$0.10/M input tokens$0.50/M output tokens26 providers
- Index 38.1
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 20261.05M context$0.10/M input tokens$0.50/M output tokens27 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 9 providers.
by x-aiJun 27, 2025$0.20/M input tokens$0.50/M output tokens9 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 23 providers.
by googleJun 17, 2025$0.10/M input tokens$0.40/M output tokens23 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$0.10/M input tokens$0.50/M output tokens2 providers
More from DeepSeek
- 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 and images. Tool calling, structured output, reasoning. Served by 56 providers.
by deepseekSep 10, 20261M context$0.15/M input tokens$0.60/M output tokens56 providers
- 1.05M context
Reads text and images. Tool calling, structured output, reasoning. Served by 14 providers.
by deepseekAug 21, 2026$0.44/M input tokens$1.32/M output tokens14 providers
- 1M context
Reads text. Tool calling, structured output, reasoning.
by deepseekAug 2, 2026$0.05/M input tokens$0.16/M output tokens
- 1.05M context
Reads text. Tool calling, structured output, reasoning. Served by 48 providers.
by deepseekJul 31, 2026$0.14/M input tokens$0.28/M output tokens48 providers
- 1.05M context
Reads text. Tool calling, structured output, reasoning.
by deepseekMay 3, 2026$0.48/M input tokens$1.98/M output tokens
DeepSeek V3.2 Thinking questions
How much does the DeepSeek V3.2 Thinking API cost?
$0.28 per million input tokens and $0.42 per million output tokens, with cached input at $0.14. 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?
163,000 tokens of input, and it can write up to 65,536 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve DeepSeek V3.2 Thinking?
24 providers serve it, including Friendli, Azure and Amazon Bedrock. The lowest input price is $0.18 per million tokens at CrofAI. 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 and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is DeepSeek V3.2 Thinking open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was DeepSeek V3.2 Thinking released?
Jan 1, 2025, with training data up to Jul 2024.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on DeepSeek V3.2 Thinking?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting