DeepSeek V3.2 Exp

DeepSeekdeepseek/deepseek-v3.2-expProviders: 2
Inputi$0.27per 1M tokens
Outputi$0.41per 1M tokens
Contexti160K163,840 tokens
ReleasedSep 29, 2025Max output: 144K

Where it stands

Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.

100110120130140150160170$0.01$0.03$0.1$0.3$1$3$10$30$100Overall indexPrice per million tokens, log scale (3 parts input to 1 part output)↖ Cheaper and smarterDeepSeek V3.2 Exp
Scores: Epoch AI (CC BY 4.0). Prices: OpenRouter. View as a table

About this model

DeepSeek V3.2 Exp is an AI model from DeepSeek, made available through the API on September 29, 2025. It can read up to 163,840 tokens in one request, roughly 307 pages of text, and write up to 147,456 tokens in a single answer.

Through the API it costs $0.27 per million input tokens and $0.41 per million output tokens. Its pricing puts it among the more affordable models we track, which makes it a good fit for high-volume tasks.

It supports extended reasoning: it can "think" step by step before answering, which helps on maths, code and complex questions. It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (deepseek-ai/DeepSeek-V3.2-Exp), so it can also be downloaded and run on your own hardware.

Quality scores

Rankings →
145.0Overall index · #74 of 136

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 2. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
AtlasCloudCheapestfp8
$0.13$0.20160K99.6%
SiliconFlowfp8
$0.27$0.41160K99.4%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call DeepSeek V3.2 Exp through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek/deepseek-v3.2-exp", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $0.258
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.014
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $130

Cost calculator →

Similar-priced alternatives

ModelInputiOutputiContexti
$0.27$1.08200KCompare with ⇄
Qwen3.5-122B-A10BAlibaba Qwen
$0.26$2.08256KCompare with ⇄
Gemini 3.1 Flash LiteGoogle DeepMind
$0.25$1.501MCompare with ⇄
$0.25$0.80256KCompare with ⇄
Seed-2.0-LiteByteDance Seed
$0.25$2256KCompare with ⇄
Mercury 2Inception
$0.25$0.75128KCompare with ⇄

News about DeepSeek

See all →

Frequently asked questions

How much does DeepSeek V3.2 Exp cost?
DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.258.
What is the context window of DeepSeek V3.2 Exp?
DeepSeek V3.2 Exp can read up to 163,840 tokens in one request, about 307 pages of text. It can write up to 147,456 tokens in a single answer.
Is DeepSeek V3.2 Exp open source?
Yes. Its weights are published (deepseek-ai/DeepSeek-V3.2-Exp), so you can download it and run it on your own hardware, or use it through one of 2 API providers.
Who makes DeepSeek V3.2 Exp?
DeepSeek V3.2 Exp is made by DeepSeek. It became available through the API on September 29, 2025.
How good is DeepSeek V3.2 Exp?
DeepSeek V3.2 Exp has an overall index of 145.0 in Epoch AI’s independent tests, ranking #74 of 136 models we track.
Can DeepSeek V3.2 Exp read images?
No. DeepSeek V3.2 Exp only accepts text as input.
What are the alternatives to DeepSeek V3.2 Exp?
Models with a similar price from other companies include MiniMax M2.5, Qwen3.5-122B-A10B and Gemini 3.1 Flash Lite. You can compare them side by side on this page.