DeepSeekReleased on Dec 1, 2025

DeepSeek-V3.2 (Non-thinking): API Pricing, Context Window & Benchmarks

DeepSeek-V3.2 (Non-thinking) is a language model from DeepSeek, released in December 2025, with a 131K-token context window, and pricing from $0.280/M input and $0.420/M output.

DeepSeek-V3.2 in non-thinking mode. A powerful language model with 685B parameters using DeepSeek Sparse Attention (DSA) for efficient long-context processing. Supports JSON output, tool calls, and chat prefix completion. This is the

Input
Text
Output
Text

DeepSeek-V3.2 (Non-thinking) pricing

Providers

DeepSeek-V3.2 (Non-thinking) starts at $0.280 per million input tokens and $0.420 per million output tokens via DeepSeek.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
DeepSeek logoDeepSeek
$0.280$0.420131.1K/8.2K
0.77/0.77
610/610
33.33%(6)
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

DeepSeek-V3.2 (Non-thinking) model size

DeepSeek-V3.2 (Non-thinking) has 685 billion parameters. See how it compares to other models in the same parameter range.

Parameters
685BMoE
Frontier (200B+)
685B
1B7B70B405B

DeepSeek-V3.2 (Non-thinking) context window

Input and output token limits for DeepSeek-V3.2 (Non-thinking), plus how it ranks on long-context understanding.

InputOutput
131Ktokens
8Ktokens
197 pages of text
131K
8K128K1M

DeepSeek-V3.2 (Non-thinking) API

POST/v1/chat/completions

Run a request to see the response

Use it in your code

Billed at $0.28 input / $0.42 output per 1M tokens through the LLM Stats gateway.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://gateway.llm-stats.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ]
)

print(response.choices[0].message.content)

Need an API key? Create one above in the playground, or read the API documentation.

DeepSeek-V3.2 (Non-thinking) latency

DeepSeek-V3.2 (Non-thinking) time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Provider operational metrics

Time to first token, output throughput, and failed-request rate from live API traffic

Loading chart...
Loading chart...
Loading chart...

DeepSeek-V3.2 (Non-thinking) examples

Recent arena outputs from DeepSeek-V3.2 (Non-thinking), picked from the highest-ranked matchups.

DeepSeek-V3.2 (Non-thinking) license

DeepSeek-V3.2 (Non-thinking) is released under the MIT license, which permits commercial use, has 685.0B parameters.

License
MIT
Commercial use allowed
Parameters
685.0B

MIT License - allows commercial use

DeepSeek-V3.2 (Non-thinking) resources

Official sources for DeepSeek-V3.2 (Non-thinking): api documentation, official playground, paper or system card, model weights.

FAQ

Common questions about DeepSeek-V3.2 (Non-thinking).

When was DeepSeek-V3.2 (Non-thinking) released?

DeepSeek-V3.2 (Non-thinking) was released on December 1, 2025 by DeepSeek. This is the official DeepSeek-V3.2 (Non-thinking) release date tracked on LLM Stats.

How much does DeepSeek-V3.2 (Non-thinking) cost?

DeepSeek-V3.2 (Non-thinking) costs $0.28 per million input tokens and $0.42 per million output tokens through the LLM Stats API, which works with any OpenAI-compatible SDK. Across tracked providers, the lowest price is $0.28 per million input tokens via DeepSeek.

Is DeepSeek-V3.2 (Non-thinking) available via API?

Yes. DeepSeek-V3.2 (Non-thinking) is available through the LLM Stats API and works with any OpenAI-compatible SDK — point your client at the gateway base URL and pass the model name. It is served by 1 provider tracked on LLM Stats.

How big is DeepSeek-V3.2 (Non-thinking)?

DeepSeek-V3.2 (Non-thinking) has 685 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created DeepSeek-V3.2 (Non-thinking)?

DeepSeek-V3.2 (Non-thinking) was created by DeepSeek.

What is the license for DeepSeek-V3.2 (Non-thinking)?

DeepSeek-V3.2 (Non-thinking) is released under the MIT license. This is an open-source / open-weight license that permits self-hosting.

What is DeepSeek-V3.2 (Non-thinking) latency?

DeepSeek-V3.2 (Non-thinking) p95 time to first token is 0.77 seconds via DeepSeek over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use DeepSeek-V3.2 (Non-thinking)?

DeepSeek-V3.2 (Non-thinking) is available through 1 provider including DeepSeek.

Where is the DeepSeek-V3.2 (Non-thinking) paper or technical report?

DeepSeek-V3.2 (Non-thinking) has a paper or technical report available at https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf. Use that source for architecture, training, release and evaluation details.