Skip to content
OpenKey

DeepSeek V3.2 Exp

DeepSeekReleased Sep 29, 2025

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Try in playground
Context window
164K tokens
Max output
66K tokens
Input
text
Output
text
Tokenizer
DeepSeek
Knowledge cutoff
Jul 31, 2025
Released
Sep 29, 2025
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.270$0.0081$0.278
Output$0.410$0.012$0.422

Benchmarks

Design Arena

CategoryEloWin rateRank
3Dmodels122556.4%#36
Codemodels122054.2%#40
Data vizmodels119650.6%#51
Game devmodels121053.1%#42
SVGmodels109042%#53
UI componentsmodels122253.3%#39
Websitesmodels122154.2%#44

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model deepseek/deepseek-v3.2-exp.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v3.2-exp",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="deepseek/deepseek-v3.2-exp",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "deepseek/deepseek-v3.2-exp",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does DeepSeek V3.2 Exp cost via API?
Through OpenKey, DeepSeek V3.2 Exp costs $0.278 per 1M input tokens and $0.422 per 1M output tokens. That is the provider price ($0.270 / $0.410) plus a flat 3% fee — nothing else.
What is DeepSeek V3.2 Exp's context window?
DeepSeek V3.2 Exp accepts up to 164K tokens of context and returns up to 66K tokens per request.
Is DeepSeek V3.2 Exp OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "deepseek/deepseek-v3.2-exp" using any OpenAI SDK — only the base URL and API key change.
What inputs does DeepSeek V3.2 Exp support?
DeepSeek V3.2 Exp accepts text input and produces text output. Its knowledge cutoff is Jul 31, 2025.

More from DeepSeek

All DeepSeek models →