DeepSeek-V3.2-Exp Non-Thinking API

DeepSeek-V3.2-Exp is an experimental variant of DeepSeek-V3.2 with extended context and non-thinking mode for fast responses.

Modalities: TextText
In / Out price: $0.2857/$0.4338per 1M
Context window: 125K tokens
Released: Oct 3, 2025

DeepSeek-V3.2-Exp Non-Thinking overview

DeepSeek-V3.2-Exp Non-Thinking specs

Model ID: deepseek/deepseek-non-thinking-v3.2-exp
Developer: DeepSeek
Context window: 128,000 tokens
Max output: 64,000 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What is DeepSeek V3.2 Exp API?

DeepSeek-V3.2-Exp is an experimental variant of DeepSeek-V3.2 with extended context and non-thinking mode for fast responses.

Where to Use DeepSeek V3.2 Exp

Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.

Use cases

Fast interactive chatbots and assistants where responsiveness is critical
Long-form document summarization and extraction without explanation overhead
Code generation/completion over large repositories where speed is key
Multi-document search and retrieval with low latency
Pipeline integrations requiring JSON outputs without intermediate reasoning noise

Capabilities

Streaming
Structured outputs
Function calling

DeepSeek-V3.2-Exp Non-Thinking API pricing

DeepSeek-V3.2-Exp Non-Thinking pricing in US dollars
Usage	Price	Unit
Input	$0.2857	1M tokens
Output	$0.4338	1M tokens
Cached input	$0.2857	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

DeepSeek-V3.2-Exp Non-Thinking vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
DeepSeek-V3.2-Exp Non-Thinking	$0.2857	$0.4338
DeepSeek Chat (V4.1 Flash)	$0.3	$1.2
DeepSeek V4.1 Flash	$0.3	$1.2
DeepSeek V4 Flash Vision Exp	$0.44	$1.32
DeepSeek V4.1 Flash 1017	$0.39	$1.56

How to use the DeepSeek-V3.2-Exp Non-Thinking API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-non-thinking-v3.2-exp",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "deepseek/deepseek-non-thinking-v3.2-exp",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-non-thinking-v3.2-exp",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

DeepSeek-V3.2-Exp Non-Thinking FAQ

What is the context window of DeepSeek-V3.2-Exp Non-Thinking?

DeepSeek-V3.2-Exp Non-Thinking has a 128,000 tokens context window and can return up to 64,000 tokens.

What inputs and outputs does DeepSeek-V3.2-Exp Non-Thinking support?

DeepSeek-V3.2-Exp Non-Thinking takes text as input and returns text.

What is the model ID for DeepSeek-V3.2-Exp Non-Thinking?

Use deepseek/deepseek-non-thinking-v3.2-exp as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

How much does DeepSeek-V3.2-Exp Non-Thinking cost?

DeepSeek-V3.2-Exp Non-Thinking costs $0.2857 input and $0.4338 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does DeepSeek-V3.2-Exp Non-Thinking support streaming?

Yes, DeepSeek-V3.2-Exp Non-Thinking can stream responses as they are generated.

Who created DeepSeek-V3.2-Exp Non-Thinking?

DeepSeek-V3.2-Exp Non-Thinking was built by DeepSeek.

What is DeepSeek-V3.2-Exp Non-Thinking best suited for?

It is designed for fast text responses using extended context and a non-thinking mode.

Start building with DeepSeek-V3.2-Exp Non-Thinking

Get API key

DeepSeek-V3.2-Exp Non-Thinking API

deepseek/deepseek-non-thinking-v3.2-exp

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-non-thinking-v3.2-exp",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "deepseek/deepseek-non-thinking-v3.2-exp",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-non-thinking-v3.2-exp",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

DeepSeek-V3.2-Exp Non-Thinking API

DeepSeek-V3.2-Exp Non-Thinking overview

DeepSeek-V3.2-Exp Non-Thinking specs

Use cases

Capabilities

DeepSeek-V3.2-Exp Non-Thinking API pricing

DeepSeek-V3.2-Exp Non-Thinking vs other models: token prices

How to use the DeepSeek-V3.2-Exp Non-Thinking API

Build with your agent

1Get your API key

2Make your first request

Related articles

DeepSeek-V3.2-Exp Non-Thinking FAQ

Start building with DeepSeek-V3.2-Exp Non-Thinking

DeepSeek-V3.2-Exp Non-Thinking API

Build with your agent

1Get your API key

2Make your first request

DeepSeek-V3.2-Exp Non-Thinking API

DeepSeek-V3.2-Exp Non-Thinking overview

DeepSeek-V3.2-Exp Non-Thinking specs

Use cases

Capabilities

DeepSeek-V3.2-Exp Non-Thinking API pricing

DeepSeek-V3.2-Exp Non-Thinking vs other models: token prices

How to use the DeepSeek-V3.2-Exp Non-Thinking API

Build with your agent

1Get your API key

2Make your first request

Models similar to DeepSeek-V3.2-Exp Non-Thinking

DeepSeek Chat (V4.1 Flash)

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash 1017

Gemini 3.5 Flash Lite

MiniMax-M2.5

MiniMax M2.7

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

DeepSeek-V3.2-Exp Non-Thinking FAQ

Start building with DeepSeek-V3.2-Exp Non-Thinking