DeepSeek V3.2

deepseek-v3.2 by DeepSeek Released December 2, 2025
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to 35% off
Input from
$0.26 / 1M
Output from
$0.38 / 1M
Cached input from
$0.0741 / 1M
Context window
164K
Endpoints
8
from 5 providers
Regions
Global, Europe, United States

About DeepSeek V3.2

DeepSeek-V3.2 is the official release of a model that incorporates DeepSeek Sparse Attention—a sparse attention mechanism. It’s also the first model launched by DeepSeek that integrates reasoning into tool usage, supporting both reasoning-enabled and non-reasoning tool calls.

DeepSeek V3.2 is a chat model by DeepSeek, available on Eden AI through 8 endpoints from 5 providers, from $0.26 per million input tokens and $0.38 per million output tokens, with a context window of up to 164K tokens.

Providers and prices

8 endpoints from 5 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
DeepInfra (United States)Official−%deepinfra/deepseek-ai/DeepSeek-V3.2
United States
164K
$0.26$0.26
$0.38
$0.13
ReasoningToolsJSONCacheVisionWeb
TensorX (Europe)Official−%tensorx/deepseek/deepseek-v3.2
Europe
164K
$0.3$0.3
$0.5
$0.075
ReasoningToolsJSONCacheVisionWeb
QwenOfficial−35%qwen/deepseek-v3.2
Global
131K
$0.57$0.3705
$1.1115
$0.0741
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/deepseek-ai/deepseek-v3.2-maas
Global
164K
$0.56$0.56
$1.68
$
ReasoningToolsJSONCacheVisionWeb
Google Cloud (Europe)Official−%vertex/deepseek-ai/deepseek-v3.2-maas@eu
Europe
164K
$0.616$0.616
$1.848
$
ReasoningToolsJSONCacheVisionWeb
Google Cloud (United States)Official−%vertex/deepseek-ai/deepseek-v3.2-maas@us
United States
164K
$0.616$0.616
$1.848
$
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (Europe)Official−%amazon/deepseek.v3.2
Europe
164K
$0.74$0.74
$2.22
$
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (United States)Official−%amazon/deepseek.v3.2@us
United States
164K
$0.74$0.74
$2.22
$
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.48 s
Amazon Web Services (Europe)
Lowest latency
2.72 s
Amazon Web Services (Europe)
Highest throughput
64.55 tok/s
Amazon Web Services (United States)
Best availability
100%
TensorX (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
DeepInfra (United States)
1.56 s
9.28 s
34.99 s
19.34 tok/s
100%
32.23%
0%
3.46%
TensorX (Europe)
2.01 s
7.25 s
64.62 s
9.55 tok/s
100%
33.67%
0%
0%
Qwen
0.91 s
7.95 s
14.17 s
49.3 tok/s
99.99%
35.42%
0%
0%
Google Cloud
s
20.56 s
29.85 s
22.42 tok/s
100%
6.65%
0%
0%
Google Cloud (Europe)
s
s
s
tok/s
%
%
%
%
Google Cloud (United States)
s
s
s
tok/s
%
%
%
%
Amazon Web Services (Europe)
0.48 s
2.72 s
11.88 s
64.49 tok/s
100%
0.12%
0%
0%
Amazon Web Services (United States)
0.48 s
2.74 s
12.13 s
64.55 tok/s
100%
0.12%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call DeepSeek V3.2 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about DeepSeek V3.2

On Eden AI, prices for this model start at $0.26 per million input tokens and $0.38 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 164K tokens, depending on the endpoint.

8 endpoints from 5 providers, available in: Global, Europe, United States. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.48 s (Amazon Web Services (Europe)) and the highest throughput was 64.55 tokens per second (Amazon Web Services (United States)).