Skip to main content
DeepSeekDec 4, 2025

DeepSeek V3.2

deepseek-v3.2PrivateOpen weights

DeepSeek-V3.2 is an efficient large language model with DeepSeek Sparse Attention (DSA) for long contexts. It features strong reasoning and tool-use skills, achieving top results on the 2025 IMO and IOI.

$0.33/$0.48
per 1M in / out
160K
context window
32K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 58%86.9%
Blended pricecheaper than 81%$0.37
Context windowlarger than 13%160K
Max outputlarger than 21%32K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InText
OutText

Not supportedimage input, video input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
86.9%58th of 139 · GPT-6 Luna and DeepSeek V4 Flash 0423 score higher for less

Specs

Model ID
deepseek-v3.2
Endpoint
POST /api/v1/chat/completions
Context window
160,000 tokens
Max output
32,768 tokens
Reasoning
none · low · medium · high · default low
Precision
Not disclosed
Privacy
Private
Added
Dec 4, 2025

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
DeepSeek V3.2$0.33$0.4886.9%160K32K——
Qwen 3.5 35B A3B$0.15$1.0083.8%256K16K——
Venice Uncensored 1.2$0.20$0.9042.1%128K8K——
Gemma 4 26B A4B Uncensored E2EE$0.19$0.8866.2%64K4K——
Qwen3 VL 30B A3B E2EE$0.25$0.9041.4%128K4K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$0.33per 1M tokens
Cached input$0.1652% off input
Output$0.48per 1M tokens

Estimate a workload

$0.0009per request
$9.00for 10,000 requests

Blended price against similar models

DeepSeek V3.2$0.3675

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3.2",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modeldeepseek-v3.2Required
messagestextContent parts the model reads
max_completion_tokensUp to 32,768Counts reasoning tokens
reasoning_effortnone | low | medium | highDefault low
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations