Skip to main content
Alibaba QwenFeb 25, 2026

Qwen 3.5 35B A3B

qwen3-5-35b-a3bPrivateOpen weights

Qwen 3.5 35B A3B is a highly efficient MoE model with 35B total parameters and only 3B active parameters. It surpasses the larger Qwen3-235B-A22B while being 6.7x smaller, excelling at reasoning, coding, and general knowledge tasks.

$0.15/$1.00
per 1M in / out
256K
context window
16K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 44%83.8%
Blended pricecheaper than 82%$0.36
Context windowlarger than 22%256K
Max outputlarger than 8%16K

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.

InTextImageVideo
OutText
Streamingstream: true
Function callingtoolsStructured outputsresponse_formatReasoningreasoning_effort none · low · medium · highVisionUp to 10 images
Video inputVideo in messages
Web searchenable_web_search
Prompt cachingReads at $0.05
Log probabilitieslogprobs
Optimized for codeTuned for software work

Not supportedaudio input and X search

Benchmarks

GPQA Diamond
83.8%76th of 139 · 7 score higher for less, including GPT-6 Luna, DeepSeek V4 Flash 0423 and Google Gemma 4 31B Instruct

Specs

Model ID
qwen3-5-35b-a3b
Endpoint
POST /api/v1/chat/completions
Context window
256,000 tokens
Max output
16,384 tokens
Reasoning
none · low · medium · high · default low
Precision
Not disclosed
Privacy
Private
Added
Feb 25, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
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——
DeepSeek V3.2$0.33$0.4886.9%160K32K——
MiniMax M2.5$0.27$0.9590.4%198K32K——

Other versions

  1. Qwen 3.5 35B A3BFeb 2026
  2. Qwen 3.6 35B A3BJul 2026

Pricing

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

Input$0.15per 1M tokens
Cached input$0.0567% off input
Output$1.00per 1M tokens

Estimate a workload

$0.0008per request
$8.00for 10,000 requests

Blended price against similar models

Qwen 3.5 35B A3B$0.3625

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": "qwen3-5-35b-a3b",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelqwen3-5-35b-a3bRequired
messagestext · image_url · video_urlContent parts the model reads
max_completion_tokensUp to 16,384Counts 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
logprobstrue | falseWith top_logprobs