Skip to main content
Alibaba QwenJan 27, 2026

Qwen 3 Coder 480B Turbo

qwen3-coder-480b-a35b-instruct-turboPrivateOpen weights

Turbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.

$0.35/$1.50
per 1M in / out
256K
context window
64K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 16%59.6%
Blended pricecheaper than 72%$0.64
Context windowlarger than 22%256K
Max outputlarger than 37%64K

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
Streamingstream: true
Function callingtoolsStructured outputsresponse_format
Web searchenable_web_search
Prompt cachingReads at $0.04
Log probabilitieslogprobs
Optimized for codeTuned for software work

Not supportedreasoning, image input, video input, audio input and X search

Benchmarks

GPQA Diamond
59.6%117th of 139 · 28 score higher for less, including DeepSeek v4.1 Flash (1017), MiniMax M2.5 and DeepSeek V4.1 Flash 1017 Uncensored

Specs

Model ID
qwen3-coder-480b-a35b-instruct-turbo
Endpoint
POST /api/v1/chat/completions
Context window
256,000 tokens
Max output
65,536 tokens
Reasoning
None
Precision
FP8
Privacy
Private
Added
Jan 27, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Qwen 3 Coder 480B Turbo$0.35$1.5059.6%256K64K——
MiniMax M2.7$0.375$1.5088.4%198K32K——
Venice Role Play Uncensored$0.50$2.0040.2%128K4K——
MiniMax M3 Preview$0.30$1.2089.4%512K128K——
MiniMax M2.5$0.27$0.9590.4%198K32K——

Pricing

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

Input$0.35per 1M tokens
Cached input$0.0489% off input
Output$1.50per 1M tokens

Estimate a workload

$0.0014per request
$14.50for 10,000 requests

Blended price against similar models

Qwen 3 Coder 480B Turbo$0.6375

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-coder-480b-a35b-instruct-turbo",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelqwen3-coder-480b-a35b-instruct-turboRequired
messagestextContent parts the model reads
max_completion_tokensUp to 65,536
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