Table of Contents [expand]
Last updated December 17, 2025
Qwen3-Coder-480B is a large language model (LLM) from Qwen that supports conversational chat, tool-calling, and agentic coding. It offers an open-weight solution that runs on AWS compute in the US region.
- Model ID:
qwen3-coder-480b - Region:
us
When to Use This Model
Qwen3-Coder-480B is an agentic code model. It’s optimized for foundational coding tasks, including agentic coding, browser-use, and tool-use.
Usage
Qwen3-Coder-480B follows our Claude /v1/chat/completions API schema.
To provision access to the model, attach qwen3-coder-480b to your app $APP_NAME:
heroku ai:models:create -a $APP_NAME qwen3-coder-480b
Using config variables, you can invoke qwen3-coder-480b in a variety of ways:
- Heroku CLI
aiplugin (heroku ai:models:call) - curl
- Python
- Ruby
- Javascript
Rate Limits
- Maximum requests per minute: 150
- Maximum tokens per minute: 800,000
Prompt Caching
Prompt caching isn’t supported for Qwen3-Coder-480B.
Example curl Request
Get started quickly with an example request:
export INFERENCE_MODEL_ID=$(heroku config:get -a $APP_NAME INFERENCE_MODEL_ID)
export INFERENCE_KEY=$(heroku config:get -a $APP_NAME INFERENCE_KEY)
export INFERENCE_URL=$(heroku config:get -a $APP_NAME INFERENCE_URL)
curl $INFERENCE_URL/v1/chat/completions \
-H "Authorization: Bearer $INFERENCE_KEY" \
-d @- <<EOF
{
"model": "$INFERENCE_MODEL_ID",
"messages": [
{ "role": "user", "content": "Hello!" },
{ "role": "assistant", "content": "Hi there! How can I assist you today?" },
{ "role": "user", "content": "What's the weather like in Portland, Oregon right now?" }
],
"temperature": 0.5,
"max_tokens": 100,
"stream": false,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Fetches the current weather for a given city.",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The name of the city to get weather for."
}
},
"required": ["city"]
}
}
}
],
"tool_choice": "auto",
"top_p": 0.9
}
EOF