- Model
Qwen/Qwen3-Coder-480B-A35B-Instruct- Provider
huggingface- API
openai-completions- Base URL
https://router.huggingface.co/v1- Input
- text
- Reasoning
- No
- Context window
- 262,144
- Max tokens
- 66,536
- Cost / million input
- $2
- Cost / million output
- $2
- Cost / million cache read
- $0
- Cost / million cache write
- $0
Model config JSON
{
"providers": {
"huggingface": {
"apiKey": "YOUR_API_KEY",
"models": [
{
"id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
"name": "Qwen3-Coder-480B-A35B-Instruct",
"reasoning": false,
"input": [
"text"
],
"contextWindow": 262144,
"maxTokens": 66536,
"cost": {
"input": 2,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"compat": {
"supportsDeveloperRole": false
}
}
],
"api": "openai-completions",
"baseUrl": "https://router.huggingface.co/v1"
}
}
}