The setup originally published at this URL no longer works on Cerebras’s shared public API. Cerebras deprecated qwen-3-coder-480b on November 5, 2025. Keeping the old model in OpenCode can produce a model-not-found response.
Pick the migration path
If you want to stay on the public Cerebras service, list the models available to your account and choose a current production model. Cerebras’s public catalog changes, so copy the ID returned by the API rather than reusing an old article.
If you specifically want Qwen, use Alibaba Model Studio or Requesty. Requesty’s current managed ID is qwen3.8-max, and its live catalog can route that model across several providers.
Update OpenCode for Requesty
Store a Requesty key in REQUESTY_API_KEY, then add an OpenAI-compatible provider:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"requesty-extra": {
"npm": "@ai-sdk/openai-compatible",
"name": "Requesty",
"options": {
"baseURL": "https://router.requesty.ai/v1",
"apiKey": "{env:REQUESTY_API_KEY}"
},
"models": {
"qwen3.8-max": { "name": "Qwen3.8-Max" }
}
}
},
"model": "requesty-extra/qwen3.8-max"
}
Restart OpenCode, open the model picker, and confirm that Qwen3.8-Max appears. Test a read-only request before approving edits.
Remove the retired ID
Search user and project OpenCode configuration for:
qwen-3-coder-480b
Remove every active reference, including fallback lists. A hidden fallback can keep generating errors after the primary model has been changed.
Cerebras Qwen migration checklist
- Deprecated qwen-3-coder-480b references removed
- Current provider and model selected
- API key stored outside the repository
- OpenCode restarted
- Read-only tool request tested
For direct Alibaba use, see Qwen3.8-Max with Claude Code. For current prices, see Qwen3.8-Max pricing.