How to add Unquant to OpenCode
OpenCode takes any OpenAI-compatible endpoint as a custom provider. Add Unquant to your config and pick the model from OpenCode's model list.
1 Set your key
export UNQUANT_API_KEY=your-unquant-key2 Add the provider
In
opencode.jsonin your project, or~/.config/opencode/opencode.jsonfor every project:{ "$schema": "https://opencode.ai/config.json", "provider": { "unquant": { "npm": "@ai-sdk/openai-compatible", "name": "Unquant", "options": { "baseURL": "https://api.unquant.io/v1", "apiKey": "{env:UNQUANT_API_KEY}" }, "models": { "glm-5.3-flash": { "name": "GLM-5.3-Flash" }, "qwen-3.8-flash-next": { "name": "Qwen 3.8 Flash Next" } } } } }3 Choose the model
Restart OpenCode, run
/modelsand pick Unquant · GLM-5.3-Flash.
401
Unauthorized
Check UNQUANT_API_KEY is set where OpenCode runs.
403
Not included in your subscription
Pick the model on your plan.
429
Concurrent stream limit reached
Another request is still running on your account.
Keep reading
- How to use Claude Code with an uncensored, unlimited modelRun Claude Code on GLM-5.3-Flash or Qwen 3.8 Flash Next through Unquant's Anthropic-compatible endpoint: two environment variables, no proxy, unlimited tokens and 262K context.
- How to use the Pi coding agent with UnquantAdd Unquant to the Pi coding agent in ~/.pi/agent/models.json as an OpenAI-completions provider and run it on GLM-5.3-Flash or Qwen 3.8 Flash Next.
- Uncensored AI for coding and agentsWhy developers use an uncensored model for coding and agents: no refusals on security work, reverse engineering or edgy content pipelines, plus 262K context and unlimited tokens for long agent loops.