Stop metering your coding agent.
opencode talks to any OpenAI-compatible endpoint. Add ProxyLLM as a custom provider and OpenAI-model calls run through Codex Hosted, billed to the ChatGPT plan you already have, with your API key as fallback.
$129/month SaaS. Bring your own model keys. No inference markup.
Three steps to connect.
Create a key, export it
Generate a ProxyLLM key in the dashboard and export it as PROXYLLM_API_KEY. Or store it inside opencode with the /connect command and skip the env var.
Add the provider block
Drop the provider config into opencode.json in your project, or ~/.config/opencode/opencode.json for every project. opencode speaks to any OpenAI-compatible endpoint via @ai-sdk/openai-compatible.
Code on your subscription
Pick a ProxyLLM model in opencode and OpenAI calls run through Codex Hosted. Past a plan limit, a second Codex account or your own API key carries the session until it resets.
One block in opencode.json.
Expose ProxyLLM models in the /models picker behind one OpenAI-compatible endpoint.
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"proxyllm": {
"npm": "@ai-sdk/openai-compatible",
"name": "ProxyLLM",
"options": {
"baseURL": "https://api.proxyllm.ai/v1",
"apiKey": "{env:PROXYLLM_API_KEY}"
},
"models": {
"gpt-4o-mini": { "name": "GPT-4o mini" },
"anthropic/claude-3.5-sonnet": { "name": "Claude 3.5 Sonnet" }
}
}
}
}Run your AI workloads on your ChatGPT subscription.
ProxyLLM runs OpenAI's Codex for you, signed in with your own ChatGPT account. Your apps call one OpenAI-compatible endpoint and the work bills to your flat plan instead of per-token API pricing.
Long sessions, flat bill.
Agent loops burn tokens fast. Through Codex Hosted an opencode session bills to your ChatGPT subscription instead of per-token API pricing, inside a scoped budget cap.