Tokun

Use Tokun with OpenCode

Use Tokun as the model backend for OpenCode (the terminal agent) via an OpenAI-compatible provider — the same OpenCode workflow, billed at Tokun pricing with Tokun's model routing.

What this connects

Use Tokun as the model backend for OpenCode (the terminal agent) via an OpenAI-compatible provider — the same OpenCode workflow, billed at Tokun pricing with Tokun's model routing.

Before you start

  • A Tokun API key (starts with sk-) from the console.
  • A funded Tokun balance.
  • OpenCode installed.
  • A chosen model id, e.g. anthropic/claude-opus-4-8.

Recommended quickstart

In your opencode.json (project root or ~/.config/opencode/opencode.json), add Tokun as an OpenAI-compatible provider:

json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "tokun": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://api.tokun.sh/v1", "apiKey": "sk-..." },
      "models": { "anthropic/claude-opus-4-8": {} }
    }
  }
}

Run opencode and select the Tokun model.

Copy for AI agent

Working inside an AI coding agent? The shortest path is one line — paste this and your agent reads the full machine-readable guide at /llms.txt and does the OpenCode setup itself. You only supply your key:

text
Read https://tokun.sh/llms.txt and integrate Tokun into this project.
Want a fully-specified, deterministic block instead (exact steps, idempotent, fail-closed)? Paste the one below — it configures OpenCode specifically.
text
You are helping the user configure OpenCode to use Tokun. Edit opencode.json (project root or ~/.config/opencode/opencode.json) and add an OpenAI-compatible provider:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "tokun": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://api.tokun.sh/v1", "apiKey": "<the Tokun sk- key>" },
      "models": { "anthropic/claude-opus-4-8": {} }
    }
  }
}

Notes:
- baseURL keeps the /v1 suffix (https://api.tokun.sh/v1).
- The key is a Tokun sk- key, NOT an OpenAI key.
- Add more model ids under "models" as needed.

Manual configuration

The provider lives under provider in opencode.json using @ai-sdk/openai-compatible with baseURL: https://api.tokun.sh/v1 + your key. To roll back, remove the provider block.

Model naming

Each key under models is a Tokun lab/model id, e.g. anthropic/claude-opus-4-8 or openai/gpt-5.5. Tokun does not silently substitute models — an unknown id returns an error.

Verify & troubleshoot

Use @ai-sdk/openai-compatible and keep the /v1 suffix on baseURL (https://api.tokun.sh/v1). The key is your Tokun sk- key.
SymptomLikely causeFix
401 / auth errorWrong or missing keySet options.apiKey to your Tokun sk- key.
402 / payment requiredEmpty Tokun balanceTop up in the console.
Model not foundModel id not under "models"Add the lab/model id, e.g. anthropic/claude-opus-4-8.