Use Tokun with OpenCode

OpenCode, the terminal agent, connects to Tokun through an OpenAI-compatible provider. Your OpenCode workflow stays the same, and requests use Tokun's pricing and model routing.

• A Tokun API key (starts with sk-) from the API keys page.
• A funded Tokun balance.
• OpenCode, installed.
• A model ID, such as anthropic/claude-opus-4-8.

In your opencode.json (project root or ~/.config/opencode/opencode.json), add Tokun as 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": "sk-..." },
      "models": { "anthropic/claude-opus-4-8": {} }
    }
  }
}

Run opencode and select the Tokun model.

Paste this prompt into your AI coding agent. It reads the setup guide at /llms.txt and sets up OpenCode for you. You only need to provide your API key.

Read https://tokun.sh/llms.txt and integrate Tokun into this project.

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.

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

Each key under models is a Tokun model ID in lab/model format, such as anthropic/claude-opus-4-8 or openai/gpt-5.5. Tokun never substitutes a different model: an unknown ID returns an error.

Official model pools

Official model pools appear in the model catalog and use a pool ID such as flash-pool. Choose an available pool from the live catalog; pool names and members are configured by Tokun administrators.

When the pool enables member selection, use pool-id/member-name, replacing the model's lab prefix with the pool ID. The selected member is the only model that can execute; the pool's pricing mode still applies. When selection is disabled, this form returns 400.

• Fixed token pricing uses the pool's input, output, cache and context-tier rates for every member, including a member you select yourself.
• Actual model pricing uses the serving member's price, frozen before the request. A retry to another member uses that member's frozen price.
• Fixed per-request pricing charges once after an upstream success response begins. Missing usage, a partial response or a client disconnect after that point still counts once. Failures before success and unsuccessful retries do not add charges.

Use a pool that lists the API format this client sends. Model pool settings in the live catalog control which members are shown and whether member selection is available.

• Quickstart
• Models and pricing
• Machine-readable docs (llms-full.txt)