Use Tokun with Continue

Use Tokun as a model in Continue (the VS Code / JetBrains assistant) via its OpenAI-compatible provider — the same Continue workflow, billed at Tokun pricing with Tokun's model routing.

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

In your Continue config (~/.continue/config.yaml), add a Tokun model under models:

models:
  - name: Tokun Opus
    provider: openai
    model: anthropic/claude-opus-4-8
    apiBase: https://api.tokun.sh/v1
    apiKey: sk-...

Reload Continue and pick the Tokun model.

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 Continue setup itself. You only supply your key:

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

You are helping the user configure Continue to use Tokun. Edit ~/.continue/config.yaml and add a model:

models:
  - name: Tokun Opus
    provider: openai
    model: anthropic/claude-opus-4-8
    apiBase: https://api.tokun.sh/v1
    apiKey: <the Tokun sk- key>

Notes:
- provider MUST be "openai" (the OpenAI-compatible path); apiBase keeps the /v1 suffix.
- The key is a Tokun sk- key, NOT an OpenAI/Anthropic key.
- Reload Continue after saving.

The Tokun model lives in ~/.continue/config.yaml with provider: openai, apiBase: https://api.tokun.sh/v1, and your key. To roll back, remove the model entry.

Set model to any 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.

• API quickstart
• Models & pricing
• Machine-readable docs (llms-full.txt)