Use Tokun with Cursor

Cursor connects to Tokun through its OpenAI-compatible provider settings. Your Cursor 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.
• Cursor, installed.
• A model ID, such as anthropic/claude-opus-4-8.

Cursor's model provider is set in its Settings. Open Settings → Models, then in the OpenAI section:

• Paste your Tokun key (sk-…) as the OpenAI API key.
• Turn on “Override OpenAI Base URL” and set it to https://api.tokun.sh/v1.
• Add a custom model with its Tokun ID, such as anthropic/claude-opus-4-8, and select it.

Click Verify, then chat with the selected model.

Paste this prompt into your AI coding agent. It reads the setup guide at /llms.txt and sets up Cursor 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 Cursor to use Tokun. Cursor's provider config lives in its Settings UI (not a file you can edit), so OUTPUT these steps for the user to follow rather than editing anything:

1. Open Cursor -> Settings -> Models.
2. In the OpenAI section, paste the Tokun API key (starts with sk-).
3. Enable "Override OpenAI Base URL" and set it to https://api.tokun.sh/v1.
4. Add a custom model id (e.g. anthropic/claude-opus-4-8) and select it.
5. Click verify; then chat with the model.

The key is a Tokun sk- key (NOT an OpenAI key). The base URL keeps the /v1 suffix (it is the OpenAI surface).

Every setting is under Settings → Models: the OpenAI API key field, the base URL override (https://api.tokun.sh/v1), and the custom model list. To roll back, clear the base URL override and remove the custom model.

Add Tokun model IDs in lab/model format as custom models, 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)