How to connect OpenCode to the Tokenator API

What you end up with

Once configured, OpenCode stops talking to its default provider and sends every request to Tokenator. Billing comes out of your key's token limit, and the list of available models is defined by the key rather than by the tool.

Requirements and supported operating systems

• Windows 10/11, macOS 12+, or a modern 64-bit Linux.
• Outbound HTTPS access to the Tokenator domain.
• A Tokenator API key that looks like sk-your-tokenator-key.

OpenCode runs in a terminal; its config is a plain JSON file you can edit in any editor.

Installing OpenCode

npm install -g opencode-ai

Check the install with opencode --version.

Setting up Tokenator

1. Register in your account and buy a token bundle.
2. The key appears in the account right after the payment is confirmed — copy it whole, including the prefix.
3. The examples below use the placeholder sk-your-tokenator-key. Never publish a real key in repositories or screenshots.

Configuration on Windows

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "tokenator": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Tokenator",
      "options": {
        "baseURL": "https://api.tokenator.top/v1",
        "apiKey": "{env:TOKENATOR_API_KEY}"
      },
      "models": {
        "gpt-5.5": { "name": "gpt-5.5" }
      }
    }
  }
}

$env:TOKENATOR_API_KEY = "sk-your-tokenator-key"
opencode

The @ai-sdk/openai-compatible package targets the /v1/chat/completions endpoint. Prefer keeping the key out of the file and injecting it from the environment with the {env:…} syntax. Every model you want in the picker is listed under models.

Configuration on macOS and Linux

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "tokenator": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Tokenator",
      "options": {
        "baseURL": "https://api.tokenator.top/v1",
        "apiKey": "{env:TOKENATOR_API_KEY}"
      },
      "models": {
        "gpt-5.5": { "name": "gpt-5.5" }
      }
    }
  }
}

export TOKENATOR_API_KEY="sk-your-tokenator-key"
opencode

The @ai-sdk/openai-compatible package targets the /v1/chat/completions endpoint. Prefer keeping the key out of the file and injecting it from the environment with the {env:…} syntax. Every model you want in the picker is listed under models.

Your first request

Before starting the tool it helps to confirm that the key and the model both work. A single curl request answers both questions.

curl https://api.tokenator.top/v1/chat/completions \
  -H "Authorization: Bearer sk-your-tokenator-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{"role": "user", "content": "ping"}]
  }'

cd /path/to/project
opencode

A successful response means the key is valid, the model is allowed for it and the upstream is reachable. Usage appears in your account right after the request.

Switching models

Every model that should be selectable is listed in the config's models block. After editing the file, the agent's model picker shows the new list.

Examples of model IDs available right now:

• claude-haiku-4-5
• claude-opus-4-6
• claude-opus-4-7
• claude-sonnet-4-6
• gpt-5.5
• deepseek-v4-flash

Current IDs and specs live in the AI model catalog, which also shows which models are available right now. The model comparison helps choose between close options.

Configuring reasoning

If the tool can send a reasoning_effort field, Tokenator forwards it upstream unchanged. On top of that the key itself has a reasoning switch in your account, which works independently of the tool.

Common errors and how to fix them

FAQ

Read next