TokenLab

Coding Tools

Cline

Configure Cline to use TokenLab models

Overview

Cline can use TokenLab through its OpenAI-compatible settings.

Install

Install Cline from your editor's extension marketplace, then open the Cline panel. Cline supports VS Code, Cursor, VSCodium, Windsurf, Antigravity, and JetBrains IDEs.

Configure TokenLab

Save the current provider, model and connection settings locally before editing. These controls change the active model selection; restore your previous values when finished. Keep signed-in accounts and tool permissions unchanged. Do not overwrite another OpenAI-compatible connection without a restorable backup.

  1. Click the gear icon in the Cline panel.
  2. Set API Provider to OpenAI Compatible.
  3. Enter the following values:
FieldValue
Base URLhttps://api.tokenlab.sh/v1
API KeyYour TokenLab API key
Model IDclaude-sonnet-5-5
  1. Click Verify.

For the claude-sonnet-5-5 example, Cline's optional model configuration can use:

CapabilityValue
Context / input limit1000000
Max output tokens128000
Image supportEnabled

The model catalog changes over time. Use the live TokenLab model catalog when selecting another model instead of copying a stale list.

Verify

After Verify succeeds, send a small read-only task before allowing edits:

List the files in this workspace and explain which one is the application entry point. Do not edit anything.

Saving settings or listing models does not verify a key or a completed request. A prompt uses TokenLab balance. Check the reply and its matching request record before trying tools; auxiliary requests may also be billed.

Generate images and video in the same agent

Cline can also create images and short videos with the TokenLab MCP server. Each generation is paid from the same TokenLab balance. In the Cline panel, open MCP Servers → Configure → Configure MCP Servers, and merge this entry into cline_mcp_settings.json:

{
  "mcpServers": {
    "tokenlab": {
      "command": "npx",
      "args": ["-y", "@tokenlabai/mcp-server@0.6.48"],
      "env": {
        "TOKENLAB_MCP_TOOL_PROFILE": "core",
        "TOKENLAB_API_KEY": "<TOKENLAB_API_KEY>"
      },
      "disabled": false
    }
  }
}

Replace <TOKENLAB_API_KEY> with your key in this local settings file only. Check that tokenlab is enabled and lists its tools in MCP Servers. Then try:

Call get_model_pricing for nano-banana-2, then use create_image with nano-banana-2 at 1k to make a photo of a matte black coffee mug on a white desk.

create_video returns a task ID. The agent calls get_task_status until the video is ready. See Cline MCP configuration for other settings.

Troubleshooting

On this page