docs: add TokenLab OpenAI-compatible example

[hedging8563]

Summary

Adds a TokenLab configuration example to the OpenAI-API-compatible model provider README. The example shows the TokenLab OpenAI-compatible base URL, a default model, and additional chat model IDs that can be configured through the existing plugin.

This is intentionally documentation-only because TokenLab works through the existing OpenAI-compatible model provider. The note also mentions TokenLab's native endpoint families (Responses, Anthropic Messages, Gemini-compatible APIs) while making clear that this plugin uses TokenLab's /v1 OpenAI-compatible endpoint.

Change Type

• Documentation / non-plugin change
• Non-LLM plugin (tools, extensions, datasource, etc.)
• LLM plugin

Screenshots / Videos

Before	After
No TokenLab-specific OpenAI-compatible setup example.	README includes a TokenLab setup table and model examples.

LLM Plugin Checklist

Not applicable; this PR only updates README documentation for an existing plugin.

Version

• Bumped top-level version in manifest.yaml (not applicable; documentation-only change)
• dify_plugin>=0.3.0,<0.6.0 is declared in pyproject.toml and locked in uv.lock (not applicable; documentation-only change)

Testing

• git diff --check

• Local deployment — Dify version: not run; documentation-only README change

• SaaS (cloud.dify.ai): not run; documentation-only README change

[gemini-code-assist]

Code Review

This pull request adds a TokenLab configuration example to the OpenAI-compatible plugin's README. The feedback suggests adding a note to clarify that while LLM models require the /v1 suffix in the API Base URL, other model types (like text-embedding, rerank, STT, or TTS) should omit it to prevent a double /v1/v1 path, as the plugin automatically appends it.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[hedging8563]

Thanks for the review. Addressed in b3ed846 by adding a note that TokenLab LLM/chat models should use https://api.tokenlab.sh/v1, while non-LLM model types where the plugin appends the API version internally should use https://api.tokenlab.sh to avoid a duplicated /v1/v1 path.