Use Cline in VS Code against an OpenAI-compatible endpoint

Cline talks to any OpenAI-compatible provider. Give it the A2Agent base URL, a key and a model id, and the extension drives GLM, Kimi, DeepSeek, Qwen or MiniMax without any other change.

Setup

1
Create an API key
Sign up and create a key. Trial credit is granted on sign-up, so the first requests cost nothing.
2
Pick the OpenAI Compatible provider in Cline
In the extension settings choose the OpenAI Compatible provider, then fill in these three values. The model id must be one from the models page.
```
Base URL:  https://a2agent.me/v1
API Key:   sk-your-a2agent-key
Model ID:  glm-5.2
```

Check the endpoint before you rely on it

Cline surfaces provider errors inside the editor, which makes them harder to read. One curl tells you whether the key and model are good.

curl https://a2agent.me/v1/chat/completions \
  -H "content-type: application/json" \
  -H "authorization: Bearer sk-your-a2agent-key" \
  -d '{
    "model": "glm-5.2",
    "messages": [{"role": "user", "content": "Reply with OK"}]
  }'

What differs from the official endpoint

Model ids are case-sensitive

The gateway matches the requested model against the account mapping exactly, with no case folding. glm-5.2 works, GLM-5.2 may not. Copy ids from the models page rather than retyping them, and prefer the lowercase form the catalogue prints.

Coding models are tagged on the models page

Cline leans on long context and tool use. The catalogue tags each model, and the coding-tagged entries in the GLM, Kimi, MiniMax and Qwen families are the ones to start with. Context lengths run from 200K to 1M depending on the model.

One key, several families

Switching the model id in Cline is enough to switch upstream. The gateway resolves the group per request, so you do not keep one provider profile per vendor.

Billing is per token, against a balance

There is no monthly fee and no minimum spend, and credit does not expire. The price you see on the models page comes from the same billing tables the gateway charges against.

Models worth starting with

Any model in the catalogue works through this client. These are the ones with a full page covering pricing, context window and setup.

Questions

Which Cline provider type do I choose?

OpenAI Compatible. A2Agent serves the Chat Completions API at https://a2agent.me/v1.

Why does my model id return an error?

Most often the case is wrong. Ids are matched exactly. Copy the id from the models page.

Can I use the same key in other editors?

Yes. The same key serves the Anthropic, OpenAI and Gemini protocol faces, so Claude Code, Codex CLI and Cline can share one credential.

Do I need to top up before trying it?

No. New accounts get trial credit and no card is required.

How do I see what a session cost?

The dashboard reports usage and balance per key, and /v1/usage answers the same question over the API.

Trial credit on sign-up, billed per token, no minimum spend.

Get an API key Browse models See pricing