# Use BigModel.io with Cline

> Configure Cline in VS Code with the OpenAI Compatible provider, base URL https://bigmodel.io/v1 and a BigModel.io key, then set context window and image support for GLM, Kimi or DeepSeek.

Web version: https://bigmodel.io/docs/cline · Updated 2026-10-18

Cline has a dedicated **OpenAI Compatible** provider. It calls Chat Completions, so any BigModel.io text model your key can call works with it, including models in Chat Completions-only GLM and DeepSeek groups.

| Field in Cline | Value |
|---|---|
| API Provider | OpenAI Compatible |
| Base URL | `https://bigmodel.io/v1` |
| API Key | your BigModel.io API key (`sk-...`) |
| Model ID | a model ID from the [model catalog](https://bigmodel.io/models), e.g. `glm-5.3` |
| Model Configuration | Max Output Tokens, Context Window, Image Support from the model page |

## Configure the OpenAI Compatible provider

1. Open the Cline panel in VS Code and click the settings (gear) icon.
2. Set **API Provider** to **OpenAI Compatible**.
3. Enter **Base URL** `https://bigmodel.io/v1`. Do not add `/chat/completions`.
4. Paste your key from [API Keys](https://bigmodel.io/keys) into **API Key**.
5. Enter the exact **Model ID**, for example `glm-5.3`, `kimi-k3` or `deepseek-v4-pro`.
6. Under **Model Configuration**, set **Context Window** and **Max Output Tokens** to the values on the model page. Turn on **Image Support** only if the model accepts images, and leave **Computer Use** off unless the model supports it.
7. Optionally fill **Input Price** and **Output Price** (USD per 1M tokens, from the model page) so Cline's cost estimate is close. The billed amount is the one in [Usage](https://bigmodel.io/usage).
8. Save.

Cline keeps separate settings for Plan and Act modes when you enable that option; configure both, or use the same model for both.

## Alternative: the Anthropic provider

If your key's group serves `/v1/messages` (see the check in the [Claude Code guide](https://bigmodel.io/docs/claude-code)), you can choose **Anthropic**, enable the custom base URL option and enter the root `https://bigmodel.io` (no `/v1`). For GLM, Kimi or DeepSeek the OpenAI Compatible provider is the simpler choice.

## Verify the setup

Start a new task with a short prompt such as "list the files in this folder". Cline should answer with the model you set, and the request should appear in [Usage](https://bigmodel.io/usage) with that model ID.

## Troubleshooting

**503 `api_error`: `No available accounts: no available accounts supporting model: ...`.** The Model ID does not match a model your key's group serves. It must match the catalog ID exactly (lowercase, with dots).

**404 on every request.** The Base URL must be `https://bigmodel.io/v1`, without `/chat/completions`.

**401 `INVALID_API_KEY`.** The key was pasted with spaces or was deleted. Copy it again from [API Keys](https://bigmodel.io/keys).

**"Context window exceeded" or truncated answers.** The model configuration in Cline does not match the model. Set the context window and max output from the model page, and start a new task to clear the history.

**Cline says the model does not support images.** Image Support is off in Model Configuration, or the model is text-only.

**The task stops with "API request failed" after a long run.** Check [Usage](https://bigmodel.io/usage) for the failing request. 403 `INSUFFICIENT_BALANCE` means top up in [Billing](https://bigmodel.io/purchase); 429 `API_KEY_QUOTA_EXHAUSTED` means raise the key's quota; 429 `rate_limit_error` means too many parallel requests, so wait and retry.

## Related

- [Configure Base URL in Codex, Claude Code, Cursor and Cline](https://bigmodel.io/blog/configure-base-url-codex-claude-code-cursor)
- [Roo Code](https://bigmodel.io/docs/roo-code) if you are moving from it to Cline.
- [Cursor](https://bigmodel.io/docs/cursor) for the editor's built-in agent.
- [OpenCode](https://bigmodel.io/docs/opencode) for a terminal agent with the same OpenAI-compatible setup.