---
title: "Cline OpenAI Compatible provider setup (GLM, DeepSeek)"
description: "Set up the Cline VS Code extension with BroadNet Inference through its OpenAI Compatible provider, with exact fields, model IDs, context sizes and common fixes."
url: https://broadrouter.com/guides/cline-openai-compatible/
lang: en
updated: 2026-11-16
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Use Cline with BroadNet Inference (OpenAI Compatible provider)

Updated 2026-11-16

In Cline settings, set API Provider to OpenAI Compatible, Base URL to https://inference.broadnet.ai/v1, API Key to your BroadNet key, and Model to a BroadNet ID such as broadnet/glm-5.3 or broadnet/deepseek-v4.1-flash. Then set the context window under Model Configuration so Cline knows how much it can send.

Cline is a coding agent that runs inside VS Code. It talks to any OpenAI-compatible API through its **OpenAI Compatible** provider, and BroadNet Inference uses the standard chat-completions shape at `https://inference.broadnet.ai/v1`. The steps below follow [Cline’s own provider docs](https://docs.cline.bot/provider-config/openai-compatible). If you prefer a terminal agent, see [the Aider guide](https://broadrouter.com/guides/aider-unlimited-deepseek/).

## Setup

1.  **Get a key.** Create a pay-as-you-go key in the BroadNet console, or buy an [unlimited plan](https://broadrouter.com/guides/unlimited-llm-api-sessions/) and use its plan key.
    
2.  **Open Cline settings.** Click the gear icon in the Cline panel.
    
3.  **Choose the provider.** In the **API Provider** dropdown, select **OpenAI Compatible**.
    
4.  **Fill in the connection fields.**
    
    | Field | Value |
    | --- | --- |
    | Base URL | `https://inference.broadnet.ai/v1` |
    | API Key | your BroadNet key |
    | Model | `broadnet/glm-5.3` (or another ID from the table below) |
    
5.  **Set Model Configuration.** Expand **Model Configuration** and enter the context window for the model you picked. Set **Max Output Tokens** high enough to leave room for reasoning; a few thousand tokens is a safe start. Turn on image support only for models that accept images. You can also enter input and output prices from the [pricing page](https://broadrouter.com/pricing/) so Cline’s cost display is close to your bill.
    
6.  **Test it.** Start a small task, such as “explain this file”. If it answers, the connection works.
    

Type the model ID exactly, including the `broadnet/` prefix.

## Which model to pick

| Model | ID | Context | Good for |
| --- | --- | --- | --- |
| GLM 5.3 | `broadnet/glm-5.3` | 1,048,576 | Agent work that depends on tool calls |
| DeepSeek V4.1 Flash | `broadnet/deepseek-v4.1-flash` | 1,048,576 | Long sessions on an unlimited plan; text and images |
| Qwen3.8 27B | `broadnet/qwen3.8-27b` | 262,144 | Tools plus images; Arabic text |
| BroadNet Gemma 4 VL 26B | `broadnet/gemma-4-26b-a4b` | 32,768 | Trying the setup on the free credit |

BroadNet’s docs list tools and structured output for GLM 5.3 and Qwen3.8 27B. They don’t list tool calling for DeepSeek V4.1 Flash, so run a short real task on it before you commit to a month. A Meteor hour costs $1 and a Full Moon month $60; both are on the [plans page](https://inference.broadnet.ai/plans?utm_source=broadrouter&utm_medium=referral&utm_campaign=guides-cline-openai-compatible&utm_content=body). See the [DeepSeek V4.1 Flash model page](https://broadrouter.com/models/deepseek-v4.1-flash/) for details.

## Troubleshooting

-   **401 Unauthorized.** The key is missing, wrong or expired, or a pay-as-you-go account has run out of allowance. Paste the key again and check the balance. Cline’s docs say to confirm the key belongs to the provider at the Base URL.
-   **Model not found or the first request fails.** Check the ID. It must match BroadNet’s model ID exactly. The paid models need a top-up; of the chat models, only `broadnet/gemma-4-26b-a4b` works on the free $5 credit.
-   **Empty answer or a reply that stops early.** Reasoning counts toward the output limit. Raise **Max Output Tokens**. [Why answers come back empty](https://broadrouter.com/guides/reasoning-tokens-empty-response/).
-   **429 Too Many Requests.** A pay-as-you-go key allows 30 requests a minute and 4 in flight. Cline sends one request after another, so this usually means another app shares the key. See [errors and retries](https://broadrouter.com/guides/errors-and-retries/).
-   **Slow replies with several Cline windows.** One plan session runs one request at a time. Two Cline tasks at once on one session queue behind each other. Buy one session per parallel task, or read [running parallel coding agents on a flat rate](https://broadrouter.com/blog/run-parallel-coding-agents-flat-rate/).
-   **Connection errors.** Check that the Base URL ends in `/v1` and that your network allows outbound HTTPS. If your key has an [IP allow-list](https://broadrouter.com/guides/api-keys-ip-allow-lists/), add your machine’s address.

## Terms in this guide

[Token](https://broadrouter.com/glossary/token/)

A token is the unit of text a language model reads and writes: a word, part of a word, a punctuation mark or a byte sequence produced by the model's tokenizer. LLM APIs count, limit and usually bill usage in tokens.

[Pay-as-you-go](https://broadrouter.com/glossary/pay-as-you-go/)

Pay-as-you-go is a pricing model in which you pay only for what you use, metered per unit such as tokens, requests or audio minutes, with no subscription or minimum commitment. Most LLM APIs bill this way, from a prepaid balance or a periodic invoice.

[Base URL](https://broadrouter.com/glossary/base-url/)

A base URL is the fixed root address of an API, such as https://api.example.com/v1, that a client puts in front of every endpoint path, such as /chat/completions. In OpenAI-compatible SDKs, changing the base URL, together with the API key and model ID, points the same code at a different provider.

[Tool calling](https://broadrouter.com/glossary/tool-calling/)

Tool calling, also called function calling, is an LLM API feature in which the model returns a structured request to run a function the developer has defined, with JSON arguments. The application runs the function and sends the result back; the model never runs code itself.

[AI coding agent](https://broadrouter.com/glossary/coding-agent/)

An AI coding agent is a software tool in which a language model works on a codebase in a loop: it reads files, edits them, runs commands such as tests, reads the output and decides the next step until the task is done or a limit is reached.

[Input and output tokens](https://broadrouter.com/glossary/input-and-output-tokens/)

Input tokens are the tokens a language model reads in a request, including the system prompt, conversation history, tool definitions and images. Output tokens are the tokens it generates in reply, including any reasoning. LLM APIs usually price them separately, and output usually costs more.

[API key](https://broadrouter.com/glossary/api-key/)

An API key is a secret string that identifies and authorizes a client calling an API. LLM APIs usually expect it in an Authorization: Bearer header, and anyone who holds the key can make requests that are billed to the account that owns it.

[Concurrency](https://broadrouter.com/glossary/concurrency/)

Concurrency is the number of requests a client has in flight at the same time. LLM APIs often cap it per key or plan, separately from requests per minute, because each open request holds GPU capacity until its response has finished.

## Questions

### Why does Cline return an empty response?

The model spent its output budget on reasoning before writing the answer. DeepSeek V4.1 Flash, GLM 5.3 and Qwen3.8 27B reason first, and reasoning counts toward max\_tokens. Raise Max Output Tokens in Model Configuration.

### Can I run Cline on the unlimited plan?

Yes. The unlimited plans cover DeepSeek V4.1 Flash, model ID broadnet/deepseek-v4.1-flash. Use your plan key as the API Key. One Cline task uses one plan session.

### Why doesn't the model list fill in by itself?

Type the model ID into the Model field. BroadNet's docs describe GET /v1/models as public catalog metadata for monitors, so don't rely on it to populate the picker.

### Which BroadNet model works on the free starting credit?

Of the chat models, only BroadNet Gemma 4 VL 26B, model ID broadnet/gemma-4-26b-a4b; the credit also covers the two Transcribe models. The other chat models need a top-up. Its 32,768-token context is small for large repositories.

## Related guides

-   [Use Roo Code with BroadNet Inference (OpenAI Compatible)](https://broadrouter.com/guides/roo-code-openai-compatible/)
-   [How the unlimited LLM API plans work for agents](https://broadrouter.com/guides/unlimited-llm-api-sessions/)
-   [Why a reasoning model returns an empty answer](https://broadrouter.com/guides/reasoning-tokens-empty-response/)
-   [BroadNet Inference error codes and when to retry](https://broadrouter.com/guides/errors-and-retries/)
-   [All tools that work with BroadNet Inference](https://broadrouter.com/integrations/): SDKs, coding agents, chat UIs and automation tools, with exact settings for each

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=guides-cline-openai-compatible&utm_content=page-cta) ·

**Sources**

-   [Cline docs, OpenAI Compatible provider (checked 2026-11-14)](https://docs.cline.bot/provider-config/openai-compatible)
-   [BroadNet Inference API reference](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=guides-cline-openai-compatible&utm_content=sources)
-   [BroadNet Inference unlimited plans](https://inference.broadnet.ai/plans?utm_source=broadrouter&utm_medium=referral&utm_campaign=guides-cline-openai-compatible&utm_content=sources)
