Cline

Checked against Cline's docs on 2026-10-11

Cline connects as an OpenAI-compatible provider: choose it in Cline's settings and fill in the base URL, your key and the model.

Base URL: https://api.creeksidecompute.ai/v1
API: OpenAI Chat Completions
Model id: qwen/qwen3.8-27b, or qwen/qwen3.6-35b-a3b for speed, or meta/muse-glimmer-30b, which always reasons first
Context window: 131072 tokens, up to 65536 of them output
Key: Make one at creeksidecompute.ai/account

Set it up

Make a key. Sign in at creeksidecompute.ai/account with your email and make a key. Each request is paid from prepaid credit: top up by card from $10, or redeem a promotional code.
Open Cline's settings with the gear icon, and set API Provider to OpenAI Compatible.
Fill in the fields. The last three are under Model Configuration:
Cline settings
```
API Provider         OpenAI Compatible
Base URL             https://api.creeksidecompute.ai/v1
API Key              <your key>
Model ID             qwen/qwen3.8-27b
Context Window Size  131072
Max Output Tokens    32768
Image Support        off
```
Qwen3.8 27B is listed for text only, so turn image support off. For Muse Glimmer 30B, enter meta/muse-glimmer-30b as the Model ID instead and turn image support on: it reads images. A smaller output limit leaves more of the window for the conversation; each model can write up to 65,536 tokens.
Start a task. Cline's terminal version takes the same settings: cline auth -p openai-compatible -b https://api.creeksidecompute.ai/v1 -k <your key> -m qwen/qwen3.8-27b.

Thinking

Thinking is off unless Cline asks for it. The surest switch is the model id: qwen/qwen3.8-27b:thinking is the same model with thinking on for every request, so enter it as the Model ID to turn thinking on.

Recent versions of Cline also offer a Reasoning Effort setting for this provider: None keeps thinking off, and Low, Medium and High turn it on. In the terminal version, --thinking none keeps it off and --thinking medium turns it on. Older versions do not show the thinking text, though it is still billed as output.

Muse Glimmer 30B always reasons before it answers, so Reasoning Effort sets how long, not whether: with no setting, or at None or Low, it reasons briefly, and Medium and High make it reason longer. The Model ID meta/muse-glimmer-30b:thinking gives High.

What does not work

Images and screenshots, on the Qwen models. They are listed for text only, so the browser tool, which works from screenshots, cannot see the page. Muse Glimmer 30B reads images.
Cache settings. None are needed: caching is automatic, and a repeated prefix is billed at the cached price.
Cost display. Cline shows a cost only if you enter prices. Ours are in GET /v1/models.

Troubleshooting

401 invalid API key: The key is wrong, or Cline did not get it. Check the API Key field in Cline's settings for a missing character or a space. To test the key alone, curl -s https://api.creeksidecompute.ai/v1/models -H "Authorization: Bearer <your key>" returns the model list when the key is good.
404 model … is not served: The model id is wrong. Use qwen/qwen3.8-27b exactly, in lower case, with the qwen/ prefix. GET /v1/models lists every id we serve. Check the Model ID field for spaces.
400 maximum context length is 131072 tokens: The conversation is longer than the model's window. Set Context Window Size to 131072 so Cline condenses the conversation in time, then start a new task.
402 or 429: A 402 means your prepaid credit does not cover the request: add credit at creeksidecompute.ai/account. A 429 means the key's rate, or the number of requests your account may run at once, is used up; agents that work in parallel reach that sooner. Wait and retry. The API reference lists the limits.

Other tools

Sources, read on 2026-10-11: OpenAI Compatible provider, CLI reference.