Integrations
Cline
Cline in VS Code with ITS INCOM AI: the OpenAI Compatible provider, the model to pick and the context window to set.
Last updated: 2026-11-03
Settings
Open Cline's settings with the gear icon and fill in:
| Field | Value |
|---|---|
| API Provider | OpenAI Compatible |
| Base URL | https://api.ai.itsincom.org/v1 |
| API Key | your key, sk-its-… |
| Model ID | qwen3.8-27b |
Then, under Model Configuration:
| Setting | qwen3.8-27b |
|---|---|
| Context Window | 131072 |
| Max Output Tokens | 32768 |
| Image Support | off |
| Computer Use | off |
For another model, write its id and the context window from
Which model:
devstral-small-2-24b takes 131072.
The input and output prices are optional: Cline uses them to show an estimate. What each request cost is in the dashboard.
Which model
qwen3.8-27b. Cline sends its own instructions and tool descriptions with
every request, and each file it reads stays in the conversation. The window of
131,072 tokens leaves room for both.
devstral-small-2-24b, with 131,072 tokens, is made for coding agents that
work across many files.
qwen3-coder-30b has 262,144 tokens and answers faster, without reasoning
first.
Do not use flint-40b with Cline: it can call tools Cline does not have.
The other models with tools are in
Which model.
Limits
- 32,768 output tokens per answer, and on a model that reasons the reasoning counts in the same 32,768. An answer that writes a long file in one go can be cut: ask Cline to write it in parts.
- No reasoning to show. Cline has nothing to display in its thinking panel: the API does not return a model's reasoning.
- Images only on a model that reads them, such as
gemma-4-26b: switch Image Support on for that model alone.