Cline

Cline connects to any OpenAI-compatible API through its OpenAI Compatible provider. Use https://api.abliteratedllm.dev/v1 as the base URL.

Placeholders: $API_BASE is https://api.abliteratedllm.dev/v1, $API_ORIGIN is https://api.abliteratedllm.dev, and $YOUR_KEY is your API key.

Configure

Open the Cline settings panel (the gear icon) and set:

Setting	Value
API Provider	OpenAI Compatible
Base URL	`$API_BASE`
API Key	`$YOUR_KEY`
Model ID	`glm-5.3-flash-abliterated`, `deepseek-v4.1-flash` or `deepseek-v4-pro`

Then open Model Configuration and set:

Setting	Value
Max Output Tokens	Up to the model's `max_output_tokens` from GET /v1/models, 65536 for our abliterated models (trial accounts are capped at 4096).
Context Window	The model's `context_length` from GET /v1/models, for example 262144 for `glm-5.3-flash-abliterated`.
Image Support	Off. The models are text only, and images fail with 400 `unsupported_content`.
Input Price, Output Price	Per 1M tokens, from GET /v1/models. Cline uses them only to estimate cost in its UI; you're billed what the API reports.

Trial accounts allow 1 concurrent request and 4096 output tokens. See Rate limits and trial.
If Cline reports Model Not Found, check the model id. It must match one of the ids above exactly.

Verified against Cline docs on 2026-11-03: OpenAI Compatible.