What Cline needs
Cline ships an OpenAI Compatible provider type that takes three values: base URL, API key, and model id.
- The base URL is the root that serves
/chat/completions. Most providers document it with the/v1suffix already included. - The model id is the provider’s exact id and not a display name; Cline passes it through verbatim.
- The model has to handle tool calls well enough to emit valid diffs. This is the real filter: small free models often return malformed edits, which Cline surfaces as repeated failed apply attempts rather than as an API error.
- Values are entered in the Cline settings panel by hand. This project does not read or write VS Code extension storage.
The file this produces
Running npx free-llm-api setup cline writes SETUP.md. It is a review guide rather than a config file, because the values are typed into a settings panel and this project does not write to another tool’s credential storage. Here it is filled in for GroqCloud:
# Cline setup
This project does not modify VS Code or Cline extension storage.
1. Open Cline settings and choose **OpenAI Compatible** as the API Provider.
2. Set **Base URL** to `https://api.groq.com/openai/v1`.
3. Paste the key held in `GROQ_API_KEY` into Cline's API Key field manually.
4. Set **Model ID** to `llama-3.3-70b-versatile`, save, and send a small test message.
Nothing in that file is a key. The value is read from GROQ_API_KEY at run time, which is the one habit that keeps a credential out of a repository by construction.
Which free tiers fit Cline
22 providers here serve the OpenAI protocol and take no credit card, which makes them the ones worth trying first with Cline. The full list, including the ones that do ask for a card, is in the catalog.
| Provider | Base URL | Published limits |
|---|---|---|
| Google Gemini API | https://generativelanguage.googleapis.com/v1beta/openai/ |
Set by project tier |
| GroqCloud | https://api.groq.com/openai/v1 |
30 requests per minute, 1000 requests per day |
| SambaNova Cloud | https://api.sambanova.ai/v1 |
20 requests per minute, 20 requests per day |
| Cohere | https://api.cohere.ai/compatibility/v1 |
20 requests per minute |
| Cloudflare Workers AI | https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1 |
Published in compute units |
| Hugging Face Inference Providers | https://router.huggingface.co/v1 |
Published as a credit balance |
| SiliconFlow | https://api.siliconflow.com/v1 |
1000 requests per minute |
| Fireworks AI | https://api.fireworks.ai/inference/v1 |
10 requests per minute |
What to expect on a free tier
Plan mode and Act mode send very different prompt sizes, so a provider that plans fine can still fail on a large diff. If edits keep failing while the API returns 200, the model is the constraint and not the quota.
Before blaming the client, check the key itself: the browser checker separates a rejected credential from a rate limit from an endpoint that is simply down, and each of those has a different fix.
Sources
Provider figures shown here come from each provider’s own documentation, reviewed on 2026-07-25. The methodology covers what is recorded and what is deliberately left blank.