Cline setup with Thalam
Install Cline, paste your Thalam API key, and ship in under a minute. Claude, GPT, Gemini, DeepSeek, Qwen and more — through Cline's built-in OpenAI-Compatible provider in VS Code, JetBrains, Cursor, Windsurf, Zed and Neovim.
Setup in three steps
Cline configures providers through its settings panel — no JSON files, no restart needed.
Sign up
Create a THALAM account and copy your API key from the dashboard. No credit card required.
Open Cline settings
In your editor, open the Cline sidebar and click the ⚙️ gear icon at the top of the panel.
Choose "OpenAI Compatible"
Pick "OpenAI Compatible" from the API Provider dropdown, then fill in the four fields below.
API Provider
OpenAI Compatible
Pick this from the dropdown.
Base URL
https://api.thalam.ai/v1
Copy verbatim — must include /v1.
API Key
tl-live-...
Paste the key from your THALAM dashboard.
Model
anthropic/claude-sonnet-4.6
Any model id from the THALAM catalog. Examples: deepseek/deepseek-v3.2, qwen/qwen3-max, openai/gpt-5.
Browse every available model id on the (format is <provider>/<model>). You can change the model from Cline's settings at any time without restarting the editor.
Verify it works
Open a new Cline task and send any prompt. If you see a streamed reply with no errors, you're done. To confirm THALAM is the route, ask:
Common gotchas
Three issues that account for almost every "it didn't work" report.
Invalid API key
The key must start with tl-live- and have no leading or trailing whitespace. After pasting, click outside the field so Cline persists the value before you send a request.
Model not found (404)
The Model field expects the full id <provider>/<model> — for example anthropic/claude-sonnet-4.6, not claude-sonnet-4.6 alone.
Connection error
The Base URL must include the /v1 suffix and use https. Paste it as-is: https://api.thalam.ai/v1.
Why use THALAM with Cline
A coding agent calls models hundreds of times per session. Reaching every leading model from one key — and switching between them in one click — is what makes Cline practical at production scale.
Every leading model, one key
Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, Llama, Mistral, GLM — change Cline's Model field and the call routes to a different upstream. No new API keys, no provider re-auth.
Right model for each task
Use cheap open-weight models like Qwen3 or DeepSeek V3.2 for routine edits, and reserve Claude or GPT flagships for hard reasoning. Same Cline workflow, different model id.
No lock-in, pay per token
No subscription, no minimums. If you ever want to drop THALAM, swap the Base URL and API Key fields back to your provider — Cline's setup stays the same.
OpenAI-compatible end to end
Streaming, tool calling, structured outputs, vision — everything Cline relies on works through the same /v1 endpoint, no custom adapter needed.
Frequently asked questions
What developers ask before wiring Thalam into Cline.
Do I need an API key to use Cline with Thalam?
?
Yes. Cline calls models through whichever provider you select in its settings. To route Cline through Thalam, create a free Thalam account, copy your API key from the dashboard, and paste it into Cline's API Key field after picking "OpenAI Compatible". No credit card required to create the key — you only pay when you make requests.
How do I install Cline and connect it to Thalam?
?
Three steps. (1) Install the Cline extension from the VS Code Marketplace (or your editor of choice — Cline ships for JetBrains, Cursor, Windsurf, Zed and Neovim too). (2) Sign up at thalam.ai and copy your tl-live-... key. (3) Open the Cline sidebar, click the gear icon, pick "OpenAI Compatible" from the API Provider dropdown, set Base URL to https://api.thalam.ai/v1, paste your key, and choose a model id.
Is Thalam OpenAI-compatible?
?
Yes. Thalam exposes an OpenAI-compatible base URL at https://api.thalam.ai/v1, so Cline's "OpenAI Compatible" provider treats it the same way it would treat OpenAI direct — just with a different baseUrl and apiKey. Every model Thalam routes to (Claude, Gemini, DeepSeek, Qwen and more) is reachable through the same OpenAI Chat Completions interface.
Can I use Thalam with Cline on Mac and Windows?
?
Both, plus Linux. Cline runs wherever its host editor runs — VS Code, JetBrains, Cursor, Windsurf, Zed, Neovim all support macOS, Windows and Linux. The Thalam setup (Base URL + API Key + Model field) is identical on every platform.
Can I switch models without changing my code?
?
Yes. Change the Model field in Cline's settings to any other Thalam model id (e.g. switch from anthropic/claude-sonnet-4.6 to deepseek/deepseek-v3.2) and the next task routes to that model. No restart, no extra API key, no code change.
Plug in. Pick a model. Ship.
Get an API key in under a minute. No credit card required.