JetBrains AI setup with Thalam
Install JetBrains AI Assistant, paste your Thalam API key into the OpenAI-compatible provider settings, and ship in under a minute. Works in IntelliJ IDEA, PyCharm, WebStorm, GoLand, RubyMine, Rider and every other JetBrains IDE that ships AI Assistant.
Read this first — what BYOK covers in JetBrains AI Assistant
Per JetBrains' official docs: "Code completion does not work in a BYOK setup because [it relies] on proprietary JetBrains models."
In practice this means routing AI Chat through THALAM works today; inline code completion stays on JetBrains' own models. If you want completion through THALAM too, install the third-party ProxyAI plugin instead — it supports custom OpenAI-compatible providers for both chat and completion. Or, if you also use VS Code, see , , or .
Setup in three steps
JetBrains AI Assistant ships natively in every modern JetBrains IDE. Open settings, add THALAM as a third-party provider, click Test Connection, done.
Sign up
Create a THALAM account and copy your API key from the dashboard. No credit card required.
Open AI Assistant settings
Settings | Tools | AI Assistant | Providers & API keys. Scroll to "Third-party AI providers".
Add OpenAI-compatible provider
Pick "OpenAI-compatible", paste the URL and key from the table below, then click Test Connection.
Provider
OpenAI-compatible
Pick this from the Third-party AI providers section.
URL
https://api.thalam.ai/v1
Copy verbatim — must include /v1.
API key
tl-live-...
Paste the key from your THALAM dashboard.
Tool calling
Enabled
Toggle on so the assistant can call tools (file edits, terminal, MCP). Most THALAM models support it; flip off if you pick a model that doesn't.
Browse the available model ids on the . After Test Connection succeeds, the model dropdown in AI Chat will list whatever the endpoint advertises.
Verify it works
Open AI Chat in your IDE, pick a THALAM model from the picker, and ask:
Common gotchas
Three issues that account for almost every "it didn't work" report.
Test Connection fails
Confirm the URL ends with /v1 and the key starts with tl-live-. The Test call hits /models on the URL — both must be correct or it fails immediately.
No code completion
Expected — JetBrains' code completion uses their proprietary models, not the BYOK provider. Only AI Chat routes through THALAM. For completion, install ProxyAI as the alternative.
Tool calls silently fail
The Tool calling toggle was off, or the chosen model doesn't support tools. Re-enable the toggle and pick a tool-calling-capable model (Claude, GPT, Gemini, DeepSeek V3.2, Qwen3 series).
Why use THALAM with JetBrains AI Assistant
You keep JetBrains' inline completion and refactoring tooling; chat routes through THALAM so you can pick any model and pay per token instead of per-seat.
Models JetBrains doesn't ship
Add Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, Llama, Mistral, GLM, MiniMax — any model THALAM lists. Use them in AI Chat just like the built-ins.
Pay per token
No fixed subscription on the chat side. Heavy users pay more, light users pay less — same THALAM dashboard tracks usage across every IDE you use.
One key across IDEs
The same THALAM key works in every JetBrains IDE — IntelliJ, PyCharm, WebStorm, GoLand, Rider, RubyMine — plus VS Code, Cline, Continue, Aider, OpenCode, Zed.
Multimodal via the same key
AI Chat is text-only, but the same key reaches image, video, audio, and embedding models from your scripts or other tools.
Frequently asked questions
What developers ask before wiring Thalam into JetBrains AI Assistant.
Do I need an API key to use JetBrains AI Assistant with Thalam?
?
Yes. JetBrains AI Assistant's "OpenAI-compatible" third-party provider needs a URL + API key pair. To route AI Chat through Thalam, create a free Thalam account, copy your API key from the dashboard, and paste it into the API key field under Settings | Tools | AI Assistant | Providers & API keys. No credit card required to create the key — you only pay when you make requests.
How do I install JetBrains AI Assistant and connect it to Thalam?
?
Three steps. (1) Install the AI Assistant plugin from JetBrains Marketplace (it ships pre-installed in recent IntelliJ / PyCharm / WebStorm versions). (2) Sign up at thalam.ai and copy your tl-live-... key. (3) Open Settings | Tools | AI Assistant | Providers & API keys, scroll to Third-party AI providers, pick "OpenAI-compatible", set URL to https://api.thalam.ai/v1, paste your key, enable Tool calling, and click Test Connection.
Is Thalam OpenAI-compatible?
?
Yes. Thalam exposes an OpenAI-compatible base URL at https://api.thalam.ai/v1, which is exactly what JetBrains AI Assistant's "OpenAI-compatible" provider type expects. 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 JetBrains AI Assistant on Mac and Windows?
?
Both, plus Linux. Every JetBrains IDE — IntelliJ IDEA, PyCharm, WebStorm, GoLand, RubyMine, Rider, CLion — runs on macOS, Windows and Linux, and AI Assistant ships with each one. The Thalam setup (URL + API key + Tool calling toggle) is identical on every platform and every IDE.
Can I switch models without changing my code?
?
Yes. After Test Connection succeeds, the model dropdown in AI Chat lists whichever models the Thalam endpoint advertises. Switching between Claude, GPT, DeepSeek or any other Thalam-routed model is a config change, not a code change — your IDE keeps its existing AI Chat UX.
Plug in. Pick a model. Ship.
Get an API key in under a minute. No credit card required.