Models: Atlarix Core and your own keys

Atlarix Core is the managed model catalogue in the app: sign in, pick one of the included models, and start building — no vendor API key required for Core itself. Models are shown by their real names in the picker.

Every feature is on every plan: unlimited workspaces, the MCP marketplace, one-click connectors, automations. Your own API keys and local models cost nothing, ever. Atlarix Auto is free in the desktop app. What you pay for is the rest of Atlarix Core, the managed models we host and meter — top up from $10 and it is billed as you use it. Atlarix runs on three surfaces — the desktop app, the Chrome extension and Atlarix Reviewer — and they share one account and one balance, so spend is metered in one place wherever it happens. Pro includes Core for everyday work across all three.

Each Core model carries its own context window, and the app shows the live figure in the chat meter:

• Core 1 — GLM-5.3 (z-ai/glm-5.3) — 1.0M context, has effort levels
• Core 2 — GPT-6.1 Sol (openai/gpt-6.1-sol) — 1.1M context, has effort levels
• Core 3 — GPT-6 Astra (openai/gpt-6-astra) — 1.1M context, has effort levels
• Core 4 — GLM-5.3-Flash (z-ai/glm-5.3-flash) — 1.0M context, has effort levels
• Core 5 — GPT-6 Luna (openai/gpt-6-luna) — 1.1M context, has effort levels

The lineup is configured remotely and can change without an app update, so treat this as what is mapped today rather than a permanent list.

There is no tier gating. Every plan can use every Core model, chosen per request from the picker. What differs is who has already paid for the inference: Pro includes Atlarix Core for everyday work, and heavier use draws on the same pay-as-you-go credit Free uses from the start.

Add provider keys under Settings → AI: 230+ providers and 7,500+ tool-capable models from the live models.dev catalogue, including OpenAI, Anthropic, Gemini, and any OpenAI-compatible endpoint.

Your keys and Atlarix Core coexist — pick the active model per chat and switch anytime without leaving the workspace. Turns on your own key show an estimated cost per reply.

Your own keys and local models are free on any plan.

Ollama and LM Studio work the same way as any other provider — select the model in the picker and it runs on your machine.

Effort is how hard the model thinks. In the app it's in the chat config dropdown next to the model picker; in the CLI it's /effort (ctrl+t jumps to the top level and back); in your editor it's in the model picker, and /effort works in the chat. It only appears for a model that has a setting.

On your own key or a Core model, you get that model's own levels, exactly as the model lists them, and the one you pick is sent unchanged. The default is what the model runs when you choose nothing. A model you switch to keeps your level only when it has it too.

On paid Atlarix Auto the levels choose the models: low uses the small, fast models, medium is the usual Auto, and max uses the strongest. Free Auto runs at one level.

Atlarix prompts you to top up or switch to another model, and keeps your conversation intact. Nothing is lost.