Provider modes
Credentials are stored independently, and more than one can be saved at once. A saved credential starts serving the calls only it can serve as soon as it is saved. Prefer this credential decides which key runs where two of them could serve the same call, such as an Anthropic key and an OpenRouter key. The top of the settings page states which credential runs what, and who pays for it.
Default models
On the Ankra default, every organisation is served the same three tiers. The chat model picker selects between them, and Auto routes each question to the right one - short questions to Quick, everyday work to the default, and architecture, security, or image questions to Expert.
Because GLM 5.3 does not accept images, Auto sends any question with an attachment to Expert.
These are defaults, not limits. Under AI → Settings → Models you can edit any tier, point it at a different model, add your own, or reset the catalog back to the Ankra defaults. With your own Anthropic key, every tier is served by Claude instead.
Models per function
AI work that runs outside chat has its own model setting per function under AI → Settings → Models → Models per function. A function with nothing selected follows its default tier, so it moves with your catalog: point a tier at a different model and every function on that tier follows it.
On the Ankra default the Think tier is GLM 5.3, so an organisation that has changed nothing writes stack READMEs and reviews code on GLM 5.3. On your own Anthropic key, Think is served by Claude.
Pick any model in your catalog for a function, or clear the selection to return it to its default tier. Only organisation admins can change a function’s model. From the terminal,
ankra ai lanes list shows what each function runs on, and ankra ai lanes set <lane> <model> changes it - it also accepts an exact OpenRouter model id.
Change the provider
ankra ai models edits the model catalog and ankra ai lanes the models per function. The sections below describe the same steps in the portal.
Configure Anthropic
1
Save the key
Expand Custom Anthropic key and paste an API key (it starts with
sk-ant-). Ankra validates it with a one-token health check before saving.2
Prefer it where keys overlap
If you also hold an OpenRouter key, press Prefer this credential on the Anthropic row to decide which of the two runs the calls both could serve. The button is disabled until a valid key is saved.
sk-ant-...XXXX). Removing the key sends AI features back to the Ankra default key.
Configure OpenRouter
With your organisation’s own OpenRouter API key active, Ankra serves the same default models and automatic failover chain through your OpenRouter account - including background and autonomous AI sessions - and your usage never draws on the free monthly allowance. The key is validated live against OpenRouter at save time and stored only in the secret store. Follow the step-by-step guide: Bring Your Own OpenRouter API Key.Configure an OpenAI-compatible endpoint
1
Save the configuration
Expand Self-hosted / OpenAI-compatible and provide:
- Base URL - the endpoint’s OpenAI
/v1root,http(s)://(e.g.https://my-litellm.internal/v1) - Model - the model identifier your endpoint serves
- API key - the endpoint’s key
GET {'{base_url}'}/models on save to verify the endpoint responds. An incorrect model id only surfaces at the first AI call.2
Point models at it
Under Chat models, add the endpoint’s models or point a tier at them. The endpoint serves only the chat models listed under it.
The endpoint serves the chat models you list under it, plus Stack summaries. The built-in Expert and Think tiers stay on their own models unless you point them at your endpoint under Chat models, and AI Insights, CI/CD pipeline generation and deploy analysis fall back to the Ankra default for tool-using steps. The settings page names which credential runs each model.
Usage and the free allowance
Ankra meters every AI request - chats, agent sessions, AI Insights, alert analysis, CI/CD file generation, code reviews - per organisation, priced in USD from the tokens each model used. Billing → Overview shows month-to-date AI usage and how much of the free monthly allowance remains. The allowance covers usage on Ankra’s managed model access: the default when your organisation has no provider of its own, and anything your own key cannot serve. Usage on your own OpenRouter, Anthropic or OpenAI-compatible key never draws on it.
Defaults can change; Billing → Overview always shows your organisation’s live allowance. For more headroom, contact support.
When the allowance runs out
AI features that would spend Ankra’s key pause for the rest of the calendar month (UTC). Those requests fail with the stable error codeAI_ALLOWANCE_EXHAUSTED, which you can match on in automation. The rest of the platform, and AI on your own key, keep working. To resume before the reset, bring your own OpenRouter API key or another provider.
Daily spend cap vs monthly allowance
The daily AI spend cap is a separate brake you set yourself on Billing → Overview:Permissions
Only organisation admins can view previews, save credentials, switch providers, or change a function’s model. Other members see the settings read-only.Other AI settings
AI → Settings has these sections besides Models:- Connections - Slack, Teams, source control, MCP tool servers and delivery; see AI Connections
- Workspaces - see AI Workspaces
- Autonomy - the stops, auto-remediation and Proactive AI Insights; see AI Autonomy
- Capabilities - skills and custom tools; see AI Skills and Custom Tools
- Usage & feedback - response ratings; see AI Memory and Feedback
- Memory - see AI Memory and Feedback