Skip to main content

Use Only Your Own API Keys (BYOK)

With Only your own API keys (BYOK), every AI request of your organization reaches the provider on your organization's API keys, never on MINEO's: conversations, Work, voice and MINEO's AI helpers. Use it when your data processing agreements or your billing require that no request goes through MINEO's provider accounts.

Everything is configured by organization administrators in Organization → AI → Models. Your pricing plan must allow BYOK models.

Before you turn it on​

Prepare the models your organization will use, in this order. The checklist under the switch (AI → General) ticks each step as you complete it.

  1. Add a credential in Models → Credentials: the provider (OpenAI, Anthropic or Google), a name and your API key; an OpenAI-compatible proxy such as LiteLLM also needs its Base URL. Use Test connection before saving.
  2. Create your chat models in Models → Models with +: pick the credential, then a base model from your plan. The name is prefilled with the base model and the credential (for example GPT-5.1 · Deoleo), so you can tell it from MINEO's model of the same name. Saving opens the model's page, where you can change its model ID and hosting region. Check it works with Test model, in the model's ⋯ menu in the list or on its page: it sends a minimal request through the model and shows the reply, how long it took and whether MINEO has a price for it (a model without a price is billed with the cost values of its catalog entry). An image model makes a real, low-quality generation.
  3. Limit models to some projects or members if departments must use different keys: open the model, and in its Projects tab turn off All projects, move its projects to the right-hand list and save. To limit it to some people instead (or as well), use its Members tab: turn off All members and pick the users and the groups. See organization models.
  4. Pick your defaults in Models → Default models, in the Organization column (and in each member region's column if it uses other models):
    • Model for MINEO's AI helpers — writes instructions, starters, form fields, assistant setups, skills, Dockerfiles and code completions.
    • Dictation model and Reading aloud model — OpenAI speech models, created in step 2 from a speech base model with an OpenAI credential.
    • Compaction model and Image generation model — optional.
  5. Review your assistants: an assistant whose allowed models are all MINEO's will have nothing to run on.

Turn it on​

  1. In AI → General, switch on Only your own API keys (BYOK). The checklist under the switch shows what is still missing.
  2. Click Save. Before anything is saved, MINEO lists what changes:
    • the default models that are MINEO's, which are cleared — the organization's and each region's;
    • the features that turn off, because nothing of yours serves them;
    • the assistants that switch to one of their own models, or stop answering until they have one — per project, and once for the plan's assistants, which are the same in every project.
  3. Confirm, or cancel and complete what is missing.

What changes for your users​

FeatureWith your own modelWithout one
Conversations and WorkRun on the assistant's own modelsThe composer says the assistant has no model available and can't send
MINEO's AI helpers (magic wands, code completion)Use the model for MINEO's AI helpersThe wands are disabled and their tooltip says why; code completion stops asking
Dictation and reading aloudUse your speech modelsThe buttons are disabled and their tooltip says why
Notebook assistant—Always off: it only works on MINEO's keys
Assistants are never rewritten

Taking MINEO's models away doesn't change any assistant's configuration. Each conversation uses the assistant's default model if it is allowed, otherwise the first of its allowed models that is. Turning the policy off again brings everything back as it was.

Next steps​