Skip to main content

Use a preferred AI provider in Tines

Builders can choose a preferred AI provider to power AI in Tines features and product.

Written by Hannah Roy
Updated over a week ago

When you create a tenant in Tines, you automatically gain access to AI capabilities in Tines features and Workbench. Tines offers models from both AWS Bedrock and OpenAI but you can choose to use a different LLM.

Getting started

Before bringing in your preferred AI provider into Tines, you must first understand your organization’s AI infrastructure.

Consider the following questions:

  • What AI models does your company support?

  • Are the models schema-compatible (input and output) with either Anthropic or OpenAI?

    • A model may not be schema-compatible if your company wrote its own API or hosts a model other than Claude, OpenAI, or Ollama.

  • Is your Tines tenant on the cloud or self-hosted?

Available providers

Tines lets you connect with the following AI providers, configurable via the below customizations:

Provider

Base URL

API key

Custom models

Custom headers

Anthropic

✅

✅

✅

✅

OpenAI

✅

✅

✅

✅

AWS Bedrock

✅

✅

✅

✅

Mistral

✅

✅

✅

✅

Notes:

  1. While we support the above providers directly, we’re able to support any OpenAI or Anthropic spec-compatible providers or observability tools. Refer to the AI Admin docs for the most current list. As with all features, this list will continue to evolve.

  2. Each model running locally will have to expose an OpenAI compatible API so that Tines may connect to it. Systems running on Ollama already provide this.

Add your own provider

Tenant admins can follow these steps to add your own AI API key:

  1. Navigate to Settings - AI settings

  2. Toggle on Use custom provider

  3. Choose the provider

  4. Enter the API key

Scope a provider to specific teams

By default, all teams in your tenant have access to every configured AI provider. Tenant owners can now restrict access to specific teams, giving you more granular control over which teams can use a given provider and its models.

To scope a provider to specific teams:

  1. Navigate to Settings → AI settings

  2. Select the provider you want to configure

  3. Under Access, deselect "Grant access to all teams on this tenant"

  4. Update the specific teams that should have access

The team that owns the provider's credential will always retain access. This is useful for managing costs, enforcing compliance requirements, or gradually rolling out a new model to specific teams first.

Additional resources

Related Articles
Security & privacy for AI in Tines
Preferred AI providers FAQs
What is AI in Tines?
AI usage and credits
Comparing Tines managed AI providers
Did this answer your question?