Documentation navigation
Getting started Quickstart Installation Core concepts Product tour
Building trees Creating nodes Prompt blocks Connectors Roles and governance Skills Co-pilot Collaboration
Run and inspect Execution Runs and traces Versions and rollback
SDK Python SDK Node.js SDK
Integrate API MCP and bundles
Providers AI connections Hosted providers for testing
Deploy Self-hosting Orchetree Cloud Environment variables

Hosted providers for testing

Last verified: June 7, 2026.

Orchetree Cloud uses Bring Your Own Key. Each user must create and secure their own provider account and accept that provider’s terms.

Local Ollama and llama.cpp servers are not onboarding options for the managed service because Orchetree Cloud cannot reach a model server running on a user’s computer.

Provider offers, model names, limits, and terms change frequently. Recheck the linked provider pages before production use.

Responsible use

  • Create and use your own provider account and API key.
  • Never publish, share, resell, or bundle an API key with Orchetree.
  • Do not create additional accounts or keys to evade quotas or rate limits.
  • Use free tiers for evaluation and light development unless the provider explicitly permits the intended production use.
  • Do not send secrets, personal data, customer data, or confidential source code unless the provider’s terms and data controls are acceptable.
  • Add billing limits before enabling a paid provider.

Documenting official free tiers is not an abuse of provider resources. Encouraging quota circumvention, account farming, shared keys, or unbounded production use of an evaluation tier would be abusive and may breach provider terms.

Ollama Cloud

Ollama Cloud exposes the Ollama API on hosted infrastructure. Its Free plan is intended for light cloud usage.

  1. Create an account at ollama.com.

  2. Create an API key in your Ollama account settings.

  3. In Orchetree, open Settings > AI Connections.

  4. Add an Ollama connection:

    Base URL: https://ollama.com
API key: your Ollama API key
Model: a current cloud model ID

  5. Test the connection before assigning it to a node.

Official references:

The Free plan currently permits one concurrent cloud model and has session and weekly limits. Ollama states that cloud prompts and responses are not logged or used for training.

Use the direct hosted API in Orchetree Cloud. Signing a local Ollama installation into Ollama Cloud is relevant to the self-hosted product, not to managed Cloud.

Mistral Studio

Mistral documents a Free mode with limited API access and no credit card requirement.

  1. Create a Mistral Studio account.
  2. Open API Keys, create a key, and set an expiration date.
  3. Add a Mistral connection in Orchetree.
  4. Enter the key and a current model ID shown by Mistral.
  5. Test the connection.

Official references:

Mistral’s current commercial terms allow data from a free subscription to be used for model training when the customer has not opted out. Do not send confidential data until the account’s data settings and applicable terms have been reviewed.

Gemini Developer API

Google offers free input and output quotas for selected Gemini models.

  1. Create a key in Google AI Studio.
  2. Add a Gemini connection in Orchetree.
  3. Enter the key and a current model ID from Google’s model list.
  4. Test the connection.

Official references:

Google’s terms require Paid Services when an API client is made available to users in the European Economic Area, Switzerland, or the United Kingdom. Google may use unpaid-service prompts and responses to improve its products and may have human reviewers process that data. Do not submit sensitive, confidential, or personal information to unpaid services.

Groq

Groq offers a Free plan with model-specific request and token limits.

  1. Create an account and API key in the Groq Console.

  2. Add an OpenAI-Compatible connection:

    Base URL: https://api.groq.com/openai/v1
API key: your Groq API key
Model: a current model ID from the Groq console

  3. Test the connection.

Official references:

Treat HTTP 429 responses as a signal to back off. Do not rotate accounts, projects, or keys to bypass organization limits.

OpenRouter

OpenRouter exposes free model variants through an OpenAI-compatible API.

  1. Create an account and API key at OpenRouter.

  2. Add an OpenAI-Compatible connection:

    Base URL: https://openrouter.ai/api/v1
API key: your OpenRouter API key
Model: openrouter/free

  3. Test the connection.

Official references:

OpenRouter currently describes free models as low-volume evaluation options. Accounts without at least 10 purchased credits are normally limited to 50 free model requests per day. The downstream model provider’s own terms and data practices also apply.

OpenAI and Anthropic

Do not treat these as guaranteed free API providers.

  • OpenAI publishes usage-based API pricing. ChatGPT subscriptions do not include API usage.
  • Anthropic API Console usage is prepaid or paid separately from a Claude subscription. See Anthropic API billing.

Promotional credits may occasionally exist, but Orchetree documentation does not promise them.

This page is operational information, not legal advice.