Creating a custom endpoint
1
Open Models & Providers
Go to Settings → Agent → Models & Providers.
2
Open custom providers
Click Custom Providers in the top-right corner of the built-in providers section.
3
Add a provider
Click Add Provider.
4
Configure the provider
Unless your provider states otherwise, use OpenAI (Chat Completions) — the de facto standard for self-hosted and proxy services.
- Name — Display name
- Provider type — The API specification your endpoint implements
- Base URL — The endpoint URL
Supported API specifications
Cloud platform configuration
Azure OpenAI
Additional fields: Resource name and API version (e.g.,2024-02-01).
Amazon Bedrock
Choose an Authentication Method:
SSO profiles require an active session. If requests fail with an expired-token error, run
aws sso login --profile <name>.
Google Vertex AI
Additional fields: Project ID, Location (e.g.,us-central1), and Google credentials (service account JSON).
Local models via Ollama
A typical setup for running models locally:- Run Ollama on your machine:
ollama serve - Pull a model:
ollama pull llama3 - Create a custom endpoint in stagewise:
- Provider type:
openai-chat-completions - Base URL:
http://localhost:11434/v1
- Provider type:
- Add a custom model with the model ID Ollama expects (e.g.,
llama3) - Select the model from the model picker
Model ID mapping
Some endpoints use different model identifiers. Use Model ID Mapping to remap:claude-v2 from this endpoint.”