Cloud

Databricks

Model Serving endpoints on your workspace.

Quick start

import polygate
 
response = polygate.chat(
    provider="databricks",
    base_url="...",
    model="databricks-claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Say hi in one word."}],
)
 
print(response.content)   # "Hi!"
print(response.usage)     # Usage(prompt_tokens=..., completion_tokens=...)

Names

Any of these work as provider. They all reach the same adapter, so pick whichever reads best in your code.

Configuration

Any of these may hold a comma-separated list. polygate rotates across them, parks a rate-limited one for its Retry-After, and drops one the provider rejects — so a key pool is configuration, not code.

Endpoint

There is no fixed host: the URL contains your own account, workspace or project, so base_url is required. Omit it and polygate raises MissingEndpointError naming the variable to set, rather than letting the request fail somewhere less informative.

Models

Examples that work today. Model names change; the provider's own list is the authority.

Things worth knowing

• The `model` is your serving endpoint name, not a vendor model id — which is why two workspaces on the same underlying model can call it different things.
• Databricks documents the URL three ways: the workspace root, the root plus /serving-endpoints, and the full per-endpoint invocation URL. polygate accepts all three, because all three are things people paste.

Batch

Databricks has no offline batch API. To run many requests at once, use map_chat — full price, but it works everywhere and returns in seconds. See Batching & concurrency.