This changelog documents all changes to the Caesar API. We follow date-based versioning, where each version represents a stable snapshot of the API.
Caesar uses Stripe-style date-based versioning. Each version is a dated snapshot that remains stable indefinitely. You can pin your integration to a specific version and upgrade on your own schedule.
Set your API version using the API-Version header or pin it to your API key in the dashboard.
The compute_units parameter has been renamed to reasoning_loops to better reflect what the parameter controls. This is a breaking change for request payloads.
Five new parameters give you finer control over research behavior:
You can now associate research requests with file collections using the collection_ids parameter. The research pipeline will search across all files within the specified collections.
Combine collection_ids with files to include both collection-based and individual file sources in a single request.
Two new fields provide better visibility into job execution:
The score field has been removed from result items. Source relevance is now determined internally and reflected in result ordering.
compute_units with reasoning_loops in all requestsreasoning_loops_consumed instead of compute_units_consumedscore field in resultsThe first public version of the Caesar Research API.
POST /research for creating research jobs/compat/completions and /compat/chat/completionsEach completed research job returns:
answer: The synthesized research responseresults: Array of source citations with URLs and excerptscompute_units_consumed: Actual units used