New parameter: prompt_cache_key /v1/chat/completions and /v1/completions now accept an optional...
UpdateUnverifiedAdded Sep 24, 2026
New parameter: prompt_cache_key /v1/chat/completions and /v1/completions now accept an optional prompt_cache_key parameter. Requests that share the same key are routed together so they reuse the same prompt cache, increasing cache hits and reducing time to first token.
Topics: AI agents, Vector search
More Cerebras Inference releases
Every Cerebras Inference releaseAlso shipped on Apr 22, 2026
Cerebras in April 2026| Date | Company | Release | Product | Type |
|---|---|---|---|---|
| Apr 22 |  MotherDuck | - Duckling Overview UI: The Duckling Overview page in Settings provides a view of activity across every...unverified | MotherDuck | Preview |
| Apr 22 |  Figma | Make preview on the mobile appunverified | Figma | Preview |
| Apr 22 |  Okta | Deploy CLI Dry Run is now GAunverified | Auth0 | GA |
| Apr 22 |  Grafana Labs | Anomaly Alerts (Usage Spike Detection)unverified | Grafana Cloud | GA |
| Apr 22 |  Google Cloud | Dataflow job builder now supports external Iceberg REST Catalogs as a sourceunverified | Dataflow | Update |
| Apr 22 |  Anyscale | Ray-2.55.1unverified | Ray | Update |
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.