Back
AI summary
Written by AI from the official notes. Check them for exact details.Grok now allows users to request higher scheduling priority for text inference requests.
- Set
service_tier: "priority"for faster processing. - Response includes actual applied
service_tierfield. - Priority rates are billed only when used.
Why it matters: Users needing faster response times for text inference should consider this feature.
Full release notes
You can now request higher scheduling priority per request by setting service_tier: "priority" on text inference endpoints (Chat Completions and Responses). The response's service_tier field reports the tier actually applied, and priority rates are billed only when priority is used. For more details, see the Priority Processing docs.