Priority Processing 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 . June 10
Open original sourceAPI changeVerified
Priority Processing
Priority Processing 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 . June 10
Evidence chain
xAI developer release notesOfficial · official
External discussion
No reviewed external discussion has been linked yet. This does not change the evidence confidence.