Sign in
← AI PulseAug 20, 2026

Wire · news · Single-source brief

xAI Introduces Priority Processing for API Requests

xAI has launched Priority Processing, allowing developers to request higher scheduling priority for API calls to achieve lower latency, particularly during peak demand.

By Illumora Editorial

Source · Aug 20, 2026, 3:13 PM · On Illumora · Aug 20, 2026, 3:38 PM

Media from the primary source — shown here so you can stay on Illumora.

Rewritten from one allowlisted primary — not independent enterprise reporting. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →xAI Docs — Priority Processing | SpaceXAI Docs
Save

xAI has introduced a new feature called Priority Processing for its API, designed to provide lower latency for requests. This functionality allows developers to specify a higher scheduling priority for their API calls, which can result in reduced time-to-first-token (TTFT) and faster inter-token latency (ITL).

This feature is particularly beneficial during periods of high demand on the xAI API. It does not require capacity reservations or advance provisioning.

Key Points

  • Priority Processing enables higher scheduling priority for xAI API requests.
  • This typically leads to lower time-to-first-token (TTFT) and faster inter-token latency (ITL).
  • The feature is activated by adding service_tier: "priority" to the request body.
  • It is supported on text inference endpoints, specifically Chat Completions and Responses.
  • The API response includes a service_tier field to confirm if priority was granted.
  • Priority requests are billed at a premium per-token rate.
  • Cache discounts still apply to cached input tokens before the premium rate is applied.

Context

According to xAI, when priority capacity is available, requests with the service_tier: "priority" setting are scheduled ahead of standard traffic. The response from the API will always include a service_tier field, allowing developers to verify that priority processing was applied.

Why It Matters

This new capability offers developers a method to optimize the responsiveness of their applications, especially those requiring minimal latency for text inference. The ability to prioritize requests without pre-booking capacity provides flexibility for managing performance during fluctuating demand.

What To Do

  • Add service_tier: "priority" to the request body for Chat Completions and Responses endpoints.
  • Check the service_tier field in the API response to confirm priority processing was applied.
  • Review the xAI Pricing page for current per-model rates and the exact priority premium.
  • Note that cache discounts still apply to cached input tokens before the premium rate.