TOPIC
Batch, cost, caching and limits
- APIAdd Batch API requests from a JSONL fileadd-requests-to-a-batch-via-jsonl
- APIAvoid breaking Grok API prompt cacheavoid-breaking-prompt-cache
- APICancel a Batch API jobcancel-a-batch-api-job
- APIGet Batch API cost breakdownget-batch-cost-breakdown
- APIGet Batch API resultsget-batch-api-results
- APIHandle Grok API rate limitshandle-grok-api-rate-limits
- APIInspect Batch API request metadatainspect-batch-request-metadata
- APIList batches via the xAI APIlist-batches-via-xai-api
- APIMaximize Grok API prompt cache hitsmaximize-prompt-cache-hits
- APIPrepare for the X Search tool pricing changeprepare-for-x-search-pricing-change
- APIRead API request cost in usd ticksread-api-request-cost-in-usd-ticks
- APIRead cost_in_usd_ticks on Grok API responsesread-cost-in-usd-ticks
- APIRun a Batch API jobrun-a-batch-api-job
- APIRun a deferred Grok chat completionrun-deferred-chat-completion
- APISend async concurrent Grok API requestssend-async-concurrent-requests
- APITrack request cost in usd tickstrack-request-cost-in-usd-ticks
- APIUnderstand long-context pricing on the Grok APIunderstand-long-context-pricing
- APIUse priority processinguse-priority-processing