Usage & billing
Token counts, streaming usage, and remaining balance
Non-streaming responses include a usage object with the token counts the request was billed on:
{
"usage": { "prompt_tokens": 18, "completion_tokens": 21, "total_tokens": 39 }
}Streaming responses omit usage from the individual chunks. Request it explicitly with
stream_options: { "include_usage": true } and it arrives in a final chunk after the content. See
the Quick Start for how to open a stream.
Prompt and completion tokens are usually priced differently, and rates vary by model. The console shows per-model pricing alongside your usage history and remaining balance.
If you are out of quota, the API returns 429 — the same status as a rate limit. Distinguish the
two from the error code and the rate-limit headers; see rate limits & errors.
Compliance
Use orientx only for legally authorized scenarios. You remain responsible for upstream provider terms, platform rules, applicable regulations, and content safety in your own product.