DocsAPI reference

OpenAPI specification

Model IDs and options in examples are illustrative. Select an available model from GET /v1/models and check its capabilities and current prices.

Performance measurements

Request history shows total duration. Provider tables show time to first token for text and total duration for Transcribe. These measure different parts of a request.

ParameterTypeDefaultDescription
latency_msinteger | null—Total duration, including queueing, uploads, processing and retries. Kept for API compatibility.
ttft_msinteger | null—Time until the model starts returning reasoning, an answer or tool-call output.
generation_msinteger | null—First generated output to last generated output.

GET /v1/usage and request details return these fields. GET /v1/usage/summary adds averages, p50, p95 and sample counts for each measurement. Historical requests, cache hits and failed requests have no provider timing. JSON-only BYOK completions have no TTFT measurement.

Generation speed

Generation speed uses the sum of output tokens minus one per measured request, divided by summed first-to-last output time. It excludes incomplete responses and requests with fewer than two output tokens or zero generation time. Check generation_samples before interpreting tps; zero samples means no measurement.

Model performance

GET /api/models/catalog/{lab}/{slug}/performance returns the figures on each model page, per provider. It needs no key, is refreshed every 5 minutes and cached for a minute.

ParameterTypeDefaultDescription
windowstring7d1d, 7d or 30d. Points are hourly, every 6 hours or daily.
percentileinteger5050, 75, 90, 95 or 99. For throughput it is the speed that share of requests reached or beat.
effortstringallall, or one reasoning level. efforts in the response lists the levels with traffic.

Each provider has a summary and a series with throughput (tokens per second), ttft and latency (milliseconds), toolCallErrorRate, structuredErrorRate and cacheHitRate. Rates run from 0 to 1, and a value is null when there were no requests to measure. A tool-call error is a call whose arguments are not a JSON object; a structured-output error is a JSON-mode reply that does not parse before repair.