gpt-5.6-luna
Optimized for cost-sensitive, high-volume workloads
One route serves GPT-5.6 Luna. Every figure below is measured on that route over the selected window; a cell with too little traffic behind it says so rather than showing a number.
| Provider | Context | Max output | Input/1M | Output/1M | p50 TTFT | p90 TTFT | p50 latency | p90 latency | p50 output rate | Eligible calls | Errors | Uptime | Evidence |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
OpenAI only route gpt-5.6-luna Vision | 1.05M | 128,000 | $0.20 ≤272K input | $1.20 ≤272K input | -- | -- | -- | -- | -- | -- | 0% | warming · 30m |
TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.
Routing follows the priority order above and fails over on error. To require a single provider, add a provider object to the request body on the OpenAI- and Anthropic-compatible endpoints. Setting allow_fallbacks to false makes the constraint strict: the request fails rather than routing elsewhere.
{"provider": {"only": ["openai"]}}