Model catalog
Use canonical lowercase model ids everywhere.
These ids are the public contract for /v1/models, IDE setup guides, and SDK examples. Human labels can change; canonical ids should not.
Luma Cloud
Provider id luma-cloud; API key env LUMA_CLOUD_API_KEY.
Default model: gpt-5.5-xhigh
Fast smoke model: gpt-5.5-medium
Limits: 400,000 context tokens, 1,024 output tokens.
Release metadata date: 2026-05-26; last updated 2026-05-26.
Provider catalog rule
External registries get the same ids, limits, capabilities, and support status that the /v1 endpoint from your dashboard exposes.
gpt-5.5
text, tools, reasoning
gpt-5.5-xhigh
text, tools, reasoning
gpt-5.5-high
text, tools, reasoning
gpt-5.5-medium
text, tools
gpt-5.5-low
text, tools
At a glance
Three facts to know before picking a model.
Everything below comes straight from the live provider catalog, so it always matches what /v1/models returns.
Default model
gpt-5.5-xhigh
Context / output limits
400,000 / 1,024
Metered price
$0.50 / 1M input, $3.00 / 1M output
Canonical ids
Public model table for SDKs and IDE provider catalogs.
One flat metered rate covers the whole GPT-5.5 line — the same price the landing page advertises.
gpt-5.5
GPT-5.5
gpt-5.5-xhigh
GPT-5.5 xHigh
gpt-5.5-high
GPT-5.5 High
gpt-5.5-medium
GPT-5.5 Medium
gpt-5.5-low
GPT-5.5 Low