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
Fast smoke model: gpt-5.5-medium
Limits are family-specific: 272,000 context tokens for GPT-5.5 and 372,000 for GPT-5.6 families; requested output is capped at 128,000.
Release metadata date: 2026-07-16; last updated 2026-07-16.
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-low
text, tools, reasoning
gpt-5.5-medium
text, tools, reasoning
gpt-5.5-high
text, tools, reasoning
gpt-5.5-xhigh
text, tools, reasoning
gpt-5.6-sol
text, tools, reasoning
At a glance
Three facts to know before picking a model.
These are product and stock-catalog facts. Authenticated GET /v1/models remains the only authority for the exact efforts currently routable for your key.
Default model
gpt-5.5
Context / output limits
272,000–372,000 / 128,000
Metered pricing
OpenAI standard ÷ 10
Effort matrix
Four families, at most 25 exact candidate ids.
Candidate catalog 2026-07-16.2. Every base family defaults to medium; authenticated GET /v1/models publishes only the exact live-verified subset and never substitutes a failed effort.
gpt-5.5
The base id stays gpt-5.5; when effort is omitted, the request uses medium.
Efforts: low, medium, high, xhigh
Metered API: $0.50 input / $3.00 output per 1M tokens.
Cached / cache write: $0.05 cached input / not published per 1M tokens. Above 272K input, the full request uses 2× input and 1.5× output pricing.
gpt-5.6-sol
The base id stays gpt-5.6-sol; when effort is omitted, the request uses medium.
Efforts: low, medium, high, xhigh, max, ultra
Metered API: $0.50 input / $3.00 output per 1M tokens.
Cached / cache write: $0.05 cached input / $0.625 cache write per 1M tokens. Above 272K input, the full request uses 2× input and 1.5× output pricing.
gpt-5.6-terra
The base id stays gpt-5.6-terra; when effort is omitted, the request uses medium.
Efforts: low, medium, high, xhigh, max, ultra
Metered API: $0.25 input / $1.50 output per 1M tokens.
Cached / cache write: $0.025 cached input / $0.3125 cache write per 1M tokens. Above 272K input, the full request uses 2× input and 1.5× output pricing.
gpt-5.6-luna
The base id stays gpt-5.6-luna; when effort is omitted, the request uses medium.
Efforts: low, medium, high, xhigh, max
Metered API: $0.10 input / $0.60 output per 1M tokens.
Cached / cache write: $0.01 cached input / $0.125 cache write per 1M tokens. Above 272K input, the full request uses 2× input and 1.5× output pricing.
Use only the canonical public model id and the endpoint-specific effort field. Capacity topology stays private and may change without changing the customer contract.
Canonical ids
Candidate ids for SDKs and IDE provider catalogs.
This table is the maximum stock candidate universe. Use authenticated GET /v1/models as the runtime authority: failed or unavailable exact efforts are omitted individually.
gpt-5.5
GPT-5.5
gpt-5.5-low
GPT-5.5 Low
gpt-5.5-medium
GPT-5.5 Medium
gpt-5.5-high
GPT-5.5 High
gpt-5.5-xhigh
GPT-5.5 xHigh
gpt-5.6-sol
GPT-5.6 Sol
gpt-5.6-sol-low
GPT-5.6 Sol Low
gpt-5.6-sol-medium
GPT-5.6 Sol Medium
gpt-5.6-sol-high
GPT-5.6 Sol High
gpt-5.6-sol-xhigh
GPT-5.6 Sol xHigh
gpt-5.6-sol-max
GPT-5.6 Sol Max
gpt-5.6-sol-ultra
GPT-5.6 Sol Ultra
gpt-5.6-terra
GPT-5.6 Terra
gpt-5.6-terra-low
GPT-5.6 Terra Low
gpt-5.6-terra-medium
GPT-5.6 Terra Medium
gpt-5.6-terra-high
GPT-5.6 Terra High
gpt-5.6-terra-xhigh
GPT-5.6 Terra xHigh
gpt-5.6-terra-max
GPT-5.6 Terra Max
gpt-5.6-terra-ultra
GPT-5.6 Terra Ultra
gpt-5.6-luna
GPT-5.6 Luna
gpt-5.6-luna-low
GPT-5.6 Luna Low
gpt-5.6-luna-medium
GPT-5.6 Luna Medium
gpt-5.6-luna-high
GPT-5.6 Luna High
gpt-5.6-luna-xhigh
GPT-5.6 Luna xHigh
gpt-5.6-luna-max
GPT-5.6 Luna Max