GET

/v1/models/llmgateway/llmgateway-azure-gpt-5-4-nano

Accept:

provider llmgatewaystatus activefirst seen Mar 17, 2026last seen 48s ago

rawId	azure/gpt-5.4-nano
displayName	GPT-5.4 Nano (azure)
id	llmgateway-azure-gpt-5-4-nano
activity	chat
schemaEndpointId	v1/chat/completions input · output
releasedAt	1773705600 — Mar 17, 2026
firstSeenAt	1773705600 — Mar 17, 2026
lastSeenAt	1794564180 — 48s ago
pricing	$0.2 / 1M input · $1.25 / 1M output → open calculator https://api.llmgateway.io/v1/models input_tokens (usage) · output_tokens (usage) · cache_read_tokens (usage) · web_searches (usage)
maxOutput	128000
modalities	{"input":["text","image"],"output":["text"]}
capabilities	{"temperature":true,"max_tokens":true,"top_p":true,"frequency_penalty":true,"presence_penalty":true,"response_format":true,"tools":true,"tool_choice":true,"reasoning":true,"reasoning_effort":false,"seed":false,"stop":false}
requestMap	{"thinking":{"on":{"reasoning_effort":"high"},"off":{"reasoning_effort":"none"},"levels":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null}},"maxTokensField":"max_tokens","developerRole":null,"replayReasoningContent":null,"store":null,"strictTools":null,"sessionAffinity":null,"cacheControl":null,"toolStream":null,"reasoningEffort":null}
contextWindow · knowledgeCutoff · openWeights · weightsUrl · providerMetadata	not published by this provider’s list endpoint

Endpoints & schemas

GET /v1/schemas/llmgateway →

endpoint	activity
v1/chat/completions input · output	chat

endpoints matching this model — the provider has more, see /v1/schemas/llmgateway

Sources

field	recorded source
maxOutput	Source unknown — no source URL recorded. listing
modalities	Source unknown — no source URL recorded. listing
pricing	Source linked above. listing data[].providers[providerId=azure].pricing Source trace `7b966d2d38e91e7db277563d21ce819d084b046c1d4f284fce3be0bf7983e750`
reasoning	Source unknown — no source URL recorded. listing
capabilities.temperature	Source unknown — no source URL recorded. listing
capabilities.max_tokens	Source unknown — no source URL recorded. listing
capabilities.top_p	Source unknown — no source URL recorded. listing
capabilities.frequency_penalty	Source unknown — no source URL recorded. listing
capabilities.presence_penalty	Source unknown — no source URL recorded. listing
capabilities.response_format	Source unknown — no source URL recorded. listing
capabilities.tools	Source unknown — no source URL recorded. listing
capabilities.tool_choice	Source unknown — no source URL recorded. listing
capabilities.reasoning	Source unknown — no source URL recorded. listing
capabilities.reasoning_effort	Source unknown — no source URL recorded. listing unlisted
capabilities.seed	Source unknown — no source URL recorded. listing unlisted
capabilities.stop	Source unknown — no source URL recorded. listing unlisted
sameAs	https://api.llmgateway.io/v1/models listing data[].providers[].externalId Source trace `481cc176ee4671e20b0658daa7051297e43511c9418ebb18c0d123be98049d8b`
activity	Source unknown — no source URL recorded.
contextWindow	Source unknown — no source URL recorded.
requestMap	Source unknown — no source URL recorded.
schemaEndpointId	Source unknown — no source URL recorded.

Use it

shell

$ curl https://modelschemas.com/v1/schemas/llmgateway/chat/v1/chat/completions # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"llmgateway","endpointId":"v1/chat/completions","payload":{…}}'
$ curl -X POST https://modelschemas.com/v1/estimate -d '{"provider":"llmgateway","model":"azure/gpt-5.4-nano","usage":{"input_tokens":1200,"output_tokens":400}}'