Current price of one AI model
The current price of one model by its key (the same name as the model field of a
request). The response has the same shape as the list, with one entry in models.
ETag and If-None-Match work the same way. No such model, or it cannot be called
right now — 404: do not send the generation until it is back.
Required key permission: none — any active key works.
Parameters
Values go straight into the request line, and the URL is built for you. Below are each parameter’s type, whether it is required, and its allowed values.
- stringin pathrequired
The model name — the same as the
keyfield of theGET /ai/modelslist and themodelfield of an AI API request.The value goes straight into the request line above.
Possible responses
200The model with its current price.
The model with its current price.
{
"success": true,
"message": "string",
"data": {
"version": "string",
"models": [
{
"key": "string",
"name": "string",
"family": "string",
"kind": "string",
"description": "string",
"context_window": "string",
"max_output_tokens": "string",
"capabilities": "string",
"pricing_mode": "string",
"price": {
"key": {
"per_mtok_minor": 1,
"per_mtok_formatted": 1
}
},
"billing_available": true,
"byok": "string"
}
],
"asset": {
"id": 1,
"code": "string",
"kind": "money",
"precision": 1,
"name": null,
"is_active": true,
"is_default": true,
"default_balance": 1,
"deleted_at": "2026-07-17T12:34:56+00:00",
"created_at": "2026-07-17T12:34:56+00:00",
"updated_at": "2026-07-17T12:34:56+00:00"
}
}
}Success flag. Branch on the HTTP status code instead: any 2xx response carries true here, while an error comes back in a different shape that need not contain this field at all.
A human-readable note in the account language. Fine to show to a user; do not parse it — the wording changes without notice and is not an error code.
datarequiredThe response payload.
object
The response payload.
Price list version. It changes with any price change, together with the ETag header.
modelsrequiredA single entry — the requested model with its current price.
array<AiGatewayCatalogModel>AiGatewayCatalogModel
A single entry — the requested model with its current price.
The model name for the model field of an AI API request, exactly as written: the gateway looks the model up by exact match.
Human-readable model name.
Model family (for example claude, gpt) — for grouping in a list.
chat or image. An image model is called through /v1/images (or through chat — the answer arrives as a markdown image); its price is price.request.
A short description of the model; null when there is none.
The model context window, in tokens.
How many tokens the model can produce in one answer.
Model capabilities (image input, tools, reasoning and so on). Image models carry image_options — allowed values of the size / aspect_ratio fields of /v1/images/*, the first one is the default; no key means no choice.
How the rate is set: markup follows the provider price and may change, fixed is set by Lumean and does not depend on the provider.
pricerequiredCurrent rates per token class. null — the model is not sold for money right now. A zero for a single class means that class is not billed (for example request on chat models).
nullableobject
Current rates per token class. null — the model is not sold for money right now. A zero for a single class means that class is not billed (for example request on chat models).
Whether the model can be called with a paid key. false on a live model — it is listed for calls with your own provider key (BYOK), and a paid call is refused.
Whether the model can be called with your own provider key (BYOK): available and the refusal reason — not_entitled (the plan does not include BYOK), no_credential (no key of yours for a matching provider) or null.
assetrequiredThe asset the rates are in (LUMC), with precision: the real rate is minor / 10^precision.
AssetAsset
The asset the rates are in (LUMC), with precision: the real rate is minor / 10^precision.
Internal identifier of the asset.
Asset code: LUMC is the internal currency, TOKEN the generation tokens.
Kind of asset: money or consumable units. It decides whether an amount counts as a payment or as quota consumption.
Number of decimal places. The load-bearing field: every integer amount in this asset is divided by 10^precision to obtain the real value. Do not assume the divisor is 100.
Display name of the asset, in the account language.
When the asset was retired, ISO 8601. null while it is in use.
When the asset was created, ISO 8601.
When the asset last changed, ISO 8601.
304The price has not changed since the ETag you sent.
The price has not changed since the ETag you sent.
"string"404There is no such model, or it cannot be called right now.
There is no such model, or it cannot be called right now.
{
"success": false,
"message": "Resource not found."
}Always false in error responses.
Error text in the key's language (set through the X-Locale header).
Machine-readable reason — present on business refusals (for example, invalid_order_status); other errors omit it. Branch on it, not on the message text.
The same machine-readable code as in reason — a second name for the field. Arrives together with reason; the values always match.
Nearby
Neighbouring operations
This page for AI
API version 1.0.0