List Model Prices

GET /model_pricing

List Model Prices

List the prices this organization is billed at: one row per (provider, model), with the organization's own override taking the place of the catalog default where one exists. source says which you are looking at — user for an override, models.dev or snapshot for the catalog, depending on how this deployment obtains it.

Prices are integer cents per 1,000,000 tokens. cache_read, cache_write and reasoning may be 0, meaning "no distinct rate": those token classes then bill at the prompt or completion rate. duration_cents_per_1m_seconds prices models billed by audio length instead of tokens, and is operator-set only — the catalog carries no audio prices to fall back to.

Parameters

Responses

• 200: OK

• data (array, required):

• data[].id (string, required): Price row id. Pass it to the delete endpoint to drop an override; catalog rows cannot be deleted.

• data[].org_id (string, optional): Organization that owns this override. Omitted on catalog rows, which belong to no organization.

• data[].provider (string, required):

• data[].model_name (string, required):

• data[].prompt_cents_per_1m (integer, required): Input token rate.

• data[].completion_cents_per_1m (integer, required): Output token rate.

• data[].cache_read_cents_per_1m (integer, required): Rate for tokens read from an upstream prompt cache. 0 means no distinct rate — those tokens bill at the prompt rate.

• data[].cache_write_cents_per_1m (integer, required): Rate for tokens written into an upstream prompt cache. 0 means no distinct rate.

• data[].reasoning_cents_per_1m (integer, required): Rate for reasoning tokens. 0 means no distinct rate — they bill at the completion rate.

• data[].duration_cents_per_1m_seconds (integer, required): Cents per 1,000,000 seconds, for models billed by audio length rather than tokens. 0 means not billed by duration. Operator-set only: the catalog carries no audio prices.

• data[].source (string, required): Where the price came from. user is this organization's own override. The other two are catalog defaults and are mutually exclusive per deployment: models.dev when the control plane syncs the catalog online, snapshot when it seeds the catalog from a local file instead — which is what an air-gapped or offline installation does.

• data[].effective_from (string, required):

• data[].updated_at (string, required):

• 401: Missing or invalid bearer.

• error (object, required): Error details.

• error.code (string, required): Machine-readable identifier. Examples: UNAUTHENTICATED, INVALID_REQUEST, MASTER_KEY_UNSET, INTERNAL.

• error.message (string, required): Human-readable explanation; safe to surface to operators.

cURL

curl -X GET '$AISIX_CP/model_pricing' -H 'Authorization: Bearer $AISIX_TOKEN'