Documentation

POST /v1/images/generations Generate images from text prompt Generate images using an AI model from a text description. OpenAI-compatible endpoint. Request body (application/json): - model (string, re

GET /v1/admin/organizations/{orgid} Get a single organization by id (Admin only) Returns one organization with its spend limit and usage. Only authenticated admins can perform this operation. Returns

GET /v1/admin/organizations/{orgid}/staking/farm Get admin organization staking farm state Returns the staking farm source and last synced farm-credit state for any organization. Requires platform adm

GET /v1/workspaces/{workspaceid}/api-keys/{apikeyid}/usage/history Get API key usage history Returns paginated usage history for a specific API key Parameters: - workspaceid (path, string, required):

GET /v1/attestation/report Get attestation report Get hardware attestation report for TEE verification. Requires an API key (nearai/infra193); report retrieval is non-billable — no usage or billing re

GET /v1/admin/models/{modelname}/history Get complete history for a model (Admin only) Returns the complete history for a specific model, showing all changes over time including pricing, context lengt

GET /v1/signature/{chatid} Get completion or Responses API signature Get a cryptographic signature for a chat completion or completed stateless resp response. Returns signature data on success, or an

POST /v1/billing/costs Get costs by request IDs Returns the cost in nano-USD for each request ID provided. A request ID is the UUID from the inference-id response header of /v1/chat/completions and /v

GET /v1/users/me Get current user Returns the profile of the currently authenticated user, including their organizations and workspaces. Responses: 200: Current user profile - authprovider (string, re

GET /v1/users/me/status Get current user's account eligibility status Returns a minimal eligibility response for frontend preflight checks. AML/KYT provider details are never exposed in this public re

GET /v1/attestation/ita-token Get Intel Trust Authority attestation token Get Intel Trust Authority signed attestation JWTs for the gateway and, when requested, compatible model provider evidence. Pub

GET /v1/invitations/{token} Get invitation details by token (public endpoint) Returns invitation details for a specific token. This is a public endpoint that allows users to view invitation details be

GET /v1/admin/organizations/{orgid}/limits/history Get limits history for an organization (Admin only) Returns the complete limits history for a specific organization, showing all limits changes over

GET /v1/model/{modelname} Get model details Get pricing and metadata for a specific model. URL-encode model names containing slashes. Public endpoint. Parameters: - modelname (path, string, required):

GET /v1/organizations/{orgid}/usage/balance Get organization balance Returns the current spending balance for an organization Parameters: - orgid (path, string, required): Organization ID. Responses:

GET /v1/admin/organizations/{orgid}/usage/balance Get organization balance (Admin only) Returns the current spending balance for an organization without requiring the caller to be a member of that org

GET /v1/organizations/{orgid} Get organization by ID Returns organization details for a specific organization ID. Parameters: - orgid (path, string, required): Organization ID. Responses: 200: Organiz

GET /v1/admin/organizations/{orgid}/concurrent-limit Get organization concurrent request limit (Admin only) Returns the current concurrent request limit for an organization. If no custom limit is set,

GET /v1/admin/organizations/{orgid}/metrics Get organization metrics (Admin only) Returns usage metrics for an organization including summary totals, and breakdowns by workspace, API key, and model. P

GET /v1/organizations/{orgid}/staking/farm Get organization staking farm state Returns the staking farm source and last synced farm-credit state for an organization. The organization must be the NEAR-

GET /v1/organizations/{orgid}/usage/by-model Get organization usage broken down by model. Returns one row per model, summed over a rolling window ending now: day = last 24h, week = last 7 days, month

GET /v1/organizations/{orgid}/usage/history Get organization usage history Returns paginated usage history for an organization Parameters: - orgid (path, string, required): Organization ID. - limit (q

GET /v1/services/{servicename} Get platform service by name (public, no auth) Parameters: - servicename (path, string, required): Service name (e.g. websearch). Responses: 200: Service details - costP

GET /v1/admin/platform/metrics Get platform-wide metrics for admin dashboards (Admin only) Returns aggregated metrics across all organizations including: - Total users and organizations - Total reques

GET /v1/admin/platform/metrics/timeseries Get platform-wide time series for admin dashboards (Admin only) Returns per-bucket requests, tokens, cost (paid/granted + verifiable/external splits), active

GET /v1/staking/farm/config Get staking farm configuration Returns the active House of Stake farm configuration used to convert on-chain staking reward units into NEAR AI Cloud credits. Responses: 200

GET /v1/admin/platform/model-revenue Get the per-model consumption ranking (Admin only) Models for the selected period ranked by consumed cost, with requests, tokens, unique orgs, verifiable flag, pro

GET /v1/admin/platform/org-revenue Get the per-organization consumption ranking (Admin only) Organizations with usage in the selected period ranked by consumed cost, with the verifiable/external split

GET /v1/admin/platform/billing-summary Get the platform billing summary (Admin only) Credit LIMITS (caps) and consumption — NOT payments/cash. Returns active paid/grant credit limits, total consumed,

GET /v1/admin/platform/infra-summary Get the platform infrastructure / fleet burn summary (Admin only) Fetches the live host list, counts active/idle hosts, and computes the monthly/daily GPU burn rat