Documentation

/api-reference/openapi.json get /v1/admin/organizations/{orgid}/metrics Returns usage metrics for an organization including summary totals, and breakdowns by workspace, API key, and model.

/api-reference/openapi.json get /v1/organizations/{orgid}/staking/farm Returns the staking farm source and last synced farm-credit state for an organization. The organization must be the NEAR-authenti

/api-reference/openapi.json get /v1/organizations/{orgid}/usage/by-model Returns one row per model, summed over a rolling window ending now: day = last 24h, week = last 7 days, month = last 30 days (N

/api-reference/openapi.json get /v1/organizations/{orgid}/usage/history Returns paginated usage history for an organization

/api-reference/openapi.json get /v1/services/{servicename}

/api-reference/openapi.json get /v1/admin/platform/metrics Returns aggregated metrics across all organizations including: - Total users and organizations - Total requests and revenue - Top models by u

/api-reference/openapi.json get /v1/admin/platform/metrics/timeseries Returns per-bucket requests, tokens, cost (paid/granted + verifiable/external splits), active organizations, and new signups for g

/api-reference/openapi.json get /v1/staking/farm/config Returns the active House of Stake farm configuration used to convert on-chain staking reward units into NEAR AI Cloud credits.

/api-reference/openapi.json get /v1/admin/platform/model-revenue Models for the selected period ranked by consumed cost, with requests, tokens, unique orgs, verifiable flag, provider type, and latency

/api-reference/openapi.json get /v1/admin/platform/org-revenue Organizations with usage in the selected period ranked by consumed cost, with the verifiable/external split, requests, tokens, models use

/api-reference/openapi.json get /v1/admin/platform/billing-summary Credit LIMITS (caps) and consumption — NOT payments/cash. Returns active paid/grant credit limits, total consumed, paying/granted org

/api-reference/openapi.json get /v1/admin/platform/infra-summary Fetches the live host list, counts active/idle hosts, and computes the monthly/daily GPU burn rate from the configured cost-per-host. D

/api-reference/openapi.json get /v1/admin/organizations/{orgid}/metrics/timeseries Returns daily/weekly/hourly aggregations for charting: requests, tokens, and cost per time period.

/api-reference/openapi.json get /v1/users/me/refresh-tokens Returns all active refresh tokens for the currently authenticated user.

/api-reference/openapi.json get /v1/organizations/{orgid}/usage/metrics

/api-reference/openapi.json get /v1/organizations/{orgid}/usage/timeseries

/api-reference/openapi.json get /v1/workspaces/{workspaceid} Returns workspace details for a specific workspace ID.

Use the Go SDK for verified, encrypted Chat Completions. Install Requires Go 1.25.8 or later. Install the published SDK in your application: bash theme={"dark"} go mod init example.com/my-app If your

Configure Goose to use NEAR AI Cloud as an OpenAI-compatible provider. Goose is an open-source AI agent from Block that runs as a desktop app and a CLI. It ships a first-class NEAR AI Cloud provider,

/api-reference/openapi.json get /v1/health Check service health status. No authentication required.

Apply an image-provenance policy to configurations measured in NEAR AI Cloud gateway and model attestations. Image provenance is separate from hardware attestation. A verified quote can bind a configu

Use NEAR AI Cloud with third-party software that supports OpenAI-compatible providers. Use these guides to connect third-party software to NEAR AI Cloud through its OpenAI-compatible API. Most clients

/api-reference/openapi.json post /v1/organizations/{orgid}/members/invite-by-email Invites multiple users to the organization by their email addresses. The authenticated user must be an owner or admin

Use the JavaScript SDK for verified, end-to-end encrypted Chat Completions. Install The SDK is available on npm. It requires Node.js 24 or later for Node usage. bash theme={"dark"} npm install @nearai

Configure LibreChat to use NEAR AI Cloud as an OpenAI-compatible custom endpoint. LibreChat can use NEAR AI Cloud through a custom OpenAI-compatible endpoint in librechat.yaml. Keep the endpoint name

/api-reference/openapi.json get /v1/organizations/{orgid}/reporting-tokens The response includes non-secret prefixes and audit timestamps. It never includes raw reporting tokens or stored hashes.

/api-reference/openapi.json get /v1/admin/access-tokens Retrieves a paginated list of all admin access tokens in the system. Only authenticated admins can access this endpoint.

/api-reference/openapi.json get /v1/admin/feature-requests

/api-reference/openapi.json get /v1/admin/models Returns a paginated list of all models in the system. By default, only active models are returned. Use includeinactive=true to also include disabled mo

/api-reference/openapi.json get /v1/admin/users Returns a paginated list of all users in the system. Only authenticated admins can perform this operation.