NEAR AI Cloud: API Reference

OpenAI-compatible REST API for private, verifiable AI inference on NEAR AI Cloud

The NEAR AI Cloud API is a REST API served from a single base URL. Its documented OpenAI-compatible inference surfaces work with OpenAI SDKs by pointing them at NEAR AI.

https://cloud-api.near.ai/v1

Authentication

Every request is authenticated with a bearer token in the Authorization header. The API accepts four token types; for programmatic access you almost always want an API key.

Token	Prefix	Use for
API key	sk-	Programmatic access to inference and most endpoints. Create keys in the Developer Dashboard.
Access token (JWT)	—	Short-lived user session token used by the dashboard. Create via POST /v1/users/me/access-tokens with a refresh token.
Refresh token	rt_	Long-lived token from OAuth login. Only valid for POST /v1/users/me/access-tokens.
Reporting token	rpt-	Read-only access to the usage reporting endpoints. Create via POST /v1/organizations/{org_id}/reporting-tokens.

curl https://cloud-api.near.ai/v1/chat/completions \
  -H "Authorization: Bearer $NEAR_AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.1-FP8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Each endpoint page lists which token types it accepts under Authorizations.

Every endpoint page has an interactive playground: paste your key, edit the request, and send it directly from the browser.

Chat Completions

The primary inference endpoint

Models

List models, context windows, and pricing

Attestation

Verify the TEE running your requests

[!NOTE]

POST /v1/responses is stateless and supports store: false only. Read the Stateless Responses guide before migrating an integration that uses conversations, files, response history, or built-in tools.

[!NOTE]

New to NEAR AI Cloud? Start with the Quickstart, then see OpenAI Compatibility for SDK setup details.