Documentation

Configure Cline, Roo Code, and Kilo Code with NEAR AI Cloud's OpenAI-compatible API. Cline, Roo Code, and Kilo Code can use NEAR AI Cloud through OpenAI-compatible provider settings. They share the sa

/api-reference/openapi.json post /v1/admin/models/pricing-changes/confirm Persists the schedule (the background scheduler applies each change at its effective date) and sends one consolidated email pe

/api-reference/openapi.json post /v1/admin/models/{modelname}/deprecation/confirm

Configure Continue to use NEAR AI Cloud through its OpenAI-compatible provider. Use Continue with NEAR AI Cloud by configuring Continue's OpenAI provider with the NEAR AI Cloud gateway base URL and a

/api-reference/openapi.json post /v1/users/me/access-tokens Creates a new short-lived access token using the current refresh token.

/api-reference/openapi.json post /v1/organizations Creates a new organization with the authenticated user as owner.

/api-reference/openapi.json post /v1/organizations/{orgid}/workspaces Creates a new workspace within the specified organization. The authenticated user must be a member of the organization to create w

/api-reference/openapi.json post /v1/organizations/{orgid}/reporting-tokens Organization owners and admins can create reporting tokens for usage export and summary endpoints. The raw rpt- token is ret

/api-reference/openapi.json post /v1/admin/access-tokens Creates an access token for admin users with customizable expiration time, IP address, and user agent. This is typically used by billing servic

/api-reference/openapi.json post /v1/workspaces/{workspaceid}/api-keys Creates a new API key for a workspace. Note: The key may take up to 10 seconds to become active for authentication due to interna

/api-reference/openapi.json post /v1/chat/completions Generate AI model responses for chat conversations. Supports both streaming and non-streaming modes. OpenAI-compatible endpoint.

/api-reference/openapi.json post /v1/admin/services

/api-reference/openapi.json post /v1/responses Generate a single-turn, stateless AI response with optional streaming.

/api-reference/openapi.json post /v1/completions Generate AI model responses for text prompts. OpenAI-compatible endpoint.

Configure Cursor with NEAR AI Cloud through Cursor's OpenAI API key and base URL settings. [!WARNING] Limited support Cursor can accept an OpenAI API key and an overridden OpenAI-compatible base URL,

/api-reference/openapi.json post /v1/users/me/invitations/{invitationid}/decline Declines a pending invitation to join an organization.

/api-reference/openapi.json delete /v1/admin/models/{modelname} Soft deletes a model by setting isactive to false. This preserves historical usage records that reference the model name while preventin

/api-reference/openapi.json delete /v1/admin/access-tokens/{tokenid} Revokes an admin access token by setting it as inactive. Only authenticated admins can perform this operation.

/api-reference/openapi.json delete /v1/organizations/{orgid} Deletes an organization. Only the organization owner can perform this action.

/api-reference/openapi.json delete /v1/workspaces/{workspaceid} Deletes (deactivates) a workspace. Only the workspace creator or organization admin/owner can delete.

/api-reference/openapi.json post /v1/admin/models/deprecate Atomically marks modelId as deprecated and routes its traffic to successorModelId: 1. Adds modelId as an alias of successorModelId, so exist

Configure Dify with NEAR AI Cloud through the OpenAI-API-compatible model provider plugin. Dify can use NEAR AI Cloud through the OpenAI-API-compatible model provider plugin. Configure it as a custom

Experimental: send requests straight to one self-hosted model's TEE endpoint, without the NEAR AI Cloud Gateway. [!WARNING] Experimental. Direct completions endpoints are not recommended for new integ

/api-reference/openapi.json post /v1/rerank Ranks documents by relevance to a query using a reranker model. Concurrent Request Limits: Each organization has a per-model concurrent request limit (defau

/api-reference/openapi.json post /v1/images/edits Edit images using an AI model from an image and text description. OpenAI-compatible endpoint. Request Body (multipart/form-data): All fields should be

Use NEAR AI Cloud for embeddings, reranking, image generation, audio transcription, and PII detection — all inside TEEs NEAR AI Cloud is not limited to chat completions. The NEAR AI Cloud Gateway (clo

How to use end-to-end encryption for chat completions with NEAR AI Cloud NEAR AI Cloud runs both the gateway and model inference inside Trusted Execution Environments (TEEs), providing strong hardware

/api-reference/openapi.json get /v1/organizations/{orgid}/usage/export Requires a reporting token scoped to the organization in the path. Results are returned in descending (createdat, source, id) ord

Use server-side multi-model deliberation from OpenAI-compatible clients Fusion runs a private, server-side deliberation across multiple models and returns one OpenAI-compatible chat completion. Your c

Verify the NEAR AI Cloud gateway attestation for requests sent to cloud-api.near.ai. gatewayattestation is evidence for the NEAR AI Cloud gateway. It is not evidence for a model environment. Use model