IN ENGLISH · API DOCS

Unsupported endpoints and features

The gateway accepts a path only when it can meter its cost exactly. Paths that cannot be metered (such as OpenAI Assistants, a file with a purpose other than batch, or Gemini cachedContents) are refused with 402 and code path_unmetered, before anything is sent or billed. This page is the full list, so that you know before you build.

Last updated:

[01]UNSUPPORTED ENDPOINTS

On the OpenAI routes

Unsupported under /v1
WhatPathAnswer
Files with a purpose other than batch, UploadsPath:/v1/files, /v1/uploadsAnswer:402 path_unmetered
Other Files and Batches pathsPath:Under /v1/files and /v1/batches, any path but the batch routesAnswer:402 path_unmetered
Assistants, ThreadsPath:/v1/assistants, /v1/threadsAnswer:402 path_unmetered
Vector stores, ContainersPath:/v1/vector_stores, /v1/containersAnswer:402 path_unmetered
ConversationsPath:/v1/conversationsAnswer:402 path_unmetered
Fine-tuning, EvalsPath:/v1/fine_tuning, /v1/evalsAnswer:402 path_unmetered
Stored responses and chat completionsPath:/v1/responses/{id}, /v1/chat/completions/{id}Answer:402 path_unmetered
The organization admin APIPath:/v1/organizationAnswer:402 path_unmetered
OpenAI's own Realtime client secretsPath:/v1/realtime/client_secretsAnswer:402 path_unmetered; use /v1/realtime/client_secret (realtime voice)
Background execution on ResponsesPath:background: trueAnswer:400 path_unmetered
Hosted toolsPath:code_interpreter, file_search, image_generation, computer_use, mcpAnswer:400 hosted_tool_unmetered
Streamed image generationPath:stream: trueAnswer:400 path_unmetered
Service tiersPath:service_tierAnswer:400 invalid_request

Because store is always false, features that rely on a response stored at OpenAI are not available. The Batch API and the upload of its input files (purpose=batch) are supported, at 50% of the usual price: OpenAI Batch.

[02]UNSUPPORTED ENDPOINTS

On the Anthropic route

  • Under /anthropic only POST /v1/messages, POST /v1/messages/count_tokens, GET /v1/models and Message Batches (without the batch list) are documented and supported. Other paths (such as the Files API and the Admin API) answer 402 with code path_unmetered.
  • The code_execution tool answers 400 with code hosted_tool_unmetered.
[03]UNSUPPORTED ENDPOINTS

On the Gemini route

Unsupported under /gemini
WhatPathAnswer
Explicit cachingPath:cachedContentsAnswer:402 path_unmetered; implicit caching is automatic and its discount is applied
File upload and listingPath:/upload/…, filesAnswer:402 path_unmetered
Batch processingPath:batches, :batchGenerateContent, :batchEmbedContentsAnswer:402 path_unmetered
Native embeddingsPath::embedContentAnswer:402 path_unmetered; use POST /v1/embeddings
Imagen (:predict)Path::predictAnswer:402 path_unmetered
Tuned models, corpora, File Search storesPath:tunedModels, corpora, fileSearchStoresAnswer:402 path_unmetered
Ephemeral tokensPath:auth_tokensAnswer:402 path_unmetered
Other API versionsPath:Any version but v1beta and v1 (such as v1alpha)Answer:402 path_unmetered
Google Maps groundingPath:tools: [{googleMaps}]Answer:402 hosted_tool_unmetered
A key in the URLPath:?key=Answer:401
[04]UNSUPPORTED ENDPOINTS

What is not offered at all

  • A rerank endpoint.
  • An MCP server for customers.
  • OAuth: authentication is by API key only.
  • WebRTC for realtime voice; WebSocket only.
  • An API to top up the wallet or to create and revoke keys; those are done in the dashboard.
  • Models run on infrastructure of our own; every model is run by its own vendor.

A path that is not in this documentation answers 404 with code path_not_found. Every code is in the error reference; any change to this list is recorded in the changelog.

1xAi is an independent gateway. It is not affiliated with, endorsed by, or a reseller for OpenAI, Anthropic, Google, DeepSeek, xAI, Moonshot AI, Z.ai, Alibaba Qwen, MiniMax or Tencent Hunyuan. Requests are relayed upstream rather than answered by models of our own, so each provider's own usage policies apply to what their models will and will not do, and their model availability is theirs to change. Current reachability is published on the status page.