Skip to content

Supported clients

Configure CloudService in clients that support the OpenAI-compatible API, the Anthropic Messages API, or local agent workflows.

Choose the correct base URL

Start with the key you bought

Choose one billing path

Your choice is remembered across the documentation. Then select the card that matches your client protocol.

For a key funded with a dollar credit balance.

OpenAI-compatible Chat Completions or Responses

Use with: Codex, OpenCode, Cursor, Roo Code, SDKs, and direct HTTP

Base URL to enter

https://api.yourdomain.example/v1

Native Anthropic Messages

Use with: Claude Code, Claude Desktop, and native Messages clients

Base URL to enter

https://api.yourdomain.example

The protocol decides whether the client field ends in /v1. OpenAI-compatible clients use a base URL ending in /v1. Native Anthropic clients use the origin only, without /v1, because they append /v1/messages themselves. A Claude token key therefore reaches /token/v1/messages when the native client builds its request.

Use the key's matching billing surface and only models returned by its authenticated catalog. A Claude token key and an OpenAI token key are provider-scoped; neither can be swapped onto the other's models.

Claude Desktop is a native Anthropic client with its own third-party inference settings. Follow the Claude Desktop guide; it does not read Claude Code's configuration.

Claude Code, managed Claude Desktop on 3P, and OpenClaw's anthropic-messages adapter use the native Messages origin. Native Codex, Cline CLI, and OpenClaw's Codex provider use the Responses API. Cline for VS Code, Hermes, OpenCode, Cursor, Roo Code, Continue, TRAE SOLO, Cherry Studio, API Code, and n8n use OpenAI-compatible adapters. OpenClaw gives deepseek-v4-flash its own Chat Completions provider.

Every configuration example is a starting point, not a model entitlement list. Use the matching authenticated /models endpoint after setup; it is the only current source for the model IDs and capabilities your key may use.

For full repo/file/terminal tools, use a real local agent client such as Codex, OpenCode, OpenClaw, Hermes, or supported agent mode in the app. A plain chat client cannot read local files unless it exposes and executes tools locally.

Browser apps

CloudService also includes hosted browser apps. Use these when you want a web workspace instead of configuring a third-party client.

  • Web Chat — browser conversations for everyday AI work.
  • Studio — website and app generation with rendered previews.

Third-party clients below use the protocol named in their guide. Cherry Studio is a separate desktop client and is not the same product as CloudService Studio.

Clients

  • Codex — Terminal and IDE agent. Native OpenAI Responses provider with shared user configuration.
  • Cursor — Experimental custom OpenAI-compatible Claude or Codex models; some Cursor-owned features may not use the custom route.
  • Roo Code for VS Code — OpenAI Compatible profiles for Claude or Codex, plus DeepSeek when the authenticated catalog confirms tool support.
  • Cline — CLI and VS Code agent using one raw key, with no custom authentication header.
  • Continue for VS Code — Universal OpenAI-compatible Chat/Edit profile for deepseek-v4-flash, including text-only fallback routes.
  • TRAE SOLO — Agent IDE. Use custom OpenAI Chat Completions model settings.
  • Claude Code — Terminal agent. Uses CloudService's Anthropic Messages gateway and model discovery.
  • Claude Desktop on 3P — Managed desktop deployment. Uses its own third-party inference Gateway configuration, separate from Claude Code and consumer Claude.ai chats.
  • OpenCode — Terminal and desktop agent. OpenAI-compatible Claude or Codex models.
  • OpenClaw — Uses separate Anthropic Messages, OpenAI Responses, and capability-aware DeepSeek Chat Completions providers.
  • Hermes — CLI agent with separate Claude, Codex, and tool-capable DeepSeek providers.
  • Cherry Studio — Desktop client. Use OpenAI-compatible provider settings.
  • n8n — Workflow automation. AI Agent with the OpenAI Chat Model sub-node for Claude, Codex, and DeepSeek; includes an importable starter workflow.
  • API Code — SDK / HTTP. Use OpenAI SDKs or direct HTTP with CloudService base URL.