Integrations

Agents & OpenAI-compatible clients

Point any OpenAI-compatible client or agent framework at Roteo.

Roteo's /v1/chat/completions and /v1/responses endpoints work with any OpenAI-compatible client: chat apps, coding agents and agent frameworks.

Universal settings

SettingValue
Base URLhttps://api.roteo.ai/v1
API keysk_your_key
Chat path/chat/completions
Modelan open-weight or gpt-* id, e.g. glm-5.3 or gpt-5.6-sol

For agents on these endpoints, use an open-weight or GPT model. Agent frameworks are refused on Claude models here, with a message telling you to switch. Claude works in agents that run Claude Code underneath: Claude Code itself, opencode's Claude Agent mode, Hermes with Roteo's plugin and omp with Roteo's plugin. It also works in direct API calls.

Model support for agents

ModelsopencodeHermesompOther agent frameworks (OpenClaw, Cursor)
Open-weight: glm-5.3, glm-5.3-flash, deepseek-v4-flash-0731, kimi-k3, qwen3.8-maxRecommended, verified with real tool callsSupported, not yet verifiedSupportedSupported, not yet verified per framework
GPT: gpt-*Supported, not yet verifiedSupportedVerified with real tool calls (Responses wire)Supported, not yet verified per framework
Claude: claude-*Through the Claude Agent mode, verified with real tool callsThrough Roteo's plugin, verified with real tool callsThrough Roteo's plugin, verified with real tool callsNot available; use Claude Code

Guides per tool

Chat apps

Any app with a "Custom Provider" or "OpenAI-compatible" option works: Chatbox, LobeChat, Cherry Studio, NextChat, Open WebUI and more. Use the universal settings above; most apps load the model list from GET /v1/models on their own.

Anything else

If it speaks the OpenAI Chat Completions or Responses protocol, it works: LangChain, LiteLLM, Continue, Aider and the OpenAI SDKs. See the OpenAI SDK guide. An agent that can read can also onboard itself from /v1/llms.txt.

Agents & OpenAI-compatible clients | Roteo