Tool Compatibility Overview

The compatibility matrix behind every integration page on this site: which protocol each tool speaks, whether Claude models work with it, where its configuration lives, and when each page was last verified

Need an API key? Sign up →·Endpoints & base URLs →

Last verified: 2026-09-18 · 📄 Per official docs (the 26 tool pages below verified the same day; protocol capabilities derived from Endpoints and API paths)

Added on 2026-10-13: five more rows — Qwen Code, Kimi Code CLI, goose, LobeChat and Open WebUI. They were checked against each tool's official documentation; no test key was used, so each carries 📄. The “26 tool pages” above refers to the 2026-09-18 pass; the table now has 31 rows.

How to read this table¶

The rule for the three protocols: Claude models only work on the Anthropic protocol (base URL https://api.qcode.cc/api); GPT models use the OpenAI Chat (https://api.qcode.cc/openai/v1) and Responses protocols; GLM / Kimi / DeepSeek / Qwen use the Anthropic or OpenAI Chat protocol; QCode does not currently offer Gemini models. A client that only implements the OpenAI protocol cannot use Claude on QCode. The "Claude" column follows exactly that derivation; details live on each tool's page.

Compatibility matrix¶

Tools that cannot take a custom endpoint¶

These products expose no field for an arbitrary Base URL, so QCode cannot be connected and we publish no setup guide for them:

• Qoder: only vendor keys from its official catalogue, no third-party Base URL (official docs).
• Devin (cloud): closed SaaS, no custom Base URL; the desktop Devin Desktop goes through the ACP route (in the table).
• iFlow CLI: shut down by its vendor on 2026-04-17.

Accepts a custom URL, but has no page yet¶

• Junie (JetBrains' agent): BYOK inside the IDE does list only fixed vendors — OpenAI / Anthropic / Google / xAI / OpenRouter / Copilot (official page) — but custom model profiles in the Junie CLI accept any baseUrl: the JSON file goes into $JUNIE_HOME/models/*.json or the project's .junie/models/*.json, and apiType is one of Anthropic / OpenAICompletion / OpenAIResponses / Google (official docs). Its baseUrl must be the complete request URL — Junie appends no path. We have not written a dedicated page for it yet; endpoints and model IDs are in Endpoints and API formats.

GPT / Chinese models only, no Claude¶

Clients that implement only the OpenAI Chat Completions protocol work fine with GPT and the GLM / Kimi / DeepSeek / Qwen families, but calling Claude models returns model_not_available_on_endpoint (validated before authentication). Every row with ❌ in the Claude column is of this kind (WorkBuddy, Codex…). In addition: CodeBuddy's models.json supports only OpenAI Chat and demands the full /chat/completions URL; Warp's custom inference endpoint is OpenAI-Chat-only and its requests are relayed through Warp servers; Chatbox is listed in this group on the strength of its official user guide, which illustrates only two API types when adding a custom provider — OpenAI API compatible for GPT models, Google Gemini compatible for Gemini models. The official repository docs also list Claude as one of the provider API types (the English UI label is "Claude API Compatible"), with custom entries mapped to CustomClaude, but neither source states how the API Host and API Path should be filled for that type, so this page makes no claim about Claude through Chatbox in either direction.

Related docs¶

• Endpoints and API paths — the protocol × model-family source of truth
• Subscriptions vs API Keys vs QCode Keys
• Troubleshooting
• FAQ

Enterprise →