Use DaoXE in Cline

Cline is an autonomous coding agent for VS Code. Point it at DaoXE's OpenAI-compatible endpoint and drive its file edits and tool use with GPT, Claude, Gemini, DeepSeek and more — from one key.

Updated 2026-07-20

Cline speaks to any OpenAI-compatible endpoint, so switching it to DaoXE is a base-URL-and-key change — no proxy, no fork. The payoff: one key for the cheapest APIs guide across vendors, and an agent that can plan on a frontier model and edit on a cheaper one.

Why route Cline through DaoXE#

  • One key, many models. Swap the agent's model without juggling per-vendor accounts, cards or bills.
  • Route by cost. A small model for routine edits, a frontier model for planning — all on one balance.
  • Native tool calling. Cline's agentic edits and command runs behave as expected when the model supports tools.

Set it up in Cline#

  1. Open the provider settings. In the Cline panel, click the settings gear and set API Provider to OpenAI Compatible.
  2. Set the Base URL. Enter https://daoxe.com/v1 — end it at /v1, not /chat/completions (Cline appends the path itself).
  3. Paste your key and Model ID. Add your DaoXE key, then a Model ID copied verbatim from GET /v1/models. Guessed names fail.
  4. Click Verify. Cline sends one live request; once it passes, run a small task to confirm edits and tool use work.

Caveats worth knowing

The Base URL must end at /v1 — a trailing /chat/completions yields malformed URLs. Model IDs are account-scoped, so read them from GET /v1/models. Agent mode needs a model with real tool-calling; if edits stall, switch to a tool-capable model and set an adequate context window under Model Configuration. More clients in the client setup notes.

Verify you actually get the model#

Prove the endpoint works before blaming the client — if this fails, no setting will fix it:

bash
export DAOXE_API_KEY="your_api_key"

# List the exact model IDs your account can call
curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/models \
  -H "Authorization: Bearer ${DAOXE_API_KEY}"

A cheaper endpoint is only a saving if it serves the real model. Prove connectivity first, then diff outputs against the official API at temperature 0:

bash
curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/chat/completions \
  -H "Authorization: Bearer ${DAOXE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_EXACT_MODEL_ID",
    "max_tokens": 64,
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

Verify us — don't trust us

Point the open benchmark at DaoXE and at the official API and compare at temperature 0. Then learn to detect model swapping so a cheaper endpoint can't quietly swap you to a smaller model.

Frequently asked questions#

Does Cline work with DaoXE?

Yes — choose the OpenAI Compatible provider, set the base URL to https://daoxe.com/v1, and paste your key plus an exact model ID.

Why does my Model ID say 'not found'?

The ID must match a string from GET /v1/models for your account. Copy it verbatim; IDs are account-scoped.

Can I use Claude and GPT in the same setup?

Yes — add several model IDs and switch between them on one balance. Current price advantage: typically ~30–80% below list via low-price groups.

Agent edits don't apply — why?

Use a model with native tool calling and set a large enough context window in Model Configuration.

Try DaoXE — and benchmark it yourself

One key for GPT, Claude, Gemini, DeepSeek and more. Point the open benchmark at us and compare — don't take our word for it.