Console

Home / Agents / Continue

Continue

Open-source AI code assistant for IDE and CLI

Continue OpenAI-compatible VS CodeJetBrainsCLI
Official install page All tools

Continue is an open-source AI code assistant that adds chat, autocomplete and edit to your IDE (VS Code / JetBrains), plus a terminal CLI (cn). Models are configured in config.yaml and can point at any OpenAI-compatible endpoint — a fit for teams routing their IDE assistant through their own model gateway.

Base URL (root)https://quantoport.comPut this in each tool's base_url or *_BASE_URL setting.
OpenAI-compatible pathhttps://quantoport.com/v1Append /v1 for anything speaking the OpenAI wire (/v1/chat/completions).
Recommended modelsdeepseek-v4.1-flashclaude-sonnet-5glm-5.3Names published in our own catalogue — confirm the live list for your key with GET /v1/models.

Skip it — one-line setup

The script installs Continue from its official source, writes the gateway settings into the tool's own config file (backing up any existing one) and runs a live check. It asks for your gateway key, or take it from --key / --key-file. --uninstall restores exactly what it wrote.

shell
curl -fsSL https://quantoport.com/agents/continue/setup | bash

1 · Install

Install Continue from its own official source.

install
Install the "Continue" extension from your IDE marketplace; CLI: curl -fsSL https://raw.githubusercontent.com/continuedev/continue/main/extensions/cli/scripts/install.sh | bash (or npm i -g @continuedev/cli)

2 · Configure — point it at QuantoPort

Gateway base URL https://quantoport.com; get your key from the console.

config
Add the model to config.yaml (global ~/.continue/ or workspace .continue/):

name: quantoport
version: 1.0.0
schema: v1
models:
  - name: quantoport
    provider: openai
    model: <model-id>
    apiBase: https://quantoport.com/v1
    apiKey: YOUR_API_KEY
    roles: [chat, edit, apply]

On the China endpoint set apiBase to https://api.shinlinkai.com/v1 (OpenAI wire only). Point the CLI at that config with cn --config <path>.

3 · Verify

One request proves you are on our channel.

verify
cn -p "reply with OK"      # or send a message in the IDE chat

4 · Common pitfalls

  • For an OpenAI-compatible endpoint use provider: openai together with apiBase — do not switch to a different provider name.
  • apiBase must include /v1.
  • gpt-5 / o-series default to the /responses endpoint; if the gateway does not support it, add useResponsesApi: false on that model to force /chat/completions.
  • In headless/CI environments the CLI authenticates with the CONTINUE_API_KEY environment variable, used with cn -p.

Sources for the tool-side steps: docs.continue.dev/customize/model-providers/top-level/openai docs.continue.dev/reference docs.continue.dev/cli/quickstart