Aider

1. Get a SupaNexus API key

Sign in to the Developer Console, open your project → API Keys, create a key, and copy the secret immediately (shown once). One project key works across OpenAI-compatible and Anthropic-compatible clients.

2. Install Aider

Install Aider in a virtualenv or with pipx, then confirm aider --version.

python -m pip install aider-chat
# or: pipx install aider-chat
aider --version

3. Export OpenAI-compatible environment

Point OPENAI_API_BASE at SupaNexus /v1 and set OPENAI_API_KEY. Persist in your shell profile for daily use, or export only in the current session for a quick test.

export OPENAI_API_BASE="<BASE_URL>/v1"
export OPENAI_API_KEY="sk-snx-..."

4. Optional: project .aider.conf.yml

Commit non-secret defaults in the repo and keep the key in the environment or a local untracked override.

# .aider.conf.yml
openai-api-base: <BASE_URL>/v1
model: openai/deepseek/deepseek-chat

5. Pick a catalog model ID

Use exact IDs from the SupaNexus Models marketplace or GET /v1/models (for example deepseek/deepseek-chat, anthropic/claude-3-5-sonnet). Do not invent vendor-only slugs from other gateways.

6. Start Aider with a catalog model

Prefix the SupaNexus model id with openai/ so Aider uses the OpenAI-compatible client. Add files with /add, then ask for a small change and confirm a commit suggestion appears.

cd /path/to/your/project
aider --model openai/deepseek/deepseek-chat

7. Troubleshooting

Aider still hits api.openai.com: OPENAI_API_BASE not exported in that shell. 404 on chat/completions: base must end with /v1. Unknown model: drop the openai/ prefix only in the catalog lookup — keep it on the CLI --model flag as openai/{model-id}.