⌁ Guides

Continue

Add Gondola to Continue's config.yaml for chat, edit, and autocomplete across the full Venice catalog, paid per request in USDC on Base.

Create an API key

Sign in with your Base wallet at /keys and mint a Gondola API key. Keys start with gnd_. It authenticates every request and each call is charged in USDC against your Gondola balance.

Top up USDC on Base once at /wallet. The same balance powers the browser chat and every tool you connect.

Point Continue at Gondola

Continue has no dedicated OpenAI-compatible type, so use provider: openai with an apiBase override. Edit ~/.continue/config.yaml and add one entry per model, with the roles you want each to serve:

~/.continue/config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: Gondola Claude Sonnet 5
    provider: openai
    model: claude-sonnet-5
    apiBase: https://api.gondola-ai.com/v1
    apiKey: gnd_xxxx
    roles:
      - chat
      - edit
      - apply

  - name: Gondola Qwen3 Coder
    provider: openai
    model: qwen3-coder-480b-a35b-instruct-turbo
    apiBase: https://api.gondola-ai.com/v1
    apiKey: gnd_xxxx
    roles:
      - autocomplete

Base URL gotcha

Set apiBase to api.gondola-ai.com/v1 only. Do not append /chat/completions; Continue adds the path itself.

Pick a model

Gondola serves the full Venice catalog. The model value must match the catalog id exactly, so pull the live list:

shell

curl https://api.gondola-ai.com/v1/models

Example ids today include claude-sonnet-5 and qwen3-coder-480b-a35b-instruct-turbo, but always confirm against the live list, since the catalog changes. Each entry also reports context_length and max_completion_tokens if you need them.

Prompt privacy

Gondola never stores prompts or completions: requests are metered, forwarded, and gone when the response finishes, and Venice runs a no-logging model underneath. For zero retention on Venice-controlled infrastructure too, pick a model whose privacy field reads private on GET /v1/models. Details on /privacy.

Notes and troubleshooting

Give autocomplete its own entry

Autocomplete needs a separate model entry with roles: [autocomplete]. Route a coding model to it, not a general chat model: chat models produce poor fill-in-the-middle completions, per Continue's docs.

Cap the price on unattended runs

Continue's agent mode can run many steps unwatched. If your model entry supports a requestOptions.headers field, set x-gondola-max-factor to a value from 0 to 1 to refuse any request priced above that ceiling instead of paying more; omit it and a request with no cheaper capacity can fall through to Gondola's own backup key at Venice list price. For a hard dollar limit rather than a relative one, send x-gondola-max-charge-usd (for example 0.50) and any request whose estimated charge would exceed it is refused with a 402 before anything is billed.

Streaming is implicit, so there is nothing to toggle. If a request returns insufficient balance, top up at /wallet.

Keep going

All setup guides →Cline guide →Cursor guide →Live prices →

Loading page

name: My Config version: 0.0.1 schema: v1 models: - name: Gondola Claude Sonnet 5 provider: openai model: claude-sonnet-5 apiBase: https://api.gondola-ai.com/v1 apiKey: gnd_xxxx roles: - chat - edit - apply - name: Gondola Qwen3 Coder provider: openai model: qwen3-coder-480b-a35b-instruct-turbo apiBase: https://api.gondola-ai.com/v1 apiKey: gnd_xxxx roles: - autocomplete