Gondolabeta
⌁ Guides

Zot

Add Gondola as a custom provider in Zot's models.json and run any Venice model from the single-binary Go agent, paid per request in USDC on Base.

1

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.

2

Add Gondola to models.json

Zot reads custom providers from a models.json file in $ZOT_HOME (defaults to %LOCALAPPDATA%\zot on Windows, ~/Library/Application Support/zot on macOS, ~/.local/state/zot on Linux). A top-level key that isn't a built-in provider id defines a custom one:

$ZOT_HOME/models.json
{
  "providers": {
    "gondola": {
      "baseUrl": "https://api.gondola-ai.com/v1",
      "api": "openai",
      "models": [
        {
          "id": "claude-sonnet-5",
          "name": "Claude Sonnet 5",
          "contextWindow": 1000000,
          "maxTokens": 64000
        },
        {
          "id": "qwen3-coder-480b-a35b-instruct-turbo",
          "name": "Qwen3 Coder 480B",
          "contextWindow": 256000,
          "maxTokens": 65536
        }
      ]
    }
  }
}

Custom-provider keys are never stored in models.json. Zot derives an env var from the provider id, upper snake case, so gondola reads GONDOLA_API_KEY. Export it and launch:

shell
export GONDOLA_API_KEY=gnd_xxxx
zot --provider gondola --model claude-sonnet-5
Other ways to supply the key
The env var isn't the only path: run zot and type /login to paste the key interactively (Zot picks it up on the gondola provider once it appears in the picker), or pass --api-key on the command line for a one-off run. Because Gondola exposes a live /models endpoint, Zot verifies the key against it up front rather than waiting for the first failed call, which is not true of every self-hosted gateway.
3

Pick a model

The block above lists claude-sonnet-5 (general agent work) and qwen3-coder-480b-a35b-instruct-turbo (coding specialist). Switch models any time with /model inside the TUI, or --model <id> on the command line. Add any other catalog id the same way; copy context_length and max_completion_tokens into contextWindow and maxTokens:

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

Entries you add show source: user and take precedence over anything with the same id from live discovery:

shell
zot --list-models
4

Notes and troubleshooting

Cap spend at the key, not the request
Zot's provider schema has no field for custom request headers today, so x-gondola-max-factor and x-gondola-max-charge-usd aren't reachable from models.json. For unattended runs, cap spend at the source instead: mint a dedicated key with a spend limit at /wallet?tab=keys, editable any time.

If a request returns insufficient balance, top up at /wallet. The model catalog above is live, so a model added to Venice today is callable from Gondola the same day.

Keep going
All setup guides →OpenHarness guide →Ante guide →Live prices →