⌁ Guides

OpenCode

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 OpenCode at Gondola

Add a Gondola provider to your OpenCode config: either the global ~/.config/opencode/opencode.json or a repo-root opencode.json (settings merge key by key). Use the OpenAI-compatible provider package and read the key from an environment variable:

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "gondola": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Gondola",
      "options": {
        "baseURL": "https://api.gondola-ai.com/v1",
        "apiKey": "{env:GONDOLA_API_KEY}"
      },
      "models": {
        "claude-sonnet-5": {
          "name": "Claude Sonnet 5",
          "limit": { "context": 1000000, "output": 32768 }
        }
      }
    }
  },
  "model": "gondola/claude-sonnet-5"
}

Export the key and launch OpenCode on a Gondola model:

shell

export GONDOLA_API_KEY=gnd_xxxx
opencode -m gondola/claude-sonnet-5

Base URL gotcha

The baseURL is api.gondola-ai.com/v1 only. Do not append /chat/completions; the provider adds the path itself.

Pick a model

Gondola serves the full Venice catalog. Each model needs its own entry under models keyed by the exact id, and you reference it as gondola/<id>. Pull the live list:

shell

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

Each entry includes context_length and max_completion_tokens. Copy those into limit.context and limit.output so OpenCode budgets the conversation correctly. The published numbers are the limits the gateway actually enforces, so copying them is always safe.

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

Cost readout shows $0.00

OpenCode's spend tracker reads a provider's own pricing metadata, which custom providers do not supply, so it shows $0.00. This is cosmetic. Your real usage and balance live at /keys and /wallet.

Cap the price on unattended runs

OpenCode agents can run many steps unwatched. If the provider's options block lets you add a custom request header, 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.

If the TUI model picker does not list your custom models, select them with the -m gondola/<id> flag (or the /model command) instead. If a request returns insufficient balance, top up at /wallet.

Keep going

All setup guides →OpenClaw guide →Aider guide →Live prices →

Loading page

{ "$schema": "https://opencode.ai/config.json", "provider": { "gondola": { "npm": "@ai-sdk/openai-compatible", "name": "Gondola", "options": { "baseURL": "https://api.gondola-ai.com/v1", "apiKey": "{env:GONDOLA_API_KEY}" }, "models": { "claude-sonnet-5": { "name": "Claude Sonnet 5", "limit": { "context": 1000000, "output": 32768 } } } } }, "model": "gondola/claude-sonnet-5" }