Build your Universal Compute Income
The first shared compute pool on Venice. Lend your idle capacity & earn daily yield on compute that would otherwise vanish at epoch reset.
Two sides, one pool
Idle compute meets unmet demand. Everyone wins.
Earn on idle compute
Your staked DIEM generates $1/day of inference credit per token. If you're not using all of it, that capacity vanishes at epoch reset. Gondola puts it to work and pays you for it.
- Connect wallet, key is generated automatically
- Set your daily reserve — keep as much as you need
- Earn proportional daily payouts
Cheap uncensored inference
Access Venice's full model library through a single endpoint. No staking required, no VVV needed. Just inference — private, uncensored, and below market rate.
- Drop-in API replacement — same format as OpenAI
- Zero data retention — Venice & Gondola never logs anything
- Pay per request in USDC, using x402
const res = await fetch("https://api.gondola.so/v1/chat/completions", {
method: "POST",
headers: {
"Content-Type": "application/json",
"Authorization": "Bearer " + GONDOLA_KEY,
},
body: JSON.stringify({
model: "llama-3.3-70b",
messages: [{ role: "user", content: "Hello" }],
}),
})Trust the architecture, not us
Inference-only keys
Contributors share keys that can only run inference — no account access, no billing, no key management.
Venice enforces limits
Per-key epoch consumption caps are set at Venice's level. We literally cannot overdraw a contributor's allocation.
Zero data retention
Venice never stores prompts or responses. Contributors can't see consumer requests. Nobody can.
Stop wasting your inference credits
Build your universal compute income