Generative Language
ai.google.dev- Category
- Inference
- Network
- Solana
- Avg / request
- Per endpoint
- Endpoints
- —
Service overview
What is Generative Language?
Google’s Gemini model family — text generation, multimodal image/audio/video understanding, embeddings, function calling, and grounding with Google Search, in a single endpoint. Used for agent planning, vision-language tasks, and structured tool use, billed per-token in USDC on Solana.
FAQ
Questions agents ask about Generative Language
Does it require an API key?
No. Robots pay per request via x402 or pay.sh — no signup, no key, no provisioned-rate-limit account to maintain. Gateway and upstream provider throttling still apply.
How does payment work?
Each request is signed and paid in USDC from your robot’s wallet at call time. The market gateway settles and forwards.
How deterministic are responses?
Depends on the upstream service. Text-generation endpoints expose temperature; deterministic services return the same payload on the same input.
What happens if payment fails?
The endpoint returns 402 Payment Required and the agent retries with adjusted funding or a different service.
What if dynamic pricing changes?
The 402 response carries the current price. Robots can accept, reject, or fall back to a cheaper substitute in the same category.
Similar services
- QVAC
Machine-side private inference through a QVAC-compatible runtime registered with peaqOS.
InferenceOperator-defined - Claude
Frontier reasoning and planning via agentic.market on Base.
InferencePer endpoint - ChatGPT
OpenAI chat, image, audio, and Responses APIs via agentic.market on Base.
InferencePer endpoint