Algorand APIs.
Start free. Scale when you need to.

AI models on Unlimited and Enterprise. Nodely-hosted, OpenAI-compatible models with your endpoint token: text embeddings, image and text embeddings, and a 125B-parameter chat model with built-in web search and page reading. No token quota: each endpoint has an hourly budget per model, refilled continuously, with a burst and an in-flight limit. Unlimited and Enterprise, per endpoint: text embeddings 10,000 req/h (3,000,000 input tokens/h), burst 600/min, 4 in flight; image and text embeddings 2,000 req/h, burst 120/min, 2 in flight; chat 300 req/h (1,500,000 input, 300,000 output tokens/h), burst 30/min, 2 in flight, 256k context.

AI add-ons. Boost: AI 125B-A6B, no quota ($16 / month): every model at the Unlimited limits. Unlimited and Enterprise: AI Throughput ×2 ($16 / month, limited availability): twice the hourly budgets and burst of the embedding models, chat excluded.

Web tools. Web search and page reading are built into the chat model and covered by fair use. An endpoint that searches or reads far more than usual may find them unavailable for a while; the request still gets an answer.

Fair use. There is no token quota: each endpoint has per-model hourly budgets, a burst limit and an in-flight limit instead. Use the models for your own products and workloads. Reselling raw model access, bulk dataset generation (for example to train other models) and abuse are not allowed. Built-in web search and page reading are fair use and are for answering requests, not for crawling sites or collecting data in bulk: pages are condensed to their main text and robots.txt is respected. For bulk search or scraping use the x402 search and scrape APIs. The models run on shared GPUs. Nodely may throttle endpoints whose traffic is far above other customers'; we contact you first when we can. The gateway logs each request's endpoint, model, status, timing and token counts, not its prompts or outputs. Models, their versions and the limits may change; the model names stay stable.

Add-ons are billed monthly with the Boost subscription and can be changed or removed in the portal by organization admins.

IPFS gateway traffic of Boost sites counts toward the Boost daily quota.

Pinning: Hard cap with no overage billing, no pay-as-you-go. One pinning size at a time: switch up or down in the portal. Without an add-on, Boost includes 100 MB / 25 files free. Every pinning quota also caps the number of pinned files: 1 file per 4 MB of quota, per organization.

* Prices are net: + 23 % VAT for buyers in Poland and EU consumers; no VAT for EU businesses with a valid VAT ID (reverse charge) and outside the EU.