Skip to main content
Use https://www.aguasto.com as the base URL. The public research endpoints accept anonymous requests. They read published information and calculate estimates. Use the Console for customer GPU requests.

Operations

The live OpenAPI document defines request fields and response schemas. You can also use the public website playground.

Search for references

Search matches published titles and descriptions. Follow each result’s canonical URL to read the full evidence. For streamed results, include "streaming":true inside prefer.

Read catalog pages

Use pagination.next_offset until it is null. For a batch request, send paths such as /gpus and /models. Results preserve your input order. An unknown path gets a per-item 404 while valid items still return.

Run a calculation

The example estimates weight memory from the parameter count and bit width. Plan separately for the runtime, activations, and cache. Calculation outputs are educational estimates.

Handle errors and limits

REST failures return error.code and error.message. Check the request on a 400 or 422. On 429, wait for Retry-After before retrying. The API also returns rate-limit headers. Instance-level limits are best effort. NLWeb and MCP use their respective error formats. Use testing and versioning for CI fixtures and retry guidance.