Question:
The answer reached the limit of 400 tokens and is cut.
Sandboxes, in private preview: isolated microVMs for AI agents, compatible with the E2B SDKs.Read more
Orionorion-plusReads imagesAn Orion model, from Serenity’s own family. The efficient tier of the Orion family: economical for large volumes.
Orionorion-proReads imagesAn Orion model, from Serenity’s own family. The top tier of the Orion family, for demanding tasks.Pick an image and ask about it. The model receives the image and your question in one request and answers in text, from what the image shows. Orion Plus and Orion Pro are Orion models, from Serenity’s own family; you choose which one answers.
Live: this demo makes real calls to the API, with a demo key and a limit of calls per visit.
Pick a model and an image, then ask one of the suggested questions or your own. The model answers from the image alone, in at most 400 tokens.
No image chosen yet.
PNG or JPEG. Your browser scales it down to 1,600 pixels on its longer side and sends at most 1 MB.
Do not upload personal or sensitive data. The image is sent to the Serenity Edge API to answer and is not stored by the website.
No image chosen yet.
Ask a question to see the answer here.
Question:
The answer reached the limit of 400 tokens and is cut.
With the local simulation, no cost or milliseconds.
Next: A sandbox reads today’s webThe cost and the milliseconds appear with the first call.
Milliseconds of each call
In this preview nothing is sent to the API, so there is no cost or milliseconds to measure.
One request per question to POST /v1/chat/completions: fixed instructions as the system message, then the image and the question, with an answer of at most 400 tokens and reasoning off.
POST /v1/chat/completionsorion-plusThe server adds the API key, which never reaches your browser.
In the cURL, the image is a placeholder: replace it with the data URL of your PNG or JPEG image.
Request
API response
The same route reads scanned documents and answers questions about images, from your own code.