Microsoft-Decision-1 vs pplx-decider

Microsoft-Decision-1

Microsoft publishes $0.042 per million input tokens, with output free, and the model is callable through Microsoft Foundry and OpenRouter. It is in public preview. No licence, model-specific retention statement, rate limit or deprecation policy was found, and the Foundry route needs an Azure deployment and an Entra token. Latency and accuracy figures are Microsoft's claims.

pplx-decider

The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.

Microsoft-Decision-1

1. Use OpenRouter's Decisions method, not an OpenAI chat-completions SDK. OpenRouter says chat completions SDKs will not work with this model
2. On Foundry, send the request to the deployment's /providers/microsoft/v1/systemone path with a Microsoft Entra token for https://cognitiveservices.azure.com/.default, not an API key
3. Take the deployment name from the Foundry quickstart before the first call. Microsoft says to confirm the route and authentication header, and the pages reviewed do not give the name
4. Keep each request within OpenRouter's 32,768-token context and send only fixed options, since the model is not intended for open-ended generation
5. Measure latency and calibration on your own labelled cases before relying on Microsoft's latency and 'nine times out of 10' statements

pplx-decider

1. Send Authorization: Bearer. A key in x-api-key returns 401 on this endpoint.
2. Set model on every request. A missing or unknown model returns 400, and the guide shows a -latest name rejected.
3. Resize images to 2,048 tiles of 32 by 32 pixels or fewer before sending. Larger images end in a 504 after about a minute.
4. Check the HTTP status before parsing an error. 404 and 405 have empty bodies, 504 can be HTML, and error.code changes type.
5. For the weights, use the repository's autojev code. The card says default causal inference does not reproduce the evaluated setup.