Galileo API 422: Field logits must be an array of floats matching number of classes

TL;DR

So count your classes and make sure every row of logits has exactly that many floats. A 422 means the syntax is fine but the data shape is wrong.

Fix

1. So count your classes and make sure every row of logits has exactly that many floats. Expected: You get the expected result; the problem is gone.

When to use

• You are setting up or using this Galileo API 422 feature.
• The symptom matches: Field logits must be an array of floats matching number of classes.

When NOT to use

• Unrelated Galileo API 422 issues (different feature, different failure).
• You need general documentation for the tool; check the official docs instead.

Compatibility

Reported against Galileo API 422 (mentions 0.3, 0.8, 1.2).

Variant phrasings

Field logits must be an array of floats matching number of classes

Why it happens

POSTing model outputs to the Galileo API returns 422 unprocessable entity: "Field logits must be an array of floats matching number of classes." My payload is valid JSON. What shape does Galileo expect?

Edge cases

• If your error message differs even slightly, this is probably a different issue; search the exact text.
• Behavior can change between releases; the linked source reflects the versions above.
• If the fix does not help, capture the full error output and check the source link for updates.

Source: POSTing model outputs to the Galileo API returns 422 unprocessable entity: "Field logits must be an array of floats matching number of classes." My payload is valid JSON. What shape does Galileo expect?

Verified resolution: A 422 means the syntax is fine but the data shape is wrong. For a classification model, the logits array for every input must have exactly one float per class. The docs example: with 3 classes and label 2, logits of [[1.2, 0.8]] fails because it only has 2 values; [[1.2, 0.8, -0.3]] passes. So count your classes and make sure every row of logits has exactly that many floats. The same idea applies to tokens and labels: the model type you declared determines the required input structure, and every logged row has to match it.

Source URL: https://docs.galileo.ai/references/faqs/errors#galileo-api-errors