Analyze images alongside text for combined policy violations
White Circle can analyze images alongside text content within a session check. This is useful when the combination of text and image matters for policy evaluation — an image alone might be safe, but paired with certain text it could become a violation.
Using Artifacts in Session Checks
Include images in your session check using the artifact content part type. You can either send an image inline or reference a previously checked artifact.
Note that you’re going to be charged for every inline artifact as if it was an independent API call to artifact check.
Inline Image
Send the image directly in the request. White Circle analyzes the image together with the text:
JSON
{
"deployment_id": "your-deployment-id",
"messages": [
{
"role": "user",
"content": [
{
"type": "artifact",
"content": {
"kind": "image",
"url": "https://cdn.example.com/uploads/photo.jpg"
}
},
{
"type": "text",
"text": "What do you think about this image?"
}
]
}
]
}Base64 is also supported:
JSON
{
"type": "artifact",
"content": {
"kind": "image",
"data": "iVBORw0KGgoAAAANSUhEUgAA..."
}
}Reference a Pre-checked Artifact
If you’ve already checked an image via Artifact Check, you can reference it by ID. White Circle uses the existing result and includes the image as context for the text evaluation — without re-checking it. If your entire API request contains only this reference to artifact without any new content at all, you will not be charged.
By internal ID:
JSON
{
"type": "artifact",
"internal_artifact_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
}By external ID:
JSON
{
"type": "artifact",
"external_artifact_id": "my-upload-42"
}Content and ID Combinations
The artifact content part supports different combinations of content, internal_artifact_id, and external_artifact_id:
Combining Text and Images
A single message can contain text and multiple images:
JSON
{
"deployment_id": "your-deployment-id",
"messages": [
{
"role": "user",
"content": [
{
"type": "artifact",
"content": {
"kind": "image",
"url": "https://example.com/photo1.jpg"
}
},
{
"type": "artifact",
"content": {
"kind": "image",
"url": "https://example.com/photo2.jpg"
}
},
{
"type": "text",
"text": "Compare these two photos"
}
]
}
]
}White Circle evaluates the message once, using all provided images as context for text evaluation.
You can also mix inline and referenced artifacts:
JSON
{
"content": [
{
"type": "artifact",
"internal_artifact_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
},
{
"type": "artifact",
"content": {
"kind": "image",
"data": "iVBORw0KGgoAAAANSUhEUgAA..."
},
"external_artifact_id": "new-upload-5"
},
{
"type": "text",
"text": "Combine these two images"
}
]
}Supported Formats
Maximum file size: 20 MB.
Response
Session checks now return an envelope with a session-level result and an artifact list:
JSON
{
"session": {
"flagged": true,
"internal_session_id": "a3e733b5-d6c4-473d-82d4-669c1e757256",
"policies": {
"5a920d64-977b-4b38-8679-d5dbb4e2c0c5": {
"name": "No Explicit Content",
"flagged": true,
"flagged_source": ["image"]
}
}
},
"artifacts": [
{
"flagged": true,
"kind": "image",
"status": "completed",
"internal_artifact_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
}
]
}For the full session envelope shape, see Check Content. Each object in artifacts[] uses the same response shape as Get Artifact Results.
When both text and image contribute to the session-level violation, session.policies.*.flagged_source includes both:
JSON
{
"session": {
"flagged": true,
"internal_session_id": "a3e733b5-d6c4-473d-82d4-669c1e757256",
"policies": {
"a4a91875-1e54-42d7-b9b0-a75dfebeb057": {
"name": "Mixed Content Violation",
"flagged": true,
"flagged_source": ["text", "image"]
}
}
},
"artifacts": [
{
"flagged": true,
"kind": "image",
"status": "completed",
"internal_artifact_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
}
]
}Artifact Entry in artifacts[]
When you send an inline artifact content part, the session response includes the artifact details inside artifacts[]. Each artifact object follows this structure:
JSON
{
"flagged": true,
"policies": {
"4d7543e2-d106-4cac-b0a4-87b27e473813": {
"name": "No Explicit Content",
"flagged": true,
"flagged_source": ["image"]
},
"d54a96f1-ccac-4967-9101-46e68eab415e": {
"name": "No Violence",
"flagged": false,
"flagged_source": []
}
},
"kind": "image",
"status": "completed",
"updated_at": "2026-04-15T10:30:00Z",
"internal_artifact_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"external_artifact_id": "my-upload-42",
"external_session_id": "user-session-123",
"internal_session_id": "a3e733b5-d6c4-473d-82d4-669c1e757256",
"created_at": "2026-04-15T10:30:00Z",
"note": null
}Best Practices
Include text context with images
When moderating images, include any accompanying text. Context matters — an image might be acceptable in one context but violate policies in another.
JSON
{
"content": [
{
"type": "artifact",
"content": {
"kind": "image",
"url": "https://example.com/diagram.png"
}
},
{ "type": "text", "text": "Check out this educational diagram" }
]
}Pre-check then reference for efficiency
For workflows where the same image appears in multiple sessions, check it once via Artifact Check, then reference it by internal_artifact_id in later session checks. White Circle reuses the existing result and includes the image as context for text evaluation.
Moderate AI-generated images
If your application generates images, run them through White Circle before displaying them to users:
JSON
{
"deployment_id": "your-deployment-id",
"messages": [
{ "role": "user", "content": "Generate an image of a sunset" },
{
"role": "assistant",
"content": [
{
"type": "artifact",
"content": {
"kind": "image",
"url": "https://your-ai/generated/abc.png"
}
},
{ "type": "text", "text": "Here's your sunset image:" }
]
}
]
}