QuantCDN AI Inference API is one of 38 APIs that QuantCDN publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include AI Inference. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, and a getting-started guide.
This API exposes
6 operations
across 6 paths,
and defines 54 schemas.
It is described by OpenAPI 3.0.0, at version 4.15.8.
Requests are made against 2 base URLs: https://dashboard.quantcdn.io, https://dash.quantgov.cloud.
The identity and technical contract details declared by the specification.
chatInference_request_toolConfig
object
Function calling configuration (Claude 3+, Nova Pro)
3 properties
imageGeneration_request_colorGuidedGenerationParams
object
Parameters for COLORGUIDEDGENERATION task
4 properties
chatInference_200_response
object
5 properties
getDurableExecutionStatus_200_response_error
object
Present when status is failed
2 properties
embeddings_200_response_embeddings
Vector embeddings for the input text(s). Single array for string input, array of arrays for batch input.
imageGeneration_200_response
object
3 properties
1 required
imageGeneration_request_imageVariationParams
object
Parameters for IMAGEVARIATION task
4 properties
chatInferenceStream_request_messages_inner_content
chatInference_request_messages_inner
object
2 properties
2 required
chatInference_request_messages_inner_content_oneOf_inner
chatInference_request_messages_inner_content_oneOf_inner_oneOf_2_video
object
2 properties
2 required
chatInference_request_messages_inner_content_oneOf_inner_oneOf_3_document_source
object
1 property
1 required
chatInference_request_toolConfig_tools_inner_toolSpec
object
3 properties
chatInference_request_messages_inner_content_oneOf_inner_oneOf_2_video_source
object
1 property
1 required
getDurableExecutionStatus_200_response_result
object
Present when status is complete
3 properties
imageGeneration_request_textToImageParams
object
Parameters for TEXTIMAGE task
6 properties
imageGeneration_request
object
11 properties
1 required
chatInference_request_messages_inner_content_oneOf_inner_oneOf_1_image
object
2 properties
2 required
getDurableExecutionStatus_200_response_result_usage
object
Token usage and cost for the final synthesis turn
4 properties
getDurableExecutionStatus_200_response
object
8 properties
chatInference_request_messages_inner_content
chatInference_request_messages_inner_content_oneOf_inner_oneOf_3
object
1 property
1 required
chatInference_request_messages_inner_content_oneOf_inner_oneOf
object
1 property
1 required
chatInferenceStream_request
object
14 properties
2 required
imageGeneration_request_imageGenerationConfig
object
General image generation configuration
6 properties
embeddings_200_response_usage
object
2 properties
2 required
chatInference_request_guardrails
object
AWS Bedrock guardrails configuration for content filtering and safety.
3 properties
chatInference_request_toolConfig_tools_inner_toolSpec_inputSchema
object
1 property
embeddings_200_response
object
4 properties
4 required
chatInference_request_messages_inner_content_oneOf_inner_oneOf_1_image_source
object
1 property
1 required
embeddings_request
object
4 properties
1 required
chatInference_request
object
15 properties
2 required
chatInference_200_response_response_toolUse
Tool use request(s). Can be a single object or array of objects. Only present when AI requests tools.
chatInference_202_response
object
5 properties
3 required
submitToolCallback_request
object
2 properties
2 required
chatInference_request_messages_inner_content_oneOf_inner_oneOf_3_document
object
3 properties
3 required
chatInference_200_response_response_toolUse_oneOf
object
Single tool request
6 properties
chatInference_200_response_response_toolUse_oneOf_1_inner
object
6 properties
chatInference_request_responseFormat
object
Structured JSON output (Claude 3.5 Sonnet v1/v2, Nova Pro)
2 properties
imageGeneration_request_inPaintingParams
object
Parameters for INPAINTING task
5 properties
chatInference_200_response_usage
object
Token usage and cost for this inference call
4 properties
chatInference_request_toolConfig_tools_inner
object
1 property
getDurableExecutionStatus_200_response_result_response
object
2 properties
chatInference_request_messages_inner_content_oneOf_inner_oneOf_1
object
1 property
1 required
imageGeneration_request_backgroundRemovalParams
object
Parameters for BACKGROUNDREMOVAL task
1 property
imageGeneration_request_outPaintingParams
object
Parameters for OUTPAINTING task
6 properties
chatInference_200_response_response
object
Assistant's response message. May contain text content and/or tool use requests.
3 properties
chatInferenceStream_request_messages_inner
object
2 properties
2 required
submitToolCallback_request_toolResults_inner
object
2 properties
2 required
embeddings_request_input
Single text string or array of text strings to embed
chatInference_request_messages_inner_content_oneOf_inner_oneOf_2
object
1 property
1 required
chatInference_200_response_response_toolUse_oneOf_result
object
Tool execution result (only present when status='complete' for sync auto-executed tools). For async tools, poll /tools/executions/{executionId}
2 properties
submitToolCallback_200_response
object
3 properties
getDurableExecutionStatus_200_response_pendingTools_inner
object
3 properties
The full machine-readable OpenAPI contract behind this narrative.
Other APIs QuantCDN publishes across the network.
