Converse with model (Bedrock format)
Sends messages to a model using AWS Bedrock Converse API format.
AuthorizationBearer <token>
Bearer token authentication. Use your MPilot virtual-key JWT or admin JWT.
Virtual keys (prefixed with sk-bf-) can also be passed here.
In: header
Path Parameters
modelIdstring
Model ID (e.g., anthropic.claude-3-sonnet-20240229-v1:0)
messages?array<BedrockMessage>
Array of messages for the conversation
system?array<object>
System messages/prompts
inferenceConfig?object
toolConfig?object
guardrailConfig?object
additionalModelRequestFields?object
Model-specific parameters
Empty Object
additionalModelResponseFieldPaths?array<string>
performanceConfig?object
promptVariables?object
Empty Object
requestMetadata?object
Empty Object
serviceTier?object
fallbacks?array<string>
Response Body
curl -X POST "https://loading/{AI_GATEWAY_URL}/bedrock/model/string/converse" \ -H "Content-Type: application/json" \ -d '{}'{
"output": {
"message": {
"role": "user",
"content": [
{
"text": "string",
"image": {
"format": "jpeg",
"source": {
"bytes": "string"
}
},
"document": {
"format": "pdf",
"name": "string",
"source": {
"bytes": "string",
"text": "string"
}
},
"toolUse": {
"toolUseId": "string",
"name": "string",
"input": {}
},
"toolResult": {
"toolUseId": "string",
"content": [
{
"text": "string",
"image": {
"format": "jpeg",
"source": {
"bytes": "string"
}
},
"document": {
"format": "pdf",
"name": "string",
"source": {
"bytes": "string",
"text": "string"
}
},
"toolUse": {
"toolUseId": "string",
"name": "string",
"input": {}
},
"toolResult": {},
"guardContent": {
"text": {
"text": "string",
"qualifiers": [
"string"
]
}
},
"reasoningContent": {
"reasoningText": {
"text": "string",
"signature": "string"
}
},
"json": {},
"cachePoint": {
"type": "default"
}
}
],
"status": "success"
},
"guardContent": {
"text": {
"text": "string",
"qualifiers": [
"string"
]
}
},
"reasoningContent": {
"reasoningText": {
"text": "string",
"signature": "string"
}
},
"json": {},
"cachePoint": {
"type": "default"
}
}
]
}
},
"stopReason": "end_turn",
"usage": {
"inputTokens": 0,
"outputTokens": 0,
"totalTokens": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokens": 0
},
"metrics": {
"latencyMs": 0
},
"additionalModelResponseFields": {},
"trace": {},
"performanceConfig": {
"latency": "standard"
},
"serviceTier": {
"type": "reserved"
}
}{
"message": "string",
"type": "string"
}{
"message": "string",
"type": "string"
}