Skip to main content
POST
/
litellm
/
bedrock
/
model
/
{modelId}
/
converse
Error
A valid request URL is required to generate request examples
{
  "output": {
    "message": {
      "content": [
        {
          "text": "<string>",
          "image": {
            "source": {
              "bytes": "aSDinaTvuI8gbWludGxpZnk="
            }
          },
          "document": {
            "name": "<string>",
            "source": {
              "bytes": "aSDinaTvuI8gbWludGxpZnk=",
              "text": "<string>"
            }
          },
          "toolUse": {
            "toolUseId": "<string>",
            "name": "<string>",
            "input": {}
          },
          "toolResult": {
            "toolUseId": "<string>",
            "content": "<array>"
          },
          "guardContent": {
            "text": {
              "text": "<string>",
              "qualifiers": [
                "<string>"
              ]
            }
          },
          "reasoningContent": {
            "reasoningText": {
              "text": "<string>",
              "signature": "<string>"
            }
          },
          "json": {},
          "cachePoint": {}
        }
      ]
    }
  },
  "usage": {
    "inputTokens": 123,
    "outputTokens": 123,
    "totalTokens": 123,
    "cacheReadInputTokens": 123,
    "cacheWriteInputTokens": 123
  },
  "metrics": {
    "latencyMs": 123
  },
  "additionalModelResponseFields": {},
  "trace": {},
  "performanceConfig": {},
  "serviceTier": {}
}

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with sk-bf-) can also be passed here.

Path Parameters

​
modelId
string
required

Model ID

Body

application/json
​
messages
object[]

Array of messages for the conversation

​
system
object[]

System messages/prompts

​
inferenceConfig
object
​
toolConfig
object
​
guardrailConfig
object
​
additionalModelRequestFields
object

Model-specific parameters

​
additionalModelResponseFieldPaths
string[]
​
performanceConfig
object
​
promptVariables
object
​
requestMetadata
object
​
serviceTier
object
​
fallbacks
string[]

Response

Successful response

​
output
object
​
stopReason
enum<string>
Available options:
end_turn,
tool_use,
max_tokens,
stop_sequence,
guardrail_intervened,
content_filtered
​
usage
object
​
metrics
object
​
additionalModelResponseFields
object
​
trace
object
​
performanceConfig
object
​
serviceTier
object