Try Bifrost Enterprise free for 14 days. Explore now
API Reference
- POSTConverse with model (Bedrock format)
- POSTStream converse with model (Bedrock format)
- POSTInvoke model (Bedrock format)
- POSTInvoke model with streaming (Bedrock format)
- POSTCount tokens (Bedrock format)
- POSTCreate batch inference job (Bedrock format)
- GETList batch inference jobs (Bedrock format)
- GETRetrieve batch inference job (Bedrock format)
- POSTCancel batch inference job (Bedrock format)
- GETS3-compatible ListObjectsV2
- GETS3-compatible GetObject
- PUTS3-compatible PutObject
- DELS3-compatible DeleteObject
- HEADS3-compatible HeadObject
Error
A valid request URL is required to generate request examples{
"inputTokens": 123
}Bedrock Integration
Count tokens (Bedrock format)
Counts tokens for a Converse-style request using AWS Bedrock format.
The request body must include input.converse with a complete Converse
payload; only Converse-shaped input is supported.
POST
/
bedrock
/
model
/
{modelId}
/
count-tokens
Error
A valid request URL is required to generate request examples{
"inputTokens": 123
}Documentation Index
Fetch the complete documentation index at: https://docs.getbifrost.ai/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
BearerAuthBasicAuthVirtualKeyAuthApiKeyAuth
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
Bedrock model identifier (e.g. anthropic.claude-3-5-sonnet-20240620-v1:0).
Body
application/json
Show child attributes
Show child attributes
Response
Successful response
Number of input tokens that would be billed for this request.
Was this page helpful?
⌘I
Assistant
Responses are generated using AI and may contain mistakes.