Does AWS Bedrock's provisioned throughput increase claude's API request rate limits?

0

The docs from anthropic claude mention default API request rate limits per organization:

Our rate limits are currently measured in number of concurrent requests across your organization, and will default to 1 while you’re evaluating the API. This means that your organization can make at most 1 request at a time to our API. If you exceed the rate limit you will get a 429 error. Once you’re ready to go live we’ll discuss the appropriate rate limit with you.

  • Does Bedrock's provisioned throughput increase the claude's default API request rate limits?
  • If so, does provisioned 10 MU means at most you can make 10 requests at a time?
preguntada hace 7 meses3038 visualizaciones
1 Respuesta
1
Respuesta aceptada

Hello, The Amazon Bedrock service is using an AWS managed deployment of the Anthropic Claude model which is not the same as when using Anthropic's API directly. As such, different limits apply to these services. Specifically for Bedrock Claude the current limit on demand is 400/100 requests per minute for the instant/claudev2 models respectively. Using Provisioned Throughput you can achieve higher rate limits. For more details on this please see: https://docs.aws.amazon.com/bedrock/latest/userguide/quotas.html

AWS
respondido hace 7 meses

No has iniciado sesión. Iniciar sesión para publicar una respuesta.

Una buena respuesta responde claramente a la pregunta, proporciona comentarios constructivos y fomenta el crecimiento profesional en la persona que hace la pregunta.

Pautas para responder preguntas