As traduções são geradas por tradução automática. Em caso de conflito entre o conteúdo da tradução e da versão original em inglês, a versão em inglês prevalecerá.
Se você comprar o Provisioned Throughput por meio da API do Amazon Bedrock, deverá especificar uma variante contextual do Amazon FMs Bedrock para o ID do modelo.
nota
A taxa de transferência provisionada é suportada em AWS GovCloud (Oeste dos EUA) somente para modelos personalizados com uma compra sem compromisso. Use a ID de um modelo personalizado ao comprar o Provisioned Throughput para ele.
A tabela a seguir mostra os modelos para os quais você pode comprar a taxa de transferência provisionada, a ID do modelo a ser usada ao comprar a taxa de transferência provisionada, as regiões nas quais você pode comprar a taxa de transferência provisionada para o modelo e se você pode comprar sem compromisso para o modelo básico.
Nome do modelo | ID do modelo do throughput provisionado | Regiões com suporte | Compra sem compromisso compatível com o modelo de base |
---|---|---|---|
Amazon Nova Lite 300k | amazon.nova-lite-v1:0:300k |
us-east-1 |
Sim |
Amazon Nova Micro 128k | amazon.nova-micro-v1:0:128k |
us-east-1 |
Sim |
Amazon Nova Pro 300k | amazon.nova-pro-v1:0:300k |
us-east-1 |
Sim |
Amazon Titan Embeddings G1 - Text 8k | amazon.titan-embed-text-v1:2:8k |
us-east-1 us-west-2 |
Sim |
Amazon Titan Image Generator G1 v2 | amazon.titan-image-generator-v2:0 |
us-east-1 us-west-2 |
Não |
Amazon Titan Image Generator G1 | amazon.titan-image-generator-v1:0 |
us-east-1 us-west-2 ap-south-1 eu-west-2 |
Não |
Amazon Titan Multimodal Embeddings G1 | amazon.titan-embed-image-v1:0 |
us-east-1 us-west-2 ap-south-1 ap-southeast-2 ca-central-1 eu-central-1 eu-west-1 eu-west-2 eu-west-3 sa-east-1 |
Sim |
Amazon Titan Text G1 - Express 8k | amazon.titan-text-express-v1:0:8k |
us-east-1 us-west-2 ap-south-1 ap-southeast-2 ca-central-1 eu-west-1 eu-west-2 eu-west-3 sa-east-1 |
Sim |
Amazon Titan Text G1 - Lite 4k | amazon.titan-text-lite-v1:0:4k |
us-east-1 us-west-2 ap-south-1 ap-southeast-2 ca-central-1 eu-central-1 eu-west-1 eu-west-2 eu-west-3 sa-east-1 |
Sim |
Anthropic Claude 2 100k | anthropic.claude-v2:0:100k |
us-east-1 us-west-2 |
Sim |
Anthropic Claude 2 18k | anthropic.claude-v2:0:18k |
us-east-1 us-west-2 |
Sim |
Anthropic Claude 2.1 18k | anthropic.claude-v2:1:18k |
us-east-1 us-west-2 ap-northeast-1 eu-central-1 |
Sim |
Anthropic Claude 2.1 200k | anthropic.claude-v2:1:200k |
us-east-1 us-west-2 ap-northeast-1 eu-central-1 |
Sim |
Anthropic Claude 3 Haiku 200k | anthropic.claude-3-haiku-20240307-v1:0:200k |
us-east-1 us-west-2 ap-southeast-2 eu-west-3 |
Sim |
Anthropic Claude 3 Haiku 48k | anthropic.claude-3-haiku-20240307-v1:0:48k |
us-east-1 us-west-2 ap-south-1 ap-southeast-2 eu-west-1 eu-west-3 |
Sim |
Anthropic Claude 3 Opus 12k | anthropic.claude-3-opus-20240229-v1:0:12k |
us-east-1 us-west-2 |
Sim |
Anthropic Claude 3 Opus 200k | anthropic.claude-3-opus-20240229-v1:0:200k |
us-east-1 us-west-2 |
Sim |
Anthropic Claude 3 Opus 28k | anthropic.claude-3-opus-20240229-v1:0:28k |
us-east-1 us-west-2 |
Sim |
Anthropic Claude 3 Sonnet 200k | anthropic.claude-3-sonnet-20240229-v1:0:200k |
us-east-1 us-west-2 ap-northeast-1 ap-northeast-2 ap-southeast-1 ap-southeast-2 eu-west-1 eu-west-3 |
Sim |
Anthropic Claude 3 Sonnet 28k | anthropic.claude-3-sonnet-20240229-v1:0:28k |
us-east-1 us-west-2 ap-northeast-1 ap-northeast-2 ap-south-1 ap-southeast-1 ap-southeast-2 eu-west-1 eu-west-3 |
Sim |
Anthropic Claude 3.5 Sonnet 18k | anthropic.claude-3-5-sonnet-20240620-v1:0:18k |
us-west-2 ap-south-1 ap-southeast-2 |
Sim |
Anthropic Claude 3.5 Sonnet 200k | anthropic.claude-3-5-sonnet-20240620-v1:0:200k |
us-west-2 ap-south-1 ap-southeast-2 |
Sim |
Anthropic Claude 3.5 Sonnet 51k | anthropic.claude-3-5-sonnet-20240620-v1:0:51k |
us-west-2 ap-south-1 ap-southeast-2 |
Sim |
Anthropic Claude 3.5 Sonnet v2 18k | anthropic.claude-3-5-sonnet-20241022-v2:0:18k |
us-west-2 |
Sim |
Anthropic Claude 3.5 Sonnet v2 200k | anthropic.claude-3-5-sonnet-20241022-v2:0:200k |
us-west-2 |
Sim |
Anthropic Claude 3.5 Sonnet v2 51k | anthropic.claude-3-5-sonnet-20241022-v2:0:51k |
us-west-2 |
Sim |
Anthropic Claude Instant 100k | anthropic.claude-instant-v1:2:100k |
us-east-1 us-west-2 |
Sim |
Cohere Command 4k | cohere.command-text-v14:7:4k |
us-east-1 us-west-2 |
Sim |
Cohere Command Light 4k | cohere.command-light-text-v14:7:4k |
us-east-1 us-west-2 |
Sim |
Cohere Embed English | cohere.embed-english-v3:0:512 |
us-east-1 us-west-2 ca-central-1 eu-west-2 eu-west-3 sa-east-1 |
Sim |
Cohere Embed Multilingual | cohere.embed-multilingual-v3:0:512 |
us-east-1 us-west-2 ca-central-1 eu-west-2 eu-west-3 sa-east-1 |
Sim |
Meta Llama 3.1 70B Instruct 128k | meta.llama3-1-70b-instruct-v1:0:128k |
us-east-2 us-west-2 |
Sim |
Meta Llama 3.1 8B Instruct 128k | meta.llama3-1-8b-instruct-v1:0:128k |
us-east-2 us-west-2 |
Sim |
Para saber mais sobre os recursos do Amazon Bedrock com os quais você pode usar throughput provisionado, consulte Usar throughput provisionado com um recurso do Amazon Bedrock.