Claude 3 Haiku

Anthropic's fastest vision and text model for near-instant responses to basic queries, meant for seamless AI experiences mimicking human interactions.

View model card in Model Garden

Model ID claude-3-haiku@20240307
Launch stage GA
Supported inputs & outputs
  • Inputs:
    Text, Code, Images
  • Outputs:
    Text
Token limits
  • Maximum input tokens: 200,000
  • Maximum output tokens: 8,000
Capabilities
Usage types
Technical specifications
Images
  • Limitation and specifications: See Vision in Anthropic's documentation
Documents
  • Limitation and specifications: See PDF support in Anthropic's documentation
Knowledge cutoff date August 2023
Versions
  • claude-3-haiku@20240307
    • Launch stage: Generally available
    • Release date: March 19, 2024
Supported regions

Model availability

(Includes fixed quota & Provisioned Throughput)
  • United States
    • us-east5
  • Europe
    • europe-west1
  • Asia pacific
    • asia-southeast1

ML processing
  • United States
    • Multi-region
  • Europe
    • Multi-region
  • Asia pacific
    • asia-southeast1
Quota limits

us-east5:

  • QPM: 245
  • TPM: 600,000 (input and output)
  • Context length: 200,000

europe-west1:

  • QPM: 75
  • TPM: 181,000 (input and output)
  • Context length: 200,000

asia-southeast1:

  • QPM: 70
  • TPM: 174,000 (input and output)
  • Context length: 200,000
Pricing See Pricing.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025年11月07日 UTC.