All AI models · LLM benchmarks · Methodology

claude-3-5-haiku-latest

Fast Claude model for responsive assistance, classification, and lightweight agents

Model facts

Context window
2K tokens
Maximum output
8K tokens
Cheapest paid input
$0.8 per 1M tokens
Cheapest paid output
$4 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

tool calling, attachments, temperature control, text, image, pdf.

Observed price history

  • 2026-08-24: $0.8 input / $4 output per 1M tokens

API providers