Anthropic
Anthropic's fastest and cheapest small model.
Knowledge cutoff Jun 2026. Adaptive thinking is on by default and can be turned off; effort is low, medium or high. Standard pricing applies to prompts up to 100K tokens and rises fivefold above that. Cached input $0.01/M.
Latency
0.6s
Context
1M
Input
$0.10/M
Output
$0.50/M
{
"model": "claude-haiku-5-5",
"messages": [
{
"role": "user",
"content": "Hello, world."
}
]
}