Messages API

AI / ML

Anthropic

Claude model family for conversational AI, analysis, and code generation with extended context windows

Reported Latency

Typical performance from public reports -- not live measurements

Average: 780ms
p50
550ms
p95
2,000ms
p99
4,000ms

Reliability

99.9%observed uptime

Pricing

Free tier

None (credit-based)

Paid starts at

$0.25 / 1M input tokens (Haiku)

Technical Details

Authentication

API Key

Rate limit

1,000 RPM (Tier 1)

Protocols

REST

SDKs

PythonTypeScriptJavaGo

Regions

USEU
DocumentationBase URL

Last updated: 2026-04-12