Padma
← All models

Claude Haiku 4

FAST

Anthropic · anthropic/claude-haiku-4

Available

Low-latency model for classification, extraction and high-volume request paths where cost per call matters more than depth.

Input / 1M tokens

৳96

Output / 1M tokens

৳480

Context length

200K

Max output

32K

Placeholder rates. Final pricing is published per model before launch.

Suitable for

  • Fast
  • Coding
  • Vision

Example request

cURL
curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-haiku-4",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Performance

Throughput168 tok/s
Time to first token0.5s
StreamingSupported
Tool callingSupported

Measured from Dhaka over the last 24h of prototype traffic.

Routing

Primary routeAnthropic direct
FallbackSecondary region
Prompt retentionNot retained