Padma
← All models

Claude Haiku 5.5

NEWFASTCHEAP

Anthropic · anthropic/claude-haiku-5.5

Coming soon

Fastest current Claude model, for classification, extraction, routing and subagent work. Prompts over 100K tokens cost five times as much.

Not callable yet: Padma has not connected Anthropic on this server. The price is real; requests answer 503 model_unavailable, and are not charged, until it is.

Input / 1M tokens

৳12.30

Output / 1M tokens

৳61.51

Cached input / 1M

৳1.23

Context length

1M

Max output

128K

Provider list price: $0.10 in · $0.50 out per 1M tokens (Anthropic), × ৳123.01 per dollar. No markup. A prompt over 100K tokens is billed at ৳61.51 in · ৳307.53 out per 1M for the whole request — the provider's own long-context price.

Suitable for

  • Fast
  • Low Cost
  • Coding
  • Vision
  • Bangla

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-5.5",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Performance

Throughput190 tok/s
Time to first token0.4s
StreamingSupported
Tool callingSupported

Typical figures for this model, which the auto/* routers score on — not a guarantee for any one request.

Routing

Primary routeAnthropic direct
Fallback hostsNone — one host
Prompt retentionPadma keeps none unless you turn on payload logging; the provider's own API terms apply