Claude Haiku 4.5

anthropic/claude-haiku-4.5

text, image, document in · text out · 200,000 context · 64,000 max output · uptime 100.00% · TTFT 869 ms

toolsschemavisionreasoningcacheZDRno-train
Effective cost per 1k requests

cost = p_in·(input − cached) + p_cache_read·cached + p_out·output + p_req; cached tokens are the prefix a sticky endpoint already holds (part2b §9.3), which is why the cheapest list price is not always the cheapest request.

ProviderRegion · quantContext / max outInput / MOutput / MCache read / writeMarkupPer 1k reqUptime 30 dTTFT p50 / p95ThroughputLast 24 hFidelityDataCapabilitiesStatus
Anthropicus · none200,000 / 64,000$1.000$5.000$0.100 / $1.250pass-through$3.600———no traffic—ZDR no-train 30 dmodel defaultactive
OpenRouterglobal · unknown200,000 / 64,000$1.050$5.250$0.105 / $1.313+5.0%$3.780100.00%869 / 1243 ms235 tok/s100.00% · 869 ms · 235 tok/s— no-train 30 d18 differactive

Quick start

curl https://api.ai.ml/v1/chat/completions \
  -H "Authorization: Bearer $AIML_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-haiku-4.5","messages":[{"role":"user","content":"Say hello"}]}'
Get a key in the console

Changelog

  • new_model endpoint ep_openrouter_claude-haiku-4.5_global (anthropic/claude-haiku-4.5) added as active; price input 1.050 output 5.250 USD/M 10/5/2026