Claude Sonnet 4.6

anthropic/claude-sonnet-4.6

text, image, document in · text out · 200,000 context · 64,000 max output

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$3.000$15.00$0.300 / $3.750pass-through$10.800———no traffic—ZDR no-train 30 dmodel defaultactive
AWS Bedrockus · none200,000 / 64,000$3.000$15.00$0.300 / $3.750pass-through$10.800———no traffic— no-train 30 d11 differactive
OpenRouterglobal · unknown1,000,000 / 128,000$3.150$15.75$0.315 / $3.938+5.0%$11.340———no traffic— no-train 30 d20 differactive
Anthropic on Vertex AIus · none200,000 / 64,000$3.000$15.00$0.300 / $3.750pass-through$10.800———no traffic— no-train 30 dmodel defaultactive

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-sonnet-4.6","messages":[{"role":"user","content":"Say hello"}]}'
Get a key in the console

Changelog

  • new_model endpoint ep_openrouter_claude-sonnet-4.6_global (anthropic/claude-sonnet-4.6) added as active; price input 3.150 output 15.750 USD/M 10/5/2026