Claude Sonnet 4.6 (mock)

anthropic/claude-sonnet-4.6

text, image in · text out · 200,000 context · 64,000 max output · uptime 100.00% · TTFT 120 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 / p95FidelityDataCapabilitiesStatus
Mock (AWS Bedrock Converse)us · none200,000 / 64,000$3.600$18.00$0.360 / pass-through$12.960 no-train model defaultactive
Mock (Anthropic dialect)us · none200,000 / 64,000$3.000$15.00$0.300 / $3.750pass-through$10.800100.00%120 / 120 msZDR no-train 9 differactive
Mock (Anthropic on Vertex AI)us · none200,000 / 64,000$3.300$16.50$0.330 / $4.125pass-through$11.880 no-train 9 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-sonnet-4.6","messages":[{"role":"user","content":"Say hello"}]}'
Get a key in the console

Changelog

  • No changes recorded.