Anthropic

Claude Sonnet 4

200K ctxTextImage Tools Reasoning

Released May 22, 2025 · 118B tokens this week · 3 providers

Overview

A mid-2025 Sonnet with strong coding and reasoning across a large context window. A reasonable step down from 4.5 when you want an older, well-characterised behaviour. Still perfectly capable for most assistant workloads.

programmingreasoningacademia

Providers

Reference data — not yet measured from live traffic

PROVIDERMAX OUTOUTPUT /MQUANT
AnthropicCheapest
200K64K$3.00$15.00239ms8099.90%Full
Amazon Bedrock
200K64K$3.12$15.60900ms6899.78%Full
Google Vertex AI
200K64K$3.15$15.75870ms7099.72%Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

GPT-5.2$10.94
Claude Sonnet 4$12.00

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'