Anthropic
Claude Sonnet 4
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.
Providers
Reference data — not yet measured from live traffic
| PROVIDER | MAX OUT | OUTPUT /M | QUANT | |||||
|---|---|---|---|---|---|---|---|---|
AnthropicCheapest | 200K | 64K | $3.00 | $15.00 | 239ms | 80 | 99.90% | Full |
Amazon Bedrock | 200K | 64K | $3.12 | $15.60 | 900ms | 68 | 99.78% | Full |
Google Vertex AI | 200K | 64K | $3.15 | $15.75 | 870ms | 70 | 99.72% | 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
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." }
]
}'