Claude Sonnet 4.5
Anthropic · Proprietary · Released Sep 29, 2025 · anthropic/claude-sonnet-4.5
1M contextVisionToolsReasoningStructured outputPrompt caching
Available from 7 providersUSD / MTOK · VERIFIED 12 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 Google | $3.00 | $15.00 | $0.30 | 1M | — | 1s | 39 tok/s | 100.0% |
 Azure | $3.00 | $15.00 | $0.30 | 200K | — | 2.1s | 57 tok/s | 99.7% |
| CPOClaude Platform on AWS | $3.00 | $15.00 | $0.30 | 1M | — | 1.8s | 37 tok/s | 100.0% |
 Amazon Bedrock | $3.00 | $15.00 | $0.30 | 1M | — | 2.2s | 46 tok/s | 99.9% |
 Anthropic1ST PARTY | $3.00 | $15.00 | $0.30 | 1M | — | 1.7s | 40 tok/s | 99.9% |
| Amazon Bedrock | $3.30 | $16.50 | $0.33 | 1M | — | — | — | — |
| Google | $3.30 | $16.50 | $0.33 | 1M | — | — | — | — |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$3.00 / $15.00
per MTok in / out
BATCH
$1.50 / $7.50
async batch
CACHE READ $0.30CACHE WRITE $3.75WEB SEARCH $0.01 / searchCACHE WRITE 1H $6.00 / MTok
About
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
Specifications
Context window1,000,000
Max output64,000
Modalities intext, image, file
Modalities outtext
LicenseProprietary
ReleasedSep 29, 2025
Knowledge cutoff2025-01-31
TokenizerClaude
Related
Embed badge
[](https://modelindex.ai/models/anthropic/claude-sonnet-4.5)Sources
OpenRouter API12 hours ago
AGGREGATORModelIndex benchmarks43 hours ago
MEASUREDVerified 12 hours ago · list prices, not negotiated rates.