Claude Sonnet 4.5 pricing & benchmarks
Claude Sonnet 4.5 is available from Anthropic at $3.00 per million input tokens and $15.00 per million output tokens ($6.00 blended at 3:1). It accepts up to 1,000,000 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$3.00
Output$15.00
Blended (3:1)$6.00
Specification
anthropic/claude-sonnet-4.5
Context window1M
Max output64K
ReleasedSep 2025
LicenceProprietary
Modalitiesin:text, in:image, in:file, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 82.3% ±2.7 | 59k thinking effort | 2025-10-28 | Independently run · Epoch AI |
| SWE-bench Verified | 71.3% ±2.1 | no thinking effort | 2026-02-05 | Independently run · Epoch AI |
| FrontierMath T1–3 | 23.9% ±2.5 | 32k thinking effort | 2026-06-11 | Independently run · Epoch AI |
| FrontierMath T4 | 2.4% ±2.4 | 32k thinking effort | 2026-06-11 | Independently run · Epoch AI |
| SimpleQA Verified | 23.6% ±1.3 | 59k thinking effort | 2025-12-09 | Independently run · Epoch AI |
| OTIS Mock AIME | 77.8% ±6.3 | 59k thinking effort | 2025-10-28 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | DeepSeek | $0.113 (−98%) | 91.0% | Compare → |
| GPT-5.6 Luna | OpenAI | $0.225 (−96%) | 91.6% | Compare → |
| GLM 5.2 | Zhipu AI | $0.387 (−94%) | 91.9% | Compare → |
| Qwen3.6 Flash | Alibaba | $0.422 (−93%) | 83.3% | Compare → |
| DeepSeek V4 Pro | DeepSeek | $0.544 (−91%) | 90.9% | Compare → |
Where to run Claude Sonnet 4.5
8 options across 4 providers · 1.1× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Uptime 24h |
|---|---|---|---|---|
| Amazon Bedrock ⚠ re-prices above 200K prompt tokens ($6.00/$22.50) |
$6.00 | $3.00 / $15.00 | 1M | 99.9% |
| Anthropic ⚠ re-prices above 200K prompt tokens ($6.00/$22.50) |
$6.00 | $3.00 / $15.00 | 1M | 99.7% |
| Google (global) ⚠ re-prices above 200K prompt tokens ($6.00/$22.50) |
$6.00 | $3.00 / $15.00 | 1M | 99.7% |
| Anthropic (2) ⚠ re-prices above 200K prompt tokens ($6.00/$22.50) |
$6.00 | $3.00 / $15.00 | 1M | 72.1% |
| Amazon Bedrock (claude-on-aws) ⚠ re-prices above 200K prompt tokens ($6.00/$22.50) |
$6.00 | $3.00 / $15.00 | 1M | 85.8% |
| Azure (global) ⚠ 200K context, not 1M |
$6.00 | $3.00 / $15.00 | 200K | 100.0% |
| Google (us-east5) ⚠ re-prices above 200K prompt tokens ($6.60/$24.75) |
$6.60 | $3.30 / $16.50 | 1M | — |
| Amazon Bedrock (eu-west-1) ⚠ re-prices above 200K prompt tokens ($6.60/$24.75) |
$6.60 | $3.30 / $16.50 | 1M | 100.0% |
Host prices and uptime from OpenRouter, synced 2026-08-08.
Compare Claude Sonnet 4.5
FAQ
How much does Claude Sonnet 4.5 cost?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $6.00 per million tokens.
What is Claude Sonnet 4.5's context window?
Claude Sonnet 4.5 accepts up to 1,000,000 tokens of context, and can generate up to 64,000 output tokens.
How good is Claude Sonnet 4.5 on benchmarks?
Claude Sonnet 4.5 scores 82.3% on GPQA Diamond, independently run and published by Epoch AI. 6 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Claude Sonnet 4.5?
Yes — 5 models in our catalogue cost less per token than Claude Sonnet 4.5 and score at least as high on the same benchmark. The cheapest is DeepSeek V4 Flash 0731 at $0.113 per million tokens blended.