Claude Sonnet 5
- Context
- 1M
- 128K max output
- Input price
- $2.00
- per 1M tokens · Claude API
- Output price
- $10.00
- per 1M tokens
- Epoch Capabilities Index
- 156.3
- #20 of 71 listed
- LMArena Text
- 1,462
- #32 of 79 listed
Where to run it
7 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $2.00 / 1M tokens |
| Batch | $1.00 / 1M tokens | |
| Output | Standard | $10.00 / 1M tokens |
| Batch | $5.00 / 1M tokens | |
| Cache read | Standard | $0.20 / 1M tokens |
| Cache write | 5-minute cache | $2.50 / 1M tokens |
| 1-hour cache | $4.00 / 1M tokens | |
Amazon Bedrock (opens in a new tab) Claude Sonnet 5 | ||
| Input | Standard | $2.20 / 1M tokens |
| Output | Standard | $11.00 / 1M tokens |
| Cache read | Standard | $0.22 / 1M tokens |
| Cache write | 5-minute cache | $2.75 / 1M tokens |
| 1-hour cache | $4.40 / 1M tokens | |
Amazon Bedrock (opens in a new tab) Claude Sonnet 5 | ||
| Input | Standard | $2.20 / 1M tokens |
| Output | Standard | $11.00 / 1M tokens |
| Cache read | Standard | $0.22 / 1M tokens |
| Cache write | 5-minute cache | $2.75 / 1M tokens |
| 1-hour cache | $4.40 / 1M tokens | |
Amazon Bedrock (opens in a new tab) Claude Sonnet 5 | ||
| Input | Standard | $2.20 / 1M tokens |
| Output | Standard | $11.00 / 1M tokens |
| Cache read | Standard | $0.22 / 1M tokens |
| Cache write | 5-minute cache | $2.75 / 1M tokens |
| 1-hour cache | $4.40 / 1M tokens | |
Google Cloud Vertex AI (opens in a new tab) claude-sonnet-5 | ||
| Input | Standard | $2.00 / 1M tokens |
| Batch | $1.00 / 1M tokens | |
| Prompts over 200K tokens | $2.00 / 1M tokens | |
| Prompts over 200K tokens · Batch | $1.00 / 1M tokens | |
| Output | Standard | $10.00 / 1M tokens |
| Batch | $5.00 / 1M tokens | |
| Prompts over 200K tokens | $10.00 / 1M tokens | |
| Prompts over 200K tokens · Batch | $5.00 / 1M tokens | |
| Cache read | Standard | $0.20 / 1M tokens |
| Prompts over 200K tokens | $0.20 / 1M tokens | |
| Cache write | 5-minute cache | $2.50 / 1M tokens |
| 1-hour cache | $4.00 / 1M tokens | |
| Prompts over 200K tokens · 5-minute cache | $2.50 / 1M tokens | |
| Prompts over 200K tokens · 1-hour cache | $4.00 / 1M tokens | |
Google Cloud Vertex AI (opens in a new tab) Claude Sonnet 5 | ||
| Input | Standard | $2.20 / 1M tokens |
| Batch | $1.10 / 1M tokens | |
| Prompts over 200K tokens | $2.20 / 1M tokens | |
| Prompts over 200K tokens · Batch | $1.10 / 1M tokens | |
| Output | Standard | $11.00 / 1M tokens |
| Batch | $5.50 / 1M tokens | |
| Prompts over 200K tokens | $11.00 / 1M tokens | |
| Prompts over 200K tokens · Batch | $5.50 / 1M tokens | |
| Cache read | Standard | $0.22 / 1M tokens |
| Prompts over 200K tokens | $0.22 / 1M tokens | |
| Cache write | 5-minute cache | $2.75 / 1M tokens |
| 1-hour cache | $4.40 / 1M tokens | |
| Prompts over 200K tokens · 5-minute cache | $2.75 / 1M tokens | |
| Prompts over 200K tokens · 1-hour cache | $4.40 / 1M tokens | |
Google Cloud Vertex AI (opens in a new tab) Claude Sonnet 5 | ||
| Input | Standard | $2.20 / 1M tokens |
| Batch | $1.10 / 1M tokens | |
| Prompts over 200K tokens | $2.20 / 1M tokens | |
| Prompts over 200K tokens · Batch | $1.10 / 1M tokens | |
| Output | Standard | $11.00 / 1M tokens |
| Batch | $5.50 / 1M tokens | |
| Prompts over 200K tokens | $11.00 / 1M tokens | |
| Prompts over 200K tokens · Batch | $5.50 / 1M tokens | |
| Cache read | Standard | $0.22 / 1M tokens |
| Prompts over 200K tokens | $0.22 / 1M tokens | |
| Cache write | 5-minute cache | $2.75 / 1M tokens |
| 1-hour cache | $4.40 / 1M tokens | |
| Prompts over 200K tokens · 5-minute cache | $2.75 / 1M tokens | |
| Prompts over 200K tokens · 1-hour cache | $4.40 / 1M tokens | |
Vendor-reported scores
Published by Anthropic, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| SWE-bench Verified | adaptive thinking, max effort, average of 5 trials | 85.2% |
| SWE-bench Pro | adaptive thinking, max effort, average of 5 trials | 63.2% |
| SWE-bench Multilingual | adaptive thinking, max effort, average of 5 trials | 78.3% |
| SWE-bench Multimodal | adaptive thinking, max effort, average of 5 trials | 28.1% |
| Terminal-Bench 2.1 | xhigh effort, mini-SWE-agent harness, mean reward over 5 attempts per task (89 tasks) | 80.4% |
| BrowseComp | single agent, adaptive thinking, max effort, 10M-token limit with context compaction | 84.7% |
| multi-agent, adaptive thinking, max effort | 86.6% | |
| Humanity's Last Exam | no tools, max effort | 43.2% |
| with web search, web fetch, programmatic tool calling, code execution; max effort | 57.4% | |
| OSWorld-Verified | first-attempt success rate, averaged over 5 runs, max effort | 81.2% |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 156.3
#20 of 71 listed models · CI 153.5–159.2
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text 1,462
#32 of 79 listed models · high effort · CI 1,457–1,466 · 43,340 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- Epoch AI · FrontierMath Tiers 1–3 65.6%
#24 of 56 listed models · max effort · ±2.82
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · GPQA Diamond 90.5%
#27 of 64 listed models · xhigh effort · ±1.78
Also listed: max effort 80.3%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text · Chinese 1,495
#40 of 79 listed models · high effort · CI 1,484–1,506 · 3,360 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,519
#24 of 79 listed models · high effort · CI 1,513–1,526 · 11,904 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,277
#23 of 49 listed models · high effort · CI 1,270–1,285 · 10,289 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made