Strongest Claude Opus model for coding, agents, and professional work
Specification
anthropic listing
Context
1M
Max output
128K
Released
2026-07-24
Knowledge cutoff
2026-05
Retires
2027-07-24
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · anthropic list price
Input
$5.00
Output
$25.00
Cache read
$0.50
Cache write
$6.25
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Cache write, 1 hour | bedrock_converse | $10.00 |
| Cache write, 1 hour | bedrock_converse · us | $11.00 |
| Cache write, 1 hour | bedrock | $12.00 |
Quality
9 benchmarks · 2 sources
Composite
96th
percentile of 334 scored models
Rank
16 / 334
±0.07 sd
Evidence
9 × 2
3 or more benchmarks, from 2 or more sources
Effort range
14.0
points between effort settings
reasoning95th4/4 bench
math96th3/7 bench
knowledge83rd1/1 bench
general88th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| max | 97th | 9 |
| low | 88th | 3 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Mystery Game Puzzles | 59.0 ±4.9 | max | Epoch AI | 2026-07-25 |
| ↳ | 37.0 ±4.9 | default | Epoch AI | 2026-08-06 |
| Settings differ by 22.0 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 85.6 ±2.1 | max | Epoch AI | 2026-07-24 |
| FrontierMath-Tier-4-v2 | 73.2 ±7.0 | max | Epoch AI | 2026-07-24 |
| OTIS Mock AIME 2024-2025 | 98.9 ±1.1 | max | Epoch AI | 2026-07-24 |
| ↳ | 97.8 ±2.2 | default | Epoch AI | 2026-08-06 |
| ↳ | 93.3 ±3.8 | low | Epoch AI | 2026-08-06 |
| Settings differ by 5.6 points on this benchmark. | ||||
| GPQA diamond | 93.9 ±1.5 | max | Epoch AI | 2026-07-24 |
| ↳ | 92.9 ±1.8 | default | Epoch AI | 2026-08-06 |
| ↳ | 87.9 ±2.3 | low | Epoch AI | 2026-08-06 |
| Settings differ by 6.0 points on this benchmark. | ||||
| EBR-bench | 45.7 ±3.6 | max | Epoch AI | 2026-09-05 |
| Chess Puzzles | 42.0 ±5.0 | max | Epoch AI | 2026-07-24 |
| ↳ | 33.0 ±4.7 | default | Epoch AI | 2026-08-06 |
| ↳ | 20.0 ±4.0 | low | Epoch AI | 2026-08-06 |
| Settings differ by 22.0 points on this benchmark. | ||||
| SimpleQA Verified | 59.9 ±1.6 | max | Epoch AI | 2026-08-10 |
| LiveBench | 80.5 | max · 23 runs | LiveBench | 2026-06-25 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 49 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| anthropicvendor | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | 2027-07-24 |
| kenari | free | free | — | — | 1M | 128K | — |
| 302ai | $5.00 | $25.00 | — | — | 1M | 128K | — |
| abacus | $5.00 | $25.00 | — | — | 1M | 128K | — |
| aihubmix | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| amazon-bedrock | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| amazon-bedrock · au | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| amazon-bedrock · global | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| amazon-bedrock · jp | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| amazon-bedrock · us | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| azure | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| azure_ai | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | 2027-07-08 |
| azure-cognitive-services | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| bedrock_converse | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| bedrock_converse · global | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| cloudflare-ai-gateway | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| crossmodel | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| databricks | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| deepinfra | $5.00 | $25.00 | — | — | 1M | — | — |
| edenai | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| github-copilot | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 64K | — |
| kilo | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| llmgateway | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| llmgateway-providers | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| llmgateway-providers · aws-bedrock | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| llmgateway-providers · azure-anthropic | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| merge-gateway | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| nano-gpt | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| neon | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| ofox | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| opencode | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| openrouter | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| opper | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| orcarouter | $5.00 | $25.00 | $0.50 | $10.00 | 1M | 128K | — |
| perplexity | $5.00 | $25.00 | $0.50 | — | — | — | — |
| pioneer | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| requesty | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| vercel | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | — |
| vertex_ai-anthropic_models | $5.00 | $25.00 | $0.50 | $6.25 | 1M | 128K | 2027-01-24 |
| amazon-bedrock · eu | $5.50 | $27.50 | $0.55 | $6.875 | 1M | 128K | — |
| bedrock_converse · au | $5.50 | $27.50 | $0.55 | $6.875 | 1M | 128K | — |
| bedrock_converse · eu | $5.50 | $27.50 | $0.55 | $6.875 | 1M | 128K | — |
| bedrock_converse · jp | $5.50 | $27.50 | $0.55 | $6.875 | 1M | 128K | — |
| bedrock_converse · us | $5.50 | $27.50 | $0.55 | $6.875 | 1M | 128K | — |
| cortecs | $5.50 | $27.498 | $0.55 | $6.874 | 1M | 128K | — |
| bedrock | $6.00 | $30.00 | $0.60 | $7.50 | 1M | 128K | — |
| venice | $6.00 | $30.00 | $0.60 | $7.50 | 1M | 128K | — |
| agentrouter | — | — | — | — | 1M | 128K | — |
| snowflake-cortex | — | — | — | — | 1M | 128K | — |
Other listings of this model
same model, different key
More from Anthropic
most-hosted first