Claude Opus 4.5 (latest)
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Shogo Agent Index
Supported#46 of 9246.0range 41.5–50.6 · 67% of weight measured
Agentic coding
47
57% measured
Long-horizon autonomy
61
80% measured
Knowledge-work agents
37
68% measured
Computer use
30
40% measured
Security & context learning
52
100% measured
Price
- Input
- $5.00/M
- Output
- $25.00/M
- Cache read
- $0.50/M
- 3:1 blend
- $10.00/M
- Agent-effective
- $2.31/M
Cheapest host for agents: Amazon Bedrock at $2.31/M.
Agent-effective = 20 input tokens per output token, 85% cache hits. Why.
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | 76.7% | 8% | source | |
| Terminal-Bench 2.0 | 63.1% | 8% | Droid | |
| DeepSWE | est. | 6% | predicted 41 | |
| FrontierSWE | est. | 5% | predicted 11 | |
| CursorBench | est. | 4% | predicted 34 | |
| GSO-Bench | 26.5% | 4% | OpenHands | |
| METR Time Horizons | 75.0% | 10% | source | |
| Vending-Bench 2 | $4,967 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 22 | |
| APEX-Agents | est. | 8% | predicted 38 | |
| GDPval | 45.5% | 7% | source | |
| Remote Labor Index | 3.8% | 5% | source | |
| DeepResearch Bench | 54.8% | 5% | source | |
| OSWorld 2.0 | est. | 6% | predicted 6 | |
| OSWorld | 66.3% | 4% | Claude Opus 4.5 | |
| Cybench | 82.0% | 5% | source | |
| CL-bench | 21.1% | 5% | source |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| AlgoTune | Coding | 1.77× | source |
| ARC-AGI | Reasoning | 80.0% | source |
| ARC-AGI-2 | Reasoning | 37.6% | source |
| BALROG | Long-horizon | 43.5% | source |
| Chess Puzzles | Reasoning | 14.0% | source |
| DTBench | Knowledge | 89.9% | source |
| FrontierMath Tiers 1-3 | Math | 34.4% | source |
| FrontierMath Tier 4 | Math | 4.9% | source |
| GeoBench | Multimodal | 75.0% | source |
| GPQA Diamond | Reasoning | 86.0% | source |
| Humanity's Last Exam | Reasoning | 25.2% | source |
| LMCA | Knowledge | 44.5% | source |
| OTIS Mock AIME | Math | 86.1% | source |
| ProofBench | Math | 36.0% | source |
| SimpleBench | Reasoning | 62.0% | source |
| SimpleQA Verified | Knowledge | 45.7% | source |
| VPCT | Multimodal | 40.0% | source |
| WebDev Arena | Coding | 1495 | source |
| WeirdML v3 | Coding | 6.5% | claude_code |
API hosts
Live prices and uptime for every host serving Claude Opus 4.5 (latest) via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Amazon Bedrock | $5.00 | $25.00 | $0.50 | $2.31 | 100.0% | — |
| Anthropic | $5.00 | $25.00 | $0.50 | $2.31 | 100.0% | — |
| Azure | $5.00 | $25.00 | $0.50 | $2.31 | 100.0% | — |
| Claude Platform on AWS | $5.00 | $25.00 | $0.50 | $2.31 | 100.0% | — |
| $5.00 | $25.00 | $0.50 | $2.31 | — | — |