Claude Sonnet 4.6 vs Claude Opus 4.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Anthropic
|
by Anthropic
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current flagship |
| Released | Jan 15, 2026 | May 22, 2025 |
| Pricing per million tokens | ||
| Input | $3.00/Mtok | $5.00/Mtok |
| Output | $15.00/Mtok | $25.00/Mtok |
| Blended avg | $6.00/Mtok | $10.00/Mtok |
| Cached input | $0.300/Mtok | $0.500/Mtok |
| Specifications | ||
| Context window | 1M tokens | 200K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 70.4 | 70.9 |
| Perf / dollar | 11.7 | 7.1 |
| GPQA Diamond | 89.9 | 87 |
| Terminal-Bench 2.1 | 59.1 | 59.3 |
| MCP Atlas | 69.5 | 69.8 |
| ARC-AGI 2 | 58.3 | 37.6 |
| MMMLU | 89.3 | 90.8 |
| HumanEval | 79.6 | 80.9 |
| LiveCodeBench | 72.4 | — |
| BrowseComp | 76.2 | — |
| OSWorld-Verified | 78.5 | — |
| Humanity's Last Exam | 19.1 | — |
| AIME 2025 | 83 | — |
| AutoBench | 5.3 | — |
| AIME 2026 | — | 95.1 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 48.4 | — |
| AA Agentic Index | 42.1 | — |
| AA-Omniscience Index (−100–100) | 12.2 | — |
| LMSYS Chatbot Arena | 1471.9 ELO | — |
| Providers | ||
| Available from |
Anthropic — $3.00/$15.00/Mtok
|
Anthropic — $5.00/$25.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Claude Sonnet 4.6 | Claude Opus 4.5 | Savings |
|---|---|---|---|
| 1M tokens | $6 | $10 | $4 (40%) |
| 10M tokens | $60 | $100 | $40 (40%) |
| 100M tokens | $600 | $1000 | $400 (40%) |
| 1000M tokens | $6000 | $10000 | $4000 (40%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $6.00/Mtok blended vs $10.00 — 40% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 200K (5×)
- raw capability matters more than price: 70.9 vs 70.4 average benchmark score
The cheaper option here — Claude Sonnet 4.6 costs $6.00/Mtok blended on Anthropic.
Summary
Claude Sonnet 4.6 by Anthropic costs $3.00/Mtok input and $15.00/Mtok output, with a 1M-token context window. It supports text, image input.
Claude Opus 4.5 by Anthropic costs $5.00/Mtok input and $25.00/Mtok output, with a 200K-token context window. It supports text, image input.
On a blended cost basis, Claude Sonnet 4.6 is 40% cheaper than Claude Opus 4.5.It also has a larger context window.
On benchmarks, Claude Opus 4.5 scores higher (70.9 vs 70.4) on average. In terms of value, Claude Sonnet 4.6 has better performance per dollar (11.7 vs 7.1).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.