Claude Opus 4.8 vs Claude Sonnet 4.6
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Anthropic
|
by Anthropic
|
|---|---|---|
| Overview | ||
| Status | Current flagship | Current mid tier |
| Released | May 28, 2026 | Jan 15, 2026 |
| Pricing per million tokens | ||
| Input | $5.00/Mtok | $3.00/Mtok |
| Output | $25.00/Mtok | $15.00/Mtok |
| Blended avg | $10.00/Mtok | $6.00/Mtok |
| Cached input | $0.500/Mtok | $0.300/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 81.3 | 70.4 |
| Perf / dollar | 8.1 | 11.7 |
| GPQA Diamond | 93.6 | 89.9 |
| Terminal-Bench 2.1 | 74.6 | 59.1 |
| MCP Atlas | 82.2 | 69.5 |
| OSWorld-Verified | 83.4 | 78.5 |
| Humanity's Last Exam | 57.9 | 19.1 |
| HumanEval | 88.6 | 79.6 |
| AutoBench | 15.5 | 5.3 |
| SWE-Bench Verified | 88.6 | — |
| LiveCodeBench | — | 72.4 |
| BrowseComp | — | 76.2 |
| ARC-AGI 2 | — | 58.3 |
| AIME 2025 | — | 83 |
| MMMLU | — | 89.3 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 57.3 | 48.4 |
| AA Agentic Index | 49.4 | 42.1 |
| AA-Omniscience Index (−100–100) | 28.8 | 12.2 |
| LMSYS Chatbot Arena | 1473.6 ELO | 1472 ELO |
| GDPval-AA v2 | 1588.3 ELO | — |
| Providers | ||
| Available from |
Anthropic — $5.00/$25.00/Mtok
|
Anthropic — $3.00/$15.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Claude Opus 4.8 | Claude Sonnet 4.6 | Savings |
|---|---|---|---|
| 1M tokens | $10 | $6 | $4 (40%) |
| 10M tokens | $100 | $60 | $40 (40%) |
| 100M tokens | $1000 | $600 | $400 (40%) |
| 1000M tokens | $10000 | $6000 | $4000 (40%) |
When to pick which
distilled from the pricing and spec data above- raw capability matters more than price: 81.3 vs 70.4 average benchmark score
- cost dominates: $6.00/Mtok blended vs $10.00 — 40% less on the same 50/50 token mix
The cheaper option here — Claude Sonnet 4.6 costs $6.00/Mtok blended on Anthropic.
Summary
Claude Opus 4.8 by Anthropic costs $5.00/Mtok input and $25.00/Mtok output, with a 1M-token context window. It supports text, image input.
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.
On a blended cost basis, Claude Sonnet 4.6 is 40% cheaper than Claude Opus 4.8.
On benchmarks, Claude Opus 4.8 scores higher (81.3 vs 70.4) on average. In terms of value, Claude Sonnet 4.6 has better performance per dollar (11.7 vs 8.1).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.