Claude Sonnet 5 vs Claude Sonnet 4.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
Claude Sonnet 5Intro price
by Anthropic
|
by Anthropic
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current mid tier |
| Released | Jun 30, 2026 | Sep 29, 2025 |
| Pricing per million tokens | ||
| Input | $2.00/Mtok | $3.00/Mtok |
| Output | $10.00/Mtok | $15.00/Mtok |
| Blended avg | $6.00/Mtok | $9.00/Mtok |
| Cached input | $0.200/Mtok | $0.300/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 | 81.5 | 75.1 |
| Perf / dollar | 13.6 | 8.3 |
| GPQA Diamond | 96.2 | 83.4 |
| SWE-Bench Verified | 85.2 | 82 |
| Terminal-Bench 2.1 | 80.4 | 42.8 |
| HumanEval | 85.2 | 82 |
| MCP Atlas | — | 59.5 |
| BrowseComp | 84.7 | — |
| OSWorld-Verified | 81.2 | — |
| Humanity's Last Exam | 57.4 | — |
| AIME 2025 | — | 87 |
| MMMLU | — | 89.1 |
| AutoBench | 13.5 | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 53.4 | — |
| AA Agentic Index | 46.7 | — |
| AA-Omniscience Index (−100–100) | 15.3 | — |
| GDPval-AA v2 | 1601.2 ELO | — |
| Providers | ||
| Available from |
Anthropic — $2.00/$10.00/Mtok
|
Anthropic — $3.00/$15.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Claude Sonnet 5 | Claude Sonnet 4.5 | Savings |
|---|---|---|---|
| 1M tokens | $6 | $9 | $3 (33.3%) |
| 10M tokens | $60 | $90 | $30 (33.3%) |
| 100M tokens | $600 | $900 | $300 (33.3%) |
| 1000M tokens | $6000 | $9000 | $3000 (33.3%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $6.00/Mtok blended vs $9.00 — 33.3% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 200K (5×)
- raw capability matters more than price: 81.5 vs 75.1 average benchmark score
- this pairing gives Claude Sonnet 4.5 no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
The cheaper option here — Claude Sonnet 5 costs $6.00/Mtok blended on Anthropic.
Summary
Claude Sonnet 5 by Anthropic costs $2.00/Mtok input and $10.00/Mtok output, with a 1M-token context window. It supports text, image input.
Claude Sonnet 4.5 by Anthropic costs $3.00/Mtok input and $15.00/Mtok output, with a 200K-token context window. It supports text, image input.
On a blended cost basis, Claude Sonnet 5 is 33.3% cheaper than Claude Sonnet 4.5. It also has a larger context window.
On benchmarks, Claude Sonnet 5 scores higher (81.5 vs 75.1) on average. In terms of value, Claude Sonnet 5 has better performance per dollar (13.6 vs 8.3).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.