Claude Opus 4.8 vs Claude Sonnet 5
API pricing, context window and capabilities for Claude Opus 4.8 and Claude Sonnet 5, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.
Verdict
computed from the published numbersClaude Opus 4.8 wins on coding and on intelligence. Claude Sonnet 5 wins on price.
Price
Claude Sonnet 5
Coding
Claude Opus 4.8
Intelligence
Claude Opus 4.8
Context window
Tied
Key takeaways
who wins on what, from the published numbersClaude Opus 4.8 wins
No clear edge on the tracked metrics.
Claude Sonnet 5 wins
- Cheaper input ($5.00 vs $2.00 /1M)
- Cheaper output ($25.00 vs $10.00 /1M)
Cheaper overall
Claude Sonnet 5
$2.00 + $10.00 /1M
Larger context
Tied
More providers
Tied
Pricing & specs
cheapest serving route · per 1M tokens| Claude Opus 4.8 | Claude Sonnet 5 | |
|---|---|---|
| Input $/1M | $5.00 | $2.00 best |
| Output $/1M | $25.00 | $10.00 best |
| Context window | 1M | 1M |
| Max output | 128K | 128K |
| Serving providers | 4 | 4 |
| Released | 2026-05-28 | 2026-06-30 |
Benchmarks
Artificial Analysis indices, side by side| Claude Opus 4.8 | Claude Sonnet 5 | |
|---|---|---|
| Intelligence | 55.7 best | 53.4 |
| Coding | 74.3 best | 71.5 |
| GPQA Diamond | 92% best | 91% |
| Output speed | 68 t/s best | 67 t/s |
| Latency (TTFT) | 38.57s best | 42.19s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Claude Opus 4.8
via Amazon Bedrock
$50
Claude Sonnet 5
via Amazon Bedrock
$20
Capabilities
feature support, side by side| Feature | Claude Opus 4.8 | Claude Sonnet 5 |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, Claude Opus 4.8 or Claude Sonnet 5?
Claude Sonnet 5 is cheaper for input ($5.00 vs $2.00 per 1M tokens). Claude Sonnet 5 is cheaper for output ($25.00 vs $10.00 per 1M tokens).
What is the context window difference between Claude Opus 4.8 and Claude Sonnet 5?
Both Claude Opus 4.8 and Claude Sonnet 5 have about a 1M-token context window.
How do Claude Opus 4.8 and Claude Sonnet 5 compare on benchmarks?
On the tracked Artificial Analysis indices, Claude Opus 4.8 leads on coding, and Claude Opus 4.8 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI