Anthropic · Workhorse
Claude Sonnet 5
The best balance of speed and intelligence in Anthropic's line, reaching what was previously Opus-tier quality on a lot of coding and agentic work. The default choice for most production applications.
Model ID: claude-sonnet-5
What that means
A worked example
Per-token pricing is hard to feel. Take a moderately chatty production workload: 100 calls a day, roughly 10,000 tokens in and 2,000 out each time. On Claude Sonnet 5 that comes to about:
$180 / month
Before caching, batching or volume discounts, all of which move this number a long way. Illustrative only.
Strong at
- -Coding
- -Agentic tasks
- -Cost efficiency at scale
Typical use
- -Production applications
- -Code generation
- -High-volume pipelines
Watch out for
- -New tokenizer: roughly 30% more tokens for the same text vs Sonnet 4.6
Same tier
What else to look at
| Model | Developer | Context | In / 1M | Out / 1M |
|---|---|---|---|---|
| Claude Sonnet 4.6 | Anthropic | 1M | $3 | $15 |
| GPT-5.6 Terra | OpenAI | 1M | $2 | $12 |
| GPT-5.4 | OpenAI | - | $2.50 | $15 |
| Gemini 3.6 Flash | 1M | $1.50 | $7.50 | |
| Grok 4.20 | xAI | - | $1.25 | $2.50 |
Verified 2026-08-07.