claude-sonnet-4-6 vs claude-sonnet-5-5
| claude-sonnet-4-6 | claude-sonnet-5-5 | |
|---|---|---|
| Providers | Anthropic | Anthropic |
| Input $/M | $1.50 | $1.00 |
| Output $/M | $7.50 | $5.00 |
| Output multiplier | ×5.00 | ×5.00 |
| Context window | 1M tokens | 1M tokens |
| Intelligence index | 24.7 | 56.0 |
| Coding index | — | — |
What the numbers mean
Input pricing is close — 1.50× apart — so the decision should come down to measured quality on your own evaluation set rather than headline cost.
On measured intelligence index the gap is 31.3 points, with claude-sonnet-5-5 ahead. That is a large enough spread to be visible on multi-step tasks.
Tags: claude-sonnet-4-6 — Chat, Reasoning, Coding, Vision · claude-sonnet-5-5 — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# claude-sonnet-4-6
client.chat.completions.create(model="claude-sonnet-4-6", messages=[{"role":"user","content":"Hi"}])
# claude-sonnet-5-5
client.chat.completions.create(model="claude-sonnet-5-5", messages=[{"role": "user", "content": "Hi"}])