StarSeaAPI
claude-opus-4-6 vs claude-sonnet-4-6
| claude-opus-4-6 | claude-sonnet-4-6 | |
|---|---|---|
| Providers | Anthropic | Anthropic |
| Input $/M | $5.00 | $3.00 |
| Output $/M | $25.00 | $15.00 |
| Output multiplier | ×5.00 | ×5.00 |
| Context window | 200K tokens | 1M tokens |
| Intelligence index | — | — |
| Coding index | — | — |
What the numbers mean
claude-sonnet-4-6 is roughly 1.7× cheaper on input than claude-opus-4-6. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to claude-opus-4-6 deliberately rather than by default.
Tags: claude-opus-4-6 — Chat, Reasoning, Coding, Vision · claude-sonnet-4-6 — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# claude-opus-4-6
client.chat.completions.create(model="claude-opus-4-6", messages=[{"role":"user","content":"Hi"}])
# claude-sonnet-4-6
client.chat.completions.create(model="claude-sonnet-4-6", messages=[{"role": "user", "content": "Hi"}])