claude-haiku-5-5 vs claude-sonnet-5
| claude-haiku-5-5 | claude-sonnet-5 | |
|---|---|---|
| Providers | Anthropic | Anthropic |
| Input $/M | $0.10 | $2.00 |
| Output $/M | $0.50 | $10.00 |
| Output multiplier | ×5.00 | ×5.00 |
| Context window | 1M tokens | 1M tokens |
| Intelligence index | — | 38.2 |
| Coding index | — | 71.5 |
What the numbers mean
claude-haiku-5-5 is roughly 20.0× cheaper on input than claude-sonnet-5. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to claude-sonnet-5 deliberately rather than by default.
Tags: claude-haiku-5-5 — Chat, Reasoning, Coding, Vision · claude-sonnet-5 — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# claude-haiku-5-5
client.chat.completions.create(model="claude-haiku-5-5", messages=[{"role":"user","content":"Hi"}])
# claude-sonnet-5
client.chat.completions.create(model="claude-sonnet-5", messages=[{"role": "user", "content": "Hi"}])