claude-fable-5 vs claude-opus-5
| claude-fable-5 | claude-opus-5 | |
|---|---|---|
| Providers | Anthropic | Anthropic |
| Input $/M | $2.50 | $1.25 |
| Output $/M | $12.50 | $6.25 |
| Output multiplier | ×5.00 | ×5.00 |
| Context window | 1M tokens | 1M tokens |
| Intelligence index | 49.6 | 50.8 |
| Coding index | 76.5 | 78.0 |
What the numbers mean
claude-opus-5 is roughly 2.0× cheaper on input than claude-fable-5. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to claude-fable-5 deliberately rather than by default.
Measured intelligence index differs by only 1.2 points, which in practice means the two models are interchangeable on most tasks — pick on price and latency.
Tags: claude-fable-5 — Chat, Vision, Reasoning, Coding, 工具调用, Long context · claude-opus-5 — Chat, Vision, Reasoning, Coding, 工具调用, Long context
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# claude-fable-5
client.chat.completions.create(model="claude-fable-5", messages=[{"role":"user","content":"Hi"}])
# claude-opus-5
client.chat.completions.create(model="claude-opus-5", messages=[{"role": "user", "content": "Hi"}])