anthropic/claude-opus-5.5
The successor to Opus 5 and Anthropic's recommended default model, built for long-running agentic coding and knowledge work. The official price drops to $4 / $20 per million tokens (from $5 / $25), and cache reads cost just 5% of the input price. Thinking is always on — tune its depth and cost with the effort parameter (default medium). 1M-token context window, text and image input, and native prompt caching.
Source : official_x0.3 · Vérifié le 2026-10-12
Lecture cache $0.06/M · Écriture cache $1.5/M
Utilisez l'un ou l'autre des IDs pour appeler ce modèle via l'API.
anthropic/claude-opus-5.5claude-opus-5-5Remplacez le placeholder ONEHOP_KEY par votre API key. Créer →
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.onehop.ai/anthropic",
api_key="<ONEHOP_KEY>",
)
message = client.messages.create(
model="anthropic/claude-opus-5.5",
max_tokens=1024,
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(message.content[0].text)Anthropic's current flagship Opus — a step change on agentic coding and long-horizon work.
$1.5/M↓ · $7.5/M↑
Anthropic Claude Opus 4.8 — current flagship, top reasoning & coding.
$1.5/M↓ · $7.5/M↑
Anthropic Claude Opus 4.7 — top-tier reasoning, coding, agentic work.
$1.5/M↓ · $7.5/M↑
Anthropic Claude Opus 4.6 — previous-gen Opus, same price as 4.7/4.8.
$1.5/M↓ · $7.5/M↑