Claude Opus 5 costs $5 per million input tokens and $25 per million output tokens on Roar AI. The previous Opus, still available for work that was built and tested on it.
Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $40. Every rate is published and stays the same from one request to the next. See every model.
Rates as of 20 November 2026.
claude-opus-5Opus 5 was Anthropic’s top everyday model from July to September 2026, when Opus 5.5 replaced it. At launch Anthropic’s headline was agent work: on Zapier’s AutomationBench it passed about one and a half times as many tasks as the next-best model at the same cost per task.
Unlike Opus 5.5, its thinking is optional, so it can give a quick answer without reasoning first. That, and stability, are the reasons to stay on it: if a product was tuned on Opus 5, keep it there until you have tested the move.
Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
reply = client.chat.completions.create(
model="claude-opus-5",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Input is $5 per 1M tokens; output is $25 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $40.
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Claude Opus 5 to another model only means changing the model name in your code.
No. Anthropic does not publish the weights, so it is only available through an API like this one.
Claude Opus 5 can read up to 1M tokens in one request, and write an answer of up to 128K tokens.
Yes. Claude Opus 5 reads images and PDFs directly.
Create a free account, get an API key and call Claude Opus 5 with the OpenAI SDK.