Roar AI
DiscordGet started
All models
Anthropic · Chat

Claude Opus 5.5

Claude Opus 5.5 costs $4 per million input tokens and $20 per million output tokens on Roar AI. Anthropic’s recommended default for demanding work, and cheaper than the Opus it replaced.

Input$4per 1M tokens
Output$20per 1M tokens
Context window1Mtokens

Claude Opus 5.5 API pricing

Input$4 per 1M tokens
Output$20 per 1M tokens
Cached input$0.20 per 1M tokens
Cache write$5 per 1M tokens
Batch input$2 per 1M tokens
Batch output$10 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $32. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byAnthropic
ReleasedSeptember 2026
TypeChat
Context window1M tokens
Longest answer128K tokens
ReadsText, images, PDFs
Thinks before answeringAlways on
WeightsClosed
Processed inGlobal
Model idclaude-opus-5-5

Is Claude Opus 5.5 worth the price?

For long, open-ended work that needs judgement throughout, yes. Anthropic says that is where Opus is clearly stronger than Sonnet 5.5, and it scored higher than Fable 5.1 on professional knowledge work in Anthropic’s own GDPval-AA test, 1846 against 1735.

For most other work, try Claude Sonnet 5.5 first. It nearly matches Opus on most measured work at a lower rate, and it beat Opus on Terminal-Bench 4.0. Anthropic itself cautions that benchmark leads have become a weak guide to real differences, so compare the two on your own tasks.

Claude Opus 5.5 and the models to compare it with, priced per 1M tokens
ModelInputOutputChoose it for
Claude Opus 5.5$4$20Complex coding and knowledge work.
Claude Sonnet 5.5$2$10Most everyday coding and documents, at a lower rate.
GPT-6.1 Sol$2$10Production agents, when cost per task decides it.
Claude Fable 5.1$10$50Problems Opus cannot solve.

Prices per 1M tokens.

About Claude Opus 5.5

Opus 5.5 replaced Opus 5 in September 2026 and is the model Anthropic tells most people to start with. Anthropic puts it at about 40% cheaper than its predecessor on typical work and more than 30% faster at writing its answer. On professional knowledge work it scored higher than Fable 5.1 in Anthropic’s own GDPval-AA test (1846 against 1735), and it reached 66.4% on Terminal-Bench 4.0.

Thinking is always on, at medium effort by default. For long coding sessions, reviewing a large codebase and business analysis it is a dependable choice for demanding work; Fable 5.1 is worth the extra cost only on problems Opus cannot solve.

What is Claude Opus 5.5 good for?

  • Long coding sessions and reviewing large codebases.
  • Financial analysis, reports and other professional knowledge work.
  • Automating multi-step business workflows.
  • A dependable default when you are not sure which model to use.

Claude Opus 5.5 limitations

  • Thinking cannot be switched off, so even a simple question carries some reasoning time and cost.
  • Anthropic itself cautions that benchmark leads have become a weak guide to real differences. Compare it on your own tasks.
  • Cybersecurity and biology requests may be refused by Anthropic’s safety filters.

How to use the Claude Opus 5.5 API

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-5-5",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Claude Opus 5.5 FAQ

How much does Claude Opus 5.5 cost?

Input is $4 per 1M tokens; output is $20 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $32.

Can I use Claude Opus 5.5 alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Claude Opus 5.5 to another model only means changing the model name in your code.

Is Claude Opus 5.5 open source?

No. Anthropic does not publish the weights, so it is only available through an API like this one.

What is the context window of Claude Opus 5.5?

Claude Opus 5.5 can read up to 1M tokens in one request, and write an answer of up to 128K tokens.

Can Claude Opus 5.5 read images and PDFs?

Yes. Claude Opus 5.5 reads images and PDFs directly.

Start using Claude Opus 5.5

Create a free account, get an API key and call Claude Opus 5.5 with the OpenAI SDK.