Claude Opus 5.5: API price, context window and how to connect

Claude Opus 5.5 by Anthropic: $4 per million input tokens, $20 per million output tokens, a 1M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.

Updated Copy as Markdown
In this article

In short#

Anthropic's flagship, successor to Claude Opus 5: for hard reasoning, code and long agentic work. Especially strong at multi-step changes in large codebases.

Specifications#

Provider Anthropic
Released 2026-09-22
Context window 1M tokens
Accepts text, images, files
Answers with text
Reasoning mode yes
Tool calling yes
Open weights no
Identifier anthropic/claude-opus-5.5

Price#

Per 1M tokens In dollars
Input (question, context) $4
Output (answer) $20

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.36. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.

What it is good for#

  • Large code changes and review
  • Long agentic tasks
  • Complex document analysis

Similar models#

Catalog models with the same kind of output, closest in the price of a typical request.

Model Input Output Window Price
Claude Opus 5 $5 $25 1M 1.2× more expensive
Qwen3.8 Max Prime $4 $12 1M 1.4× cheaper
GPT-6.1 Sol $2 $10 1.05M 2× cheaper
GPT-6.1 Sol Pro $2 $10 1.05M 2× cheaper
Claude Sonnet 5.5 $2 $10 1M 2× cheaper

Other Anthropic models#

How to connect in SKILLOK#

Claude Opus 5.5 works through OpenRouter: add an OpenRouter key in Settings → AI and pick the anthropic/claude-opus-5.5 model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.

Where the data comes from#

Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.

Was this helpful?