Anthropic: Claude models
Anthropic makes the Claude models, strong in code, long documents and careful agent work. The Haiku, Sonnet and Opus lines, access from Russia and connecting in SKILLOK.
In this article
Who they are#
Anthropic is an American company founded by former OpenAI employees. Its Claude models are known for the quality of their code, their work with long documents and careful answers.
Models#
- Haiku — fast and inexpensive: summaries, classification, simple questions.
- Sonnet — the general-purpose working model: code, analysis, agents.
- Opus — the strongest and most expensive: hard tasks and long reasoning.
The exact list and versions change often — current models are visible in the list when you connect a key in SKILLOK, and in the model catalog.
What they are good at#
- Among the best models for programming and agent work in a repository.
- A large context window — they read large documents whole.
- They follow instructions and formats carefully.
Access from Russia#
Anthropic does not serve Russia: you cannot get a key and pay directly from Russia.
Models in the catalog#
Prices, context window and comparison with similar models:
- Claude Opus 5.5 — $4 / $20 per million tokens
- Claude Sonnet 5.5 — $2 / $10 per million tokens
- Claude Haiku 5.5 — $0.1 / $0.5 per million tokens
- Claude Fable 5.1 — $10 / $50 per million tokens
- Claude Opus 5 — $5 / $25 per million tokens
How to connect in SKILLOK#
Claude models work in SKILLOK through OpenRouter: connect an OpenRouter key and pick an anthropic/… model.
In detail — Connecting in SKILLOK.
Prices#
Prices per million input and output tokens are on the official page. Through OpenRouter the prices are the same or close; how much you spent is shown in Settings → AI.
Was this helpful?