Anthropic
Claude API
Anthropic's Claude line — three models split by capability and by writing style.
3
моделей в линейке
The Claude models we serve split along two axes rather than one: Sonnet and Opus are the balanced and the most-capable tiers, while Fable is tuned specifically for long-form writing and narrative work. All three speak the OpenAI protocol here and all support prompt caching, with cached reads at a tenth of fresh input.
Коротко
- От
- 1.01 coins / 1 млн токенов
Модели этого семейства
| Модель | От | Режимы | Открыть |
|---|---|---|---|
| Claude Sonnet 5Anthropic's balanced model for coding, agentic workflows and everyday reasoning. Text and image input, long context. | 1.01 coins/ 1 млн токенов | — | ОткрытьДокументация |
| Claude Opus 5Anthropic's most capable model for complex reasoning, coding and agentic work. | 3.02 coins/ 1 млн токенов | — | ОткрытьДокументация |
| Claude Fable 5Anthropic model tuned for long-form writing and narrative work. | 3.63 coins/ 1 млн токенов | — | ОткрытьДокументация |
Цены
| Модель | Вариант | Цена |
|---|---|---|
| Claude Sonnet 5 | input | 1.01 coins/ 1 млн токенов |
| Claude Sonnet 5 | output | 5.04 coins/ 1 млн токенов |
| Claude Sonnet 5 | cacheRead | 0.101 coins/ 1 млн токенов |
| Claude Sonnet 5 | cacheWrite | 1.18 coins/ 1 млн токенов |
| Claude Opus 5 | input | 3.02 coins/ 1 млн токенов |
| Claude Opus 5 | output | 15.12 coins/ 1 млн токенов |
| Claude Opus 5 | cacheRead | 0.302 coins/ 1 млн токенов |
| Claude Opus 5 | cacheWrite | 3.78 coins/ 1 млн токенов |
| Claude Fable 5 | input | 3.63 coins/ 1 млн токенов |
| Claude Fable 5 | output | 18.17 coins/ 1 млн токенов |
| Claude Fable 5 | cacheRead | 0.363 coins/ 1 млн токенов |
| Claude Fable 5 | cacheWrite | 4.54 coins/ 1 млн токенов |
Что выбрать
Claude Sonnet 5
The default. Coding, agentic workflows and everyday reasoning with text and image input, at a third of Opus's price.
Claude Opus 5
Complex reasoning, hard coding problems and long agentic runs where capability matters more than cost.
Claude Fable 5
Long-form writing and narrative work — the tier tuned for prose rather than for reasoning benchmarks.
Сильные стороны
- A writing-specialised tier alongside the general ones, which most families do not offer.
- Prompt caching on all three, with cached reads at a tenth of the input price.
- Sonnet takes image input as well as text, at the lowest price in the line.
- OpenAI-protocol compatible, so existing client code works unchanged.
Ограничения
- Output tokens cost five times input across the line, so long generations are expensive.
- Cache writes are billed above fresh input, so caching only pays back on reuse.
- Fable is the most expensive tier per input token despite not being the most capable one.
Описание линейки от самого вендора: Anthropic — Claude