Anthropic
API Claude
Anthropic's Claude line — three models split by capability and by writing style.
3
modelos na linha
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.
Resumo
- A partir de
- $1.01 / 1 milhão de tokens
Modelos desta família
| Modelo | A partir de | Modos | Abrir |
|---|---|---|---|
| Claude Sonnet 5Anthropic's balanced model for coding, agentic workflows and everyday reasoning. Text and image input, long context. | $1.01/ 1 milhão de tokens | — | AbrirDocs |
| Claude Opus 5Anthropic's most capable model for complex reasoning, coding and agentic work. | $3.02/ 1 milhão de tokens | — | AbrirDocs |
| Claude Fable 5Anthropic model tuned for long-form writing and narrative work. | $3.63/ 1 milhão de tokens | — | AbrirDocs |
Preços
| Modelo | Opção | Preço |
|---|---|---|
| Claude Sonnet 5 | input | $1.01/ 1 milhão de tokens |
| Claude Sonnet 5 | output | $5.04/ 1 milhão de tokens |
| Claude Sonnet 5 | cacheRead | $0.101/ 1 milhão de tokens |
| Claude Sonnet 5 | cacheWrite | $1.18/ 1 milhão de tokens |
| Claude Opus 5 | input | $3.02/ 1 milhão de tokens |
| Claude Opus 5 | output | $15.12/ 1 milhão de tokens |
| Claude Opus 5 | cacheRead | $0.302/ 1 milhão de tokens |
| Claude Opus 5 | cacheWrite | $3.78/ 1 milhão de tokens |
| Claude Fable 5 | input | $3.63/ 1 milhão de tokens |
| Claude Fable 5 | output | $18.17/ 1 milhão de tokens |
| Claude Fable 5 | cacheRead | $0.363/ 1 milhão de tokens |
| Claude Fable 5 | cacheWrite | $4.54/ 1 milhão de tokens |
Qual escolher
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.
Pontos fortes
- 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.
Limitações
- 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.
A descrição do próprio fornecedor sobre esta linha: Anthropic — Claude