New: Nano Banana 2.1Try the model
API Stock
All models

Anthropic

Claude API

Anthropic's Claude line — six models across the Sonnet, Opus and Fable tiers, in two generations.

At a glance

From
$0.3 / 1M tokens

Models in this family

ModelFromModesOpen
Claude Sonnet 5Anthropic's balanced model for coding, agentic workflows and everyday reasoning. Text and image input, long context.$0.3/ 1M tokens—OpenDocs
Claude Sonnet 5.5Upgraded Sonnet-class model for agentic coding, tool use and everyday professional work — faster than Claude Sonnet 5.$0.9/ 1M tokens—OpenDocs
Claude Fable 5Anthropic model tuned for long-form writing and narrative work.$1.5/ 1M tokens—OpenDocs
Claude Opus 5.5Successor to Claude Opus 5 for demanding reasoning, coding and long-running agentic work.$1.8/ 1M tokens—OpenDocs
Claude Opus 5Anthropic's most capable model for complex reasoning, coding and agentic work.$3/ 1M tokens—OpenDocs
Claude Fable 5.1Anthropic's Mythos-class model for autonomous knowledge work and coding, with a 1M-token context window and text, image and file input.$10/ 1M tokens—OpenDocs

Pricing

ModelOptionPrice
Claude Sonnet 5input$0.3/ 1M tokens
Claude Sonnet 5output$1.5/ 1M tokens
Claude Sonnet 5cacheRead$0.03/ 1M tokens
Claude Sonnet 5cacheWrite$0.375/ 1M tokens
Claude Sonnet 5.5input$0.9/ 1M tokens
Claude Sonnet 5.5output$4.5/ 1M tokens
Claude Sonnet 5.5cacheRead$0.09/ 1M tokens
Claude Sonnet 5.5cacheWrite$1.13/ 1M tokens
Claude Fable 5input$1.5/ 1M tokens
Claude Fable 5output$7.5/ 1M tokens
Claude Fable 5cacheRead$0.15/ 1M tokens
Claude Fable 5cacheWrite$1.88/ 1M tokens
Claude Opus 5.5input$1.8/ 1M tokens
Claude Opus 5.5output$9/ 1M tokens
Claude Opus 5.5cacheRead$0.09/ 1M tokens
Claude Opus 5.5cacheWrite$2.25/ 1M tokens
Claude Opus 5input$3/ 1M tokens
Claude Opus 5output$15/ 1M tokens
Claude Opus 5cacheRead$0.3/ 1M tokens
Claude Opus 5cacheWrite$3.75/ 1M tokens
Claude Fable 5.1input$10/ 1M tokens
Claude Fable 5.1output$50/ 1M tokens
Claude Fable 5.1cacheRead$0.25/ 1M tokens
Claude Fable 5.1cacheWrite$12.5/ 1M tokens

Which one to pick

  • Claude Sonnet 5

    The default. Coding, agentic workflows and everyday reasoning with text and image input, at a tenth of Opus 5's price.

  • Claude Sonnet 5.5

    The upgraded Sonnet for agentic coding, tool use and everyday professional work — faster than Sonnet 5, at three times its price.

  • Claude Fable 5

    Long-form writing and narrative work — the tier tuned for prose rather than for reasoning benchmarks.

  • Claude Opus 5.5

    The successor to Opus 5 for demanding reasoning, coding and long-running agentic work — and priced lower than Opus 5.

  • Claude Opus 5

    Complex reasoning, hard coding problems and long agentic runs where capability matters more than cost.

  • Claude Fable 5.1

    Autonomous knowledge work and coding on a 1M-token context with text, image and file input — the most expensive model in the line, for work that justifies it.

Strengths

  • A writing-specialised tier (Fable 5) alongside the general ones, which most families do not offer.
  • Prompt caching on every model, with cached reads at a tenth of the input price or less.
  • Sonnet 5 takes image input as well as text, at the lowest price in the line.
  • Two generations to choose from: Opus 5.5 costs less than Opus 5, so the newer model is not automatically the dearer one.
  • OpenAI-protocol compatible, so existing client code works unchanged.

Limitations

  • 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 5.1 is the most expensive model in the line by a wide margin — more than three times Opus 5, the next most expensive.

Frequently asked questions

How much does the Claude API cost?

API Stock bills per use from one prepaid balance, with no subscription. Current prices: Claude Sonnet 5 — $0.3 per 1M input tokens and $1.5 per 1M output tokens; Claude Sonnet 5.5 — $0.9 per 1M input tokens and $4.5 per 1M output tokens; Claude Fable 5 — $1.5 per 1M input tokens and $7.5 per 1M output tokens; Claude Opus 5.5 — $1.8 per 1M input tokens and $9 per 1M output tokens; Claude Opus 5 — $3 per 1M input tokens and $15 per 1M output tokens; Claude Fable 5.1 — $10 per 1M input tokens and $50 per 1M output tokens.

Which Claude model is the cheapest?

Claude Sonnet 5 is the cheapest at $0.3 per 1M input tokens. The most expensive tier, Claude Fable 5.1, costs $10 per 1M input tokens.

Does the Claude API support prompt caching?

Yes. Cached input tokens are billed at a lower rate: Claude Sonnet 5 — $0.03 instead of $0.3 per 1M tokens; Claude Sonnet 5.5 — $0.09 instead of $0.9 per 1M tokens; Claude Fable 5 — $0.15 instead of $1.5 per 1M tokens; Claude Opus 5.5 — $0.09 instead of $1.8 per 1M tokens; Claude Opus 5 — $0.3 instead of $3 per 1M tokens; Claude Fable 5.1 — $0.25 instead of $10 per 1M tokens.

Can I use the Claude API with the OpenAI or Anthropic SDK?

Yes. Claude models accept the OpenAI and Anthropic request format: set the SDK's base URL to https://api.api-stock.com/api/v1 and use your API Stock API key. Switching between models only changes the model id.

How do I get an API key for Claude?

Create an account and API key on API Stock, then fund your balance. The same key works with Claude and other catalog models.

The vendor's own description of this line: Anthropic — Claude

Guides