Discover/AI APIs & Developer Services/Anthropic API

Anthropic API

by Anthropic PBC

Save Open Anthropic API

The Launchpad take

Verdict

Claude models via API

Chat completions; long-context analysis; tool use; computer use; batch processing; embeddings

Best for

DevelopersenterprisesAI product builderssafety-focused teamsresearchers

Quick facts

Free tier: No ongoing free API tier: you pay per token used. Anthropic's pricing docs say new users receive a small amount of free credits to test the API. The free Claude chat plan is a separate product (see the Claude listing).
Starting price: $0.10 input / $0.50 output per million tokens
Platforms: API, Web, Desktop, Mobile
more
API; Claude chat on web, desktop and mobile.
Company: Anthropic PBC

Ready to try Anthropic API? Start with the getting-started guide.

Pricing

Base input and output token prices (USD) from the model pricing table in Anthropic's detailed pricing docs, linked from claude.com/pricing. Cache writes and hits are priced separately. Batch API: 50% off input and output; US-only inference: 1.1x. Legacy models are listed on the same page. Consumer Claude plans (Pro, Max, Team) belong to the Claude listing, not this one.

Plan	Price	Key limits
Claude Haiku 5.5	$0.10 input / $0.50 output per million tokens	For prompts up to 100,000 tokens. Prompts over 100,000 tokens: $0.50 input / $2.50 output per million tokens
Claude Sonnet 5.5	$2 input / $10 output per million tokens
Claude Opus 5.5	$4 input / $20 output per million tokens	Fast mode is 2x standard pricing
Claude Fable 5.1	$10 input / $50 output per million tokens

Prices checked 2026-10-25

Key capabilities

Works with

Text
images (input)
documents
code

Outputs

JSON API responses
streaming
batch results

API pricing

USD per million tokens, input / output. Claude Fable 5.1: $10 / $50. Claude Opus 5.5: $4 / $20. Claude Sonnet 5.5: $2 / $10. Claude Haiku 5.5: $0.10 / $0.50 for prompts up to 100,000 tokens; $0.50 / $2.50 for prompts over 100,000 tokens.

Base input / output prices from the model pricing table. Batch API: 50% off. US-only inference: 1.1x (on Haiku 5.5 also applied to the over-100,000-token prices). Opus 5.5 fast mode: 2x. Cache-write and cache-hit rates are listed per model on the same page.

Features

Claude Models on Google Cloud (Anthropic managed) is generally available as of 2026-10-22: Anthropic operates the service and acts as the data processor, billing goes on a single Google Cloud invoice, and usage draws down an existing Google Cloud commitment.

Get it

How to use Anthropic API on phones and tablets.

Mobile web: Works in a mobile browser (responsive or dedicated mobile site).

Technical details

Offline: No
API: Yes
Languages: Multilingual (strong in English + major languages)
Difficulty: Beginner-friendly
Privacy: High
Time to productivity: 1 hour
Upgrade when: Credit exhaustion; higher rate limits; prompt caching; batch API volume; fine-tuning (emerging)
Integrations: LangChain, LlamaIndex, Vercel AI SDK, AWS Bedrock
more
Google Vertex, Zapier, n8n, major frameworks

What changed

2026-10-26 · freeTier — Free tier now notes the small amount of free credits new API users receive, per Anthropic's pricing docs.
2026-10-26 · features — Added Claude Models on Google Cloud (Anthropic managed), generally available 2026-10-22, as a place to run Claude.
2026-10-25 · plans — Re-checked every API price against the model pricing table on platform.claude.com/docs/en/about-claude/pricing; values unchanged, Haiku 5.5 tier wording now matches the docs (prompts up to / over 100,000 tokens).
2026-10-25 · plans — Replaced consumer Claude plans (wrong listing) with per-token API prices from the API section of claude.com/pricing; no free API tier.
2026-10-14 · apiPricing — RA: added Batch API: 50% off. No cache or multiplier details. Consumer plans from claude.com/pricing.

Models

Last verified Oct 14, 2026. Figures that could not be confirmed on an official vendor page are marked unverified — we do not guess.

Full Claude comparison

Which one should I use?

On claude.ai, start with Sonnet for everyday writing, coding, and analysis. It is the default on the free plan.
Use Haiku when you want a fast, cheap answer and the job is simple (summaries, sorting, short rewrites).
Use Opus when the task is long and you need it to keep working without you steering every step. That needs a paid plan.
Use Fable only for the largest, longest jobs. Anthropic positions it above Opus; it uses more of your usage limit.
API developers: Anthropic currently recommends Opus 5.5 as the default, Haiku 5.5 for high-volume cheap work, and Fable 5.1 when Opus is not enough.

Claude Opus 5.5

Current

Context: 1M
Max output: 128K
API input / 1M: $4 / 1M
API output / 1M: $20 / 1M

Best for: Hard, multi-step work you would pay extra for: long coding sessions, research write-ups, and jobs that run for a while.

Paid Claude plans (Pro and Max). Official consumer guide: Free includes Haiku and Sonnet; Pro and Max add Opus and Fable.

Source: Opus 5.5 overview

Claude Sonnet 5.5

Current

Context: 1M
Max output: 128K
API input / 1M: $2 / 1M
API output / 1M: $10 / 1M

Best for: Day-to-day writing, coding, and analysis — the version most beginners should start with.

Free and paid Claude plans. Official consumer guide lists Sonnet on Free, Pro, and Max.

Source: Sonnet 5.5 overview

Claude Haiku 5.5

Current

Context: 1M
Max output: 128K
API input / 1M: $0.1 / 1M
API output / 1M: $0.5 / 1M

Best for: Quick answers, sorting, extraction, and anything you run hundreds of times.

Free and paid Claude plans. Official consumer guide lists Haiku on Free, Pro, and Max.

Source: Haiku 5.5 overview

Claude Fable 5.1

Current

Context: 1M
Max output: 128K
API input / 1M: $10 / 1M
API output / 1M: $50 / 1M

Best for: The rare job where Opus is not enough — long autonomous work you are willing to pay more for.

Paid Claude plans. Official consumer guide: Pro and Max add Fable; Anthropic’s pricing table also lists usage-credit / weekly-limit rules on Max.

Source: Models overview

Version	Context	Max out	API in / 1M	API out / 1M	Source
Claude Opus 5.5 Current`claude-opus-5-5`	1M	128K	$4 / 1M	$20 / 1M	Opus 5.5 overview
Claude Sonnet 5.5 Current`claude-sonnet-5-5`	1M	128K	$2 / 1M	$10 / 1M	Sonnet 5.5 overview
Claude Haiku 5.5 Current`claude-haiku-5-5`	1M	128K	$0.1 / 1M	$0.5 / 1M	Haiku 5.5 overview
Claude Fable 5.1 Current`claude-fable-5-1`	1M	128K	$10 / 1M	$50 / 1M	Models overview