Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

Anthropic

Short answer

Anthropic's Claude models on this feed are hosted APIs with text, image, and file input. The practical ladder is Fable for the hardest technical work, Sonnet for everyday coding and writing, and Haiku for high-volume drafts. Opus sits between Fable and Sonnet on price.

Lab site · Filter the full catalogue to Anthropic

What the top models are good for

1. Claude Fable 5.2

Flagship · $8.00 in · $40.00 out · 1,000,000 tokens

Guide note · 19 Nov 2026

OpenRouter calls Claude Fable 5.2 Anthropic's most capable model for demanding technical work, with gains in coding, reasoning, and vision over Fable 5.1. It is the model to spend money on when the problem is actually hard.

  • Hard coding, reasoning, and vision
  • Text, image, and file input
  • A million-token context

What it is good for

Untangle a production incident

Paste the timeline, the logs, and a screenshot of the dashboard. Ask for hypotheses you can falsify, not for a heroic root cause. The listing is aimed at this kind of technical work.

Claude Fable 5.2 is listed at $8.00 input and $40.00 output per million tokens, with a 1,000,000-token context window.

Read a dense contract for flags, not for legal advice

File input and a long window can hold the agreement. Ask for dates, parties, and clauses that shift liability. A person who owns the decision still reads those clauses.

Claude Fable 5.2 is listed at $8.00 input and $40.00 output per million tokens, with a 1,000,000-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

2. Claude Sonnet 5.5

Everyday · $2.00 in · $10.00 out · 1,000,000 tokens

Guide note · 19 Nov 2026

OpenRouter describes Claude Sonnet 5.5 as the Sonnet-class model for well-scoped everyday work, especially building features, fixing bugs, and producing finished text. It is the reviewed default for most coding and writing.

  • Everyday coding and editing
  • Text, image, and file input
  • A million-token context

What it is good for

Build a small web app

A written spec for a small app — accounts, a form, a list — matches the listing's 'build the feature, fix the bug' brief. Keep the spec shorter than your ambition.

Claude Sonnet 5.5 is listed at $2.00 input and $10.00 output per million tokens, with a 1,000,000-token context window.

Edit a 2,000-word essay for structure

Ask for a reverse outline and the three weakest paragraphs. Everyday writing is the job. The long window means you can include the brief and the draft together.

Claude Sonnet 5.5 is listed at $2.00 input and $10.00 output per million tokens, with a 1,000,000-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

3. Claude Haiku 5.5

Budget · $0.10 in · $0.50 out · 1,000,000 tokens

Guide note · 19 Nov 2026

OpenRouter describes Claude Haiku 5.5 as Anthropic's small, fast model for high-volume work such as summarisation, subagents, and browser use. Stronger than Haiku 4.5 at coding, on the listing's own words, and far cheaper than Sonnet.

  • Summaries and routing
  • Subagent steps
  • Text, image, and file input at a low rate

What it is good for

Cheap bulk customer-email triage

Route the message and draft two sentences. The listing names high-volume summarisation and subagents. Sample a hundred outputs before you trust the queue.

Claude Haiku 5.5 is listed at $0.10 input and $0.50 output per million tokens, with a 1,000,000-token context window.

Summarise a meeting transcript you paste in

A one-hour transcript is a summarisation job, which the listing names, and it fits the million-token window easily.

Claude Haiku 5.5 is listed at $0.10 input and $0.50 output per million tokens, with a 1,000,000-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

Every current row

16 Anthropic rows on the feed.
ModelKindContextInputOutputListedGuide
Claude Fable 5 Chat 1,000,000 $10.00 $50.00 9 Jun 2026 New, not yet reviewed
Claude Fable 5.1 Chat 1,000,000 $10.00 $50.00 1 Sep 2026 New, not yet reviewed
Claude Fable 5.2 Chat 1,000,000 $8.00 $40.00 9 Nov 2026 Reviewed
Claude Haiku 4.5 Chat 200,000 $1.00 $5.00 15 Oct 2025 New, not yet reviewed
Claude Haiku 5.5 Chat 1,000,000 $0.10 $0.50 7 Oct 2026 Reviewed
Claude Opus 4.1 Chat 200,000 $15.00 $75.00 5 Aug 2025 New, not yet reviewed
Claude Opus 4.5 Chat 200,000 $5.00 $25.00 24 Nov 2025 New, not yet reviewed
Claude Opus 4.6 Chat 1,000,000 $5.00 $25.00 4 Feb 2026 New, not yet reviewed
Claude Opus 4.7 Chat 1,000,000 $5.00 $25.00 16 Apr 2026 New, not yet reviewed
Claude Opus 4.8 Chat 1,000,000 $5.00 $25.00 27 May 2026 New, not yet reviewed
Claude Opus 5 Chat 1,000,000 $5.00 $25.00 24 Jul 2026 New, not yet reviewed
Claude Opus 5.5 Chat 1,000,000 $4.00 $20.00 22 Sep 2026 New, not yet reviewed
Claude Sonnet 4.5 Chat 1,000,000 $3.00 $15.00 29 Sep 2025 New, not yet reviewed
Claude Sonnet 4.6 Chat 1,000,000 $3.00 $15.00 17 Feb 2026 New, not yet reviewed
Claude Sonnet 5 Chat 1,000,000 $2.00 $10.00 30 Jun 2026 New, not yet reviewed
Claude Sonnet 5.5 Chat 1,000,000 $2.00 $10.00 28 Sep 2026 Reviewed

Questions

Which Anthropic model should I start with?

For most people, start with Claude Fable 5.2, then drop to the next model on this page when the task is routine. Read the cheaper-model note under each example.

Are the examples benchmarks?

No. They are concrete tasks used to explain fit. The prices next to them are live figures from the feed. The judgment is a guide note.