Skip to content
ModelCap

Inference provider

Anthropic: AI models and API pricing

Every tracked model Anthropic serves through OpenRouter, with Anthropic's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

Anthropic serves 13 tracked models through 16 endpoints as of 1 October 2026; the highest-ranked is Claude Sonnet 5.5 (ModelCap Index #1); mean measured uptime is 100.0%.

Models served
13
On the ModelCap Index
4
Cheapest output price
$5.00/1M

Language models on Anthropic (13)

Ranked models first, in ModelCap Index order. Prices are the lowest Anthropic lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Anthropic, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Claude Sonnet 5.5Anthropic#191.6$2.00$10.001M—100.0%1
2Claude Opus 5.5Anthropic#288.0$4.00$20.001M—100.0%2
3Claude Fable 5.1Anthropic#486.9$10.00$50.001M—99.91%1
4Claude Haiku 4.5Anthropic#7559.8$1.00$5.00200K—100.0%1
5Claude Fable 5Anthropic—$10.00$50.001M—100.0%1
6Claude Opus 4.5Anthropic—$5.00$25.00200K—100.0%1
7Claude Opus 4.6Anthropic—$5.00$25.001M—100.0%1
8Claude Opus 4.7Anthropic—$5.00$25.001M——1
9Claude Opus 4.8Anthropic—$5.00$25.001M—99.93%2
10Claude Opus 5Anthropic—$5.00$25.001M—100.0%2
11Claude Sonnet 4.5Anthropic—$3.00$15.001M—99.79%1
12Claude Sonnet 4.6Anthropic—$3.00$15.001M—100.0%1
13Claude Sonnet 5Anthropic—$2.00$10.001M—100.0%1

Anthropic on ModelCap: common questions

How many AI models does Anthropic serve?

13 tracked models as of 1 October 2026: 13 language models (4 with a public ModelCap Index position), across 16 live endpoints observed through OpenRouter.

What is the best model available on Anthropic?

Claude Sonnet 5.5 from Anthropic is the highest-ranked language model Anthropic serves, at ModelCap Index position #1 and $10.00 per 1M output tokens on Anthropic. The table lists every model in Index order.

What is the cheapest model on Anthropic?

Claude Haiku 4.5 at $5.00 per 1M output tokens ($1.00 per 1M input), the lowest positive language-token price Anthropic lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Anthropic model has the largest context window?

Claude Sonnet 5.5, served with a 1M-token context window on Anthropic. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Anthropic?

Mean measured uptime across Anthropic endpoints is 100.0% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Anthropic prices come from?

From the OpenRouter catalogue entry for each Anthropic endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Anthropic exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 1 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further