Skip to content
ModelCap

Inference provider

Azure: AI models and API pricing

Every tracked model Azure serves through OpenRouter, with Azure'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 11 August 2026

Azure serves 39 tracked models through 52 endpoints as of 11 August 2026; the highest-ranked is Claude Fable 5 (ModelCap Index #1); mean measured uptime is 99.94%.

Models served
39
On the ModelCap Index
15
Cheapest output price
$0.40/1M

Language models on Azure (39)

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

Language models served by Azure, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Claude Fable 5Anthropic#183.1$10.00$50.001M——1
2Claude Opus 5Anthropic#279.6$5.00$25.001M——1
3GPT-5.6 SolOpenAI#777.3$5.00$30.001M—100.0%2
4GPT-5.2 ChatOpenAI#974.1$1.75$14.00128K——1
5GPT-5.5OpenAI#1073.9$5.00$30.001M—99.89%2
6Claude Sonnet 5Anthropic#1470.0$2.00$10.001M—99.90%1
7GPT-5.6 TerraOpenAI#1569.5$2.00$12.001M—99.77%2
8GPT-5.6 LunaOpenAI#1963.3$0.20$1.201M—100.0%2
9GPT-5.4 MiniOpenAI#2162.4$0.75$4.50400K—99.94%1
10Claude Haiku 4.5Anthropic#3651.0$1.00$5.00200K——1
11GPT-5.4 NanoOpenAI#3946.6$0.20$1.25400K—100.0%1
12GPT-5.3-CodexOpenAI#4544.1$1.75$14.00400K——1
13GPT-5.1-Codex-MiniOpenAI#6435.5$0.25$2.00400K—100.0%1
14GPT-5.1-Codex-MaxOpenAI#18621.9$1.25$10.00400K——1
15GPT-4o-miniOpenAI#2280.0$0.15$0.60128K—100.0%2
16Claude Opus 4.5Anthropic—$5.00$25.00200K——1
17Claude Opus 4.6Anthropic—$5.00$25.001M——1
18Claude Opus 4.7Anthropic—$5.00$25.001M——1
19Claude Opus 4.8Anthropic—$5.00$25.001M——1
20Claude Sonnet 4.5Anthropic—$3.00$15.00200K——1
21Claude Sonnet 4.6Anthropic—$3.00$15.001M——1
22GPT-3.5 Turbo (older v0613)OpenAI—$1.00$2.004K——1
23GPT-3.5 Turbo 16kOpenAI—$3.00$4.0016K——1
24GPT-4OpenAI—$30.00$60.008K——1
25GPT-4.1OpenAI—$2.00$8.001M—100.0%2
26GPT-4.1 MiniOpenAI—$0.40$1.601M—100.0%2
27GPT-4.1 NanoOpenAI—$0.10$0.401M—100.0%2
28GPT-4oOpenAI—$2.50$10.00128K—100.0%1
29GPT-4o (2024-05-13)OpenAI—$5.00$15.00128K——1
30GPT-4o (2024-08-06)OpenAI—$2.50$10.00128K—99.54%1
31GPT-5OpenAI—$1.25$10.00400K——2
32GPT-5 MiniOpenAI—$0.25$2.00400K—100.0%2
33GPT-5 NanoOpenAI—$0.05$0.40400K—100.0%2
34GPT-5.1OpenAI—$1.25$10.00400K—100.0%2
35GPT-5.1-CodexOpenAI—$1.25$10.00400K—100.0%1
36GPT-5.2OpenAI—$1.75$14.00400K—100.0%1
37GPT-5.2-CodexOpenAI—$1.75$14.00400K——1
38GPT-5.4OpenAI—$2.50$15.001M—100.0%2
39GPT-5.4 ProOpenAI—$30.00$1801M——1

Azure on ModelCap: common questions

How many AI models does Azure serve?

39 tracked models as of 11 August 2026: 39 language models (15 with a public ModelCap Index position), across 52 live endpoints observed through OpenRouter.

What is the best model available on Azure?

Claude Fable 5 from Anthropic is the highest-ranked language model Azure serves, at ModelCap Index position #1 and $50.00 per 1M output tokens on Azure. The table lists every model in Index order.

What is the cheapest model on Azure?

GPT-4.1 Nano at $0.40 per 1M output tokens ($0.10 per 1M input), the lowest positive language-token price Azure lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Azure model has the largest context window?

GPT-5.6 Sol, served with a 1M-token context window on Azure. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Azure?

Mean measured uptime across Azure endpoints is 99.94% 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 Azure prices come from?

From the OpenRouter catalogue entry for each Azure endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Azure 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?

It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further