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 2 October 2026

Azure serves 50 tracked models through 89 endpoints as of 2 October 2026; the highest-ranked is Claude Sonnet 5.5 (ModelCap Index #1); mean measured uptime is 99.84%.

Models served

On the ModelCap Index

Cheapest output price

$0.40/1M

Language models on Azure (50)

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
#	Model	ModelCap Index	Input $/1M	Output $/1M	Context	Quantization	Uptime (30 min)	Endpoints
1	Claude Sonnet 5.5Anthropic	#191.7	$2.00	$10.00	1M	—	100.0%	2
2	Claude Opus 5.5Anthropic	#288.0	$4.00	$20.00	1M	—	100.0%	2
3	GPT-6.1 SolOpenAI	#388.0	$2.00	$10.00	1M	—	100.0%	3
4	Claude Fable 5.1Anthropic	#486.9	$10.00	$50.00	1M	—	—	1
5	GPT-6 AstraOpenAI	#783.0	$10.00	$50.00	1M	—	100.0%	2
6	GPT-5.5OpenAI	#1479.7	$5.00	$30.00	1M	—	100.0%	3
7	GPT-5.6 TerraOpenAI	#2277.2	$2.00	$12.00	1M	—	100.0%	3
8	GPT-6 LunaOpenAI	#3171.3	$0.10	$0.50	1M	—	100.0%	3
9	GPT-5.4 MiniOpenAI	#3669.5	$0.75	$4.50	400K	—	100.0%	2
10	Claude Haiku 4.5Anthropic	#7459.8	$1.00	$5.00	200K	—	100.0%	1
11	GPT-5.4 NanoOpenAI	#8456.5	$0.20	$1.25	400K	—	100.0%	2
12	GPT-4o-miniOpenAI	#16138.8	$0.15	$0.60	128K	—	99.91%	2
13	GPT-4o (2024-08-06)OpenAI	#16537.9	$2.50	$10.00	128K	—	99.80%	1
14	GPT-5.1-Codex-MaxOpenAI	—	$1.25	$10.00	400K	—	—	1
15	GPT-5.1-Codex-MiniOpenAI	—	$0.25	$2.00	400K	—	100.0%	1
16	GPT-5.3-CodexOpenAI	—	$1.75	$14.00	400K	—	—	1
17	GPT-6 Astra ProOpenAI	—	$10.00	$50.00	1M	—	—	2
18	GPT-6 Luna ProOpenAI	—	$0.10	$0.50	1M	—	100.0%	3
19	GPT-6.1 Sol ProOpenAI	—	$2.00	$10.00	1M	—	100.0%	3
20	Claude Fable 5Anthropic	—	$10.00	$50.00	1M	—	—	1
21	Claude Opus 4.5Anthropic	—	$5.00	$25.00	200K	—	—	1
22	Claude Opus 4.6Anthropic	—	$5.00	$25.00	1M	—	—	1
23	Claude Opus 4.7Anthropic	—	$5.00	$25.00	1M	—	—	1
24	Claude Opus 4.8Anthropic	—	$5.00	$25.00	1M	—	—	2
25	Claude Opus 5Anthropic	—	$5.00	$25.00	1M	—	100.0%	2
26	Claude Sonnet 4.5Anthropic	—	$3.00	$15.00	200K	—	—	1
27	Claude Sonnet 4.6Anthropic	—	$3.00	$15.00	1M	—	—	1
28	Claude Sonnet 5Anthropic	—	$2.00	$10.00	1M	—	99.80%	2
29	DeepSeek V4 Flash 0423DeepSeek	—	$0.21	$0.56	1M	—	94.30%	1Open weights
30	DeepSeek V4 Pro 0423DeepSeek	—	$1.91	$3.83	1M	—	99.48%	1Open weights
31	GPT-3.5 Turbo 16kOpenAI	—	$3.00	$4.00	16K	—	—	1
32	GPT-4OpenAI	—	$30.00	$60.00	8K	—	—	1
33	GPT-4.1OpenAI	—	$2.00	$8.00	1M	—	100.0%	2
34	GPT-4.1 MiniOpenAI	—	$0.40	$1.60	1M	—	100.0%	2
35	GPT-4.1 NanoOpenAI	—	$0.10	$0.40	1M	—	100.0%	2
36	GPT-4oOpenAI	—	$2.50	$10.00	128K	—	99.89%	1
37	GPT-4o (2024-05-13)OpenAI	—	$5.00	$15.00	128K	—	—	1
38	GPT-5OpenAI	—	$1.25	$10.00	400K	—	99.75%	2
39	GPT-5 MiniOpenAI	—	$0.25	$2.00	400K	—	100.0%	2
40	GPT-5 NanoOpenAI	—	$0.05	$0.40	400K	—	100.0%	2
41	GPT-5.1OpenAI	—	$1.25	$10.00	400K	—	100.0%	2
42	GPT-5.1-CodexOpenAI	—	$1.25	$10.00	400K	—	—	1
43	GPT-5.2OpenAI	—	$1.75	$14.00	400K	—	100.0%	1
44	GPT-5.2-CodexOpenAI	—	$1.75	$14.00	400K	—	100.0%	1
45	GPT-5.4OpenAI	—	$2.50	$15.00	1M	—	100.0%	3
46	GPT-5.4 ProOpenAI	—	$30.00	$180	1M	—	—	1
47	GPT-5.6 LunaOpenAI	—	$0.20	$1.20	1M	—	100.0%	3
48	GPT-5.6 SolOpenAI	—	$4.00	$20.00	1M	—	100.0%	3
49	GPT-6 SolOpenAI	—	$2.00	$10.00	1M	—	100.0%	3
50	GPT-6 Sol ProOpenAI	—	$2.00	$10.00	1M	—	—	3

Azure on ModelCap: common questions

How many AI models does Azure serve?

50 tracked models as of 2 October 2026: 50 language models (13 with a public ModelCap Index position), across 89 live endpoints observed through OpenRouter.

What is the best model available on Azure?

Claude Sonnet 5.5 from Anthropic is the highest-ranked language model Azure serves, at ModelCap Index position #1 and $10.00 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-6.1 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 99.84% 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?

This page uses the published ModelCap snapshot dated 2 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.