Skip to content
ModelCap

Inference provider

OpenAI: AI models and API pricing

Every tracked model OpenAI serves through OpenRouter, with OpenAI'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

OpenAI serves 44 tracked models through 66 endpoints as of 11 August 2026; the highest-ranked is GPT-5.6 Sol (ModelCap Index #7); mean measured uptime is 98.12%.

Models served
44
On the ModelCap Index
15
Cheapest output price
$0.20/1M

Language models on OpenAI (39)

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

Language models served by OpenAI, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1GPT-5.6 SolOpenAI#777.3$2.50$15.001M—98.04%3
2GPT-5.5OpenAI#1073.9$2.50$15.001M—98.55%3
3GPT-5.6 TerraOpenAI#1569.5$0.50$3.001M—99.86%3
4GPT-5.6 LunaOpenAI#1963.3$0.05$0.301M—99.83%3
5GPT-5.4 MiniOpenAI#2162.4$0.375$2.25400K—99.48%3
6o3OpenAI#2955.4$2.00$8.00200K—100.0%1
7GPT-5.4 NanoOpenAI#3946.6$0.10$0.625400K—71.48%2
8GPT-5.3-CodexOpenAI#4544.1$1.75$14.00400K—99.30%2
9o4 MiniOpenAI#4742.5$1.10$4.40200K—100.0%1
10o3 ProOpenAI#5337.8$20.00$80.00200K——1
11GPT-5.5 ProOpenAI#6335.8$15.00$90.001M——2
12GPT-3.5 Turbo InstructOpenAI#18421.9$1.50$2.004K——1
13GPT-4o (2024-11-20)OpenAI#18521.9$2.50$10.00128K—100.0%1
14GPT-4 TurboOpenAI#18721.8$10.00$30.00128K——1
15GPT-4o-miniOpenAI#2280.0$0.15$0.60128K—100.0%1
16GPT-3.5 TurboOpenAI—$0.50$1.5016K—100.0%1
17GPT-3.5 Turbo 16kOpenAI—$3.00$4.0016K——1
18GPT-4OpenAI—$30.00$60.008K——1
19GPT-4 Turbo PreviewOpenAI—$10.00$30.00128K——1
20GPT-4.1OpenAI—$2.00$8.001M—99.20%1
21GPT-4.1 MiniOpenAI—$0.40$1.601M—99.49%1
22GPT-4.1 NanoOpenAI—$0.10$0.401M—98.47%1
23GPT-4oOpenAI—$2.50$10.00128K—100.0%1
24GPT-4o (2024-05-13)OpenAI—$5.00$15.00128K——1
25GPT-4o (2024-08-06)OpenAI—$2.50$10.00128K—100.0%1
26GPT-4o-mini (2024-07-18)OpenAI—$0.15$0.60128K—100.0%1
27GPT-5OpenAI—$1.25$10.00400K—99.92%1
28GPT-5 CodexOpenAI—$0.625$5.00400K——1
29GPT-5 MiniOpenAI—$0.125$1.00400K—99.92%2
30GPT-5 NanoOpenAI—$0.025$0.20400K—97.66%2
31GPT-5 ProOpenAI—$15.00$120400K——1
32GPT-5.1OpenAI—$0.625$5.00400K—99.20%3
33GPT-5.2OpenAI—$0.875$7.00400K—97.30%3
34GPT-5.2 ProOpenAI—$21.00$168400K——1
35GPT-5.4OpenAI—$1.25$7.501M—99.66%3
36GPT-5.4 ProOpenAI—$15.00$90.001M——2
37o1OpenAI—$15.00$60.00200K——1
38o1-proOpenAI—$150$600200K——1
39o3 MiniOpenAI—$1.10$4.40200K—100.0%1

Image, audio and video models on OpenAI (5)

Media models are ranked within their own catalogues; token prices do not apply.

Image, audio and video models served by OpenAI
#ModelContextQuantizationUptime (30 min)Endpoints
1GPT-5.4 Image 2OpenAI272K—100.0%1
2GPT-5 Image MiniOpenAI400K——1
3GPT-5 ImageOpenAI400K——1
4GPT Audio MiniOpenAI128K—100.0%1
5GPT AudioOpenAI128K—100.0%1

OpenAI on ModelCap: common questions

How many AI models does OpenAI serve?

44 tracked models as of 11 August 2026: 39 language models (15 with a public ModelCap Index position) and 5 image, audio or video models, across 66 live endpoints observed through OpenRouter.

What is the best model available on OpenAI?

GPT-5.6 Sol from OpenAI is the highest-ranked language model OpenAI serves, at ModelCap Index position #7 and $15.00 per 1M output tokens on OpenAI. The table lists every model in Index order.

What is the cheapest model on OpenAI?

GPT-5 Nano at $0.20 per 1M output tokens ($0.025 per 1M input), the lowest positive language-token price OpenAI lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which OpenAI model has the largest context window?

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

How reliable is OpenAI?

Mean measured uptime across OpenAI endpoints is 98.12% 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 OpenAI prices come from?

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