GPT-4o

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

For benchmarking against other models, it was briefly called "im-also-a-good-gpt2-chatbot"

#multimodal

openai/gpt-4o

Organization: OpenAI
Family: gpt
Providers: 17
Context: 128,000
Output limit: 16,384
Knowledge: 2023-09
Release: 2024-05-13
Updated: 2024-08-06
Weights: Closed
Input: text, image, pdf
Output: text
Capabilities: Tools, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

19 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Abacus	gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
Azure	gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	—	View
Azure Cognitive Services	gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	—	View
Cloudflare AI Gateway	openai/gpt-4o	128,000	16,384	$1.25 / $5.00	No	Yes	Yes	View
Cortecs	gpt-4o	128,000	16,000	$2.659 / $10.635	No	Yes	No	View
DevPass (LLM Gateway)	gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
Eden AI	openai/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
Impossibl	openai/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
Kilo Gateway	openai/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
LLM Gateway	azure/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	No	View
LLM Gateway	openai/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
Merge Gateway	openai/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
NanoGPT	openai/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	No	View
Ofox	openai/gpt-4o	128,000	16,384	$2.00 / $8.00	No	Yes	Yes	View
Azurevia OpenRouter	openai/gpt-4o unknown	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
OpenAIvia OpenRouter	openai/gpt-4o unknown	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
OrcaRouter	openai/gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
Pioneer	gpt-4o	128,000	16,384	$2.50 / $10.00	No	Yes	Yes	View
Vercel AI Gateway	openai/gpt-4o-fast	128,000	16,384	$4.25 / $17.00	No	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$1.25Per 1M input tokens

Output from$5.00Per 1M output tokens

Available offers19Across 17 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 2 lowest-priced configurations

InputOutput

Azureazure

$2.50$10.00

OpenAIopenai

$2.50$10.00

openai/gpt-4oObserved Oct 4, 2026, 11:31 AM UTC

Input: $2.50
Output: $10.00
Cache read: $1.25

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Azureazure	$2.50	$10.00	—	—
OpenAIopenai	$2.50	$10.00	$1.25	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 2 endpoints

P50P75P90P99

Azureazure

946–4,262.43 ms

OpenAIopenai

555–2,791.78 ms

All latency percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
Azureazure	946 ms	1,198 ms	2,414.4 ms	4,262.43 ms
OpenAIopenai	555 ms	683 ms	972 ms	2,791.78 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 2 endpoints

P50P75P90P99

Azureazure

68–213.8 t/s

OpenAIopenai

79–194.35 t/s

All throughput percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
Azureazure	68 t/s	94 t/s	128 t/s	213.8 t/s
OpenAIopenai	79 t/s	100 t/s	135 t/s	194.35 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 2 endpoints

Endpoint5 minutes30 minutes24 hours

AzureazureObserved Oct 4, 2026, 11:31 AM UTC

100%

99.77%

99.89%

OpenAIopenaiObserved Oct 4, 2026, 11:31 AM UTC

100%

99.93%

99.97%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

openai/gpt-4oObserved Oct 4, 2026, 11:31 AM UTC

Design Arena	Category	Elo	Win rate	Rank
models	3d	884	39.2%	113
models	codecategories	866	34.8%	125
models	dataviz	864	36%	123
models	gamedev	919	42.3%	122
models	uicomponent	892	38.1%	122
models	website	838	31.5%	132

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineOpenAI: GPT-4o

43.778%

gpqa diamondOpenAI: GPT-4o

50.561%

Evaluation	Configuration	Source	Results	Details
models · uicomponent	GPT-4oopenai/gpt-4o	Design Arena	892 Elo	Details
models · 3d	GPT-4oopenai/gpt-4o	Design Arena	884 Elo	Details
models · dataviz	GPT-4oopenai/gpt-4o	Design Arena	864 Elo	Details
tau bench verified airline	OpenAI: GPT-4oopenai/gpt-4o	OpenRouter	43.778%	Details
models · website	GPT-4oopenai/gpt-4o	Design Arena	838 Elo	Details
models · codecategories	GPT-4oopenai/gpt-4o	Design Arena	866 Elo	Details
gpqa diamond	OpenAI: GPT-4oopenai/gpt-4o	OpenRouter	50.561%	Details
models · gamedev	GPT-4oopenai/gpt-4o	Design Arena	919 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	openai/gpt-4o	2–9 turns	$0.048241	Details
Hermes Agent	openai/gpt-4o	10–49 turns	$0.269641	Details
Hermes Agent	openai/gpt-4o	1 turn	$0.010027	Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

openai/gpt-4oObserved Oct 4, 2026, 11:31 AM UTC

Context: 128,000
Maximum output: 16,384
Tokenizer: GPT
Input: text, image, file
Output: text
Moderation: Yes
Knowledge cutoff: 2023-10-31
Added to OpenRouter: 2024-05-13

Base URLhttps://openrouter.ai/api/v1

Model IDopenai/gpt-4o

Version IDopenai/gpt-4o

Supported parameters

frequency_penalty
logit_bias
logprobs
max_completion_tokens
max_tokens
prediction
presence_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_logprobs
top_p
web_search_options

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does GPT-4o cost?

Listed rates start at $1.25 per million input tokens and $5.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GPT-4o?

There are 19 cataloged offers across 17 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 128,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · e1d275dab203
Sep 12, 2026 · d29578cc307e