How much does OpenAI: GPT-4o cost per 1M tokens?

OpenAI: GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on the standard tier. Cached input is $1.25 per 1M.

What is OpenAI: GPT-4o's context window?

OpenAI: GPT-4o accepts up to 128,000 tokens in a single request, and can return up to 16,384 output tokens.

Is there a cheaper OpenRouter model than OpenAI: GPT-4o?

Yes. Free Models Router is free per 1M input tokens versus $2.50 for OpenAI: GPT-4o, with a 200,000 token context window.

Where does this OpenAI: GPT-4o price come from?

From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.

OpenAI: GPT-4o pricing

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. OpenAI: GPT-4o from OpenRouter costs $2.50 per 1M input tokens and $10.00 per 1M output tokens. Cached input is $1.25 per 1M. Context window 128,000 tokens.

API id openai/gpt-4o · OpenRouter · source · updated 2026-11-10 · general-purpose

$2.50

Input / 1M tokens

$10.00

Output / 1M tokens

$1.25

Cached input / 1M

128K

Context window

OpenAI: GPT-4o specifications

Provider: OpenRouter
API id: openai/gpt-4o
Model type: general-purpose
Context window: 128K tokens
Max output: 16K tokens
Currency: USD
Price source: Provider API
Last checked: 2026-11-10

gpt-4o across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

Provider	Input /1M	Cached /1M	Output /1M	1M in + 1M out	vs vendor
OpenAIVendorCheapest	$2.50	$1.25	$10.00	$12.50	—
OpenRouterHostviewing	$2.50	$1.25	$10.00	$12.50	—

What OpenAI: GPT-4o costs in practice

Estimated cost at common usage volumes
Workload	Input tokens	Output tokens	Estimated cost
Short chat turn	1,000	500	$0.0075
Document summary	50,000	2,000	$0.14
1M tokens in, 200K out	1,000,000	200,000	$4.50

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does OpenAI: GPT-4o cost per 1M tokens?: OpenAI: GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on the standard tier. Cached input is $1.25 per 1M.
What is OpenAI: GPT-4o's context window?: OpenAI: GPT-4o accepts up to 128,000 tokens in a single request, and can return up to 16,384 output tokens.
Is there a cheaper OpenRouter model than OpenAI: GPT-4o?: Yes. Free Models Router is free per 1M input tokens versus $2.50 for OpenAI: GPT-4o, with a 200,000 token context window.
Where does this OpenAI: GPT-4o price come from?: From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.

Head-to-head comparisons

Compare OpenAI: GPT-4o with another model →

Other OpenRouter models

See all OpenRouter pricing →