RentGPU RentGPU
Find a GPU →
by OpenAI

OpenAI: GPT-4o (2024-08-06).

multimodal closed 128K ctx
Cheapest input
$2.5/M
on OpenAI API
Cheapest output
$10.0/M
on OpenAI API
Hosted equiv.
~$3.6/hr
@ 100 tok/s on OpenAI API

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs

Hosted API only

No self-host path — closed weights.

OpenAI: GPT-4o (2024-08-06)'s weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenAI API api direct $2.5 $10.0 Launch ↗
OpenRouter api aggregator $2.5 $10.0 Launch ↗
FAQ

Frequently asked.

How do I run OpenAI: GPT-4o (2024-08-06)?
OpenAI: GPT-4o (2024-08-06) is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access OpenAI: GPT-4o (2024-08-06)?
OpenAI: GPT-4o (2024-08-06) is available via OpenAI API, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run OpenAI: GPT-4o (2024-08-06)?
API pricing starts at $2.5/M input tokens and $10.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is OpenAI: GPT-4o (2024-08-06) open-source or proprietary?
OpenAI: GPT-4o (2024-08-06) is a proprietary model from OpenAI. Access is API-only — there are no public weights to download.