RentGPU RentGPU
Trouver un GPU →
by OpenAI

OpenAI: GPT-4o (2024-05-13).

multimodal closed 128K ctx
Cheapest input
$5.0/M
on OpenAI API
Cheapest output
$15.0/M
on OpenAI API
Fastest
69 tok/s
on OpenRouter
Hosted equiv.
~$5.4/hr
@ 100 tok/s on OpenAI API

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](/models/openai/gpt-4-turbo) while being twice as...

Hosted API only

No self-host path — closed weights.

OpenAI: GPT-4o (2024-05-13)'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 $5.0 $15.0 Launch ↗
OpenRouter api aggregator $5.0 $15.0 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 69.4 953 ms 1657 ms
FAQ

Frequently asked.

How do I run OpenAI: GPT-4o (2024-05-13)?
OpenAI: GPT-4o (2024-05-13) 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 (2024-05-13)?
OpenAI: GPT-4o (2024-05-13) 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 (2024-05-13)?
API pricing starts at $5.0/M input tokens and $15.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is OpenAI: GPT-4o (2024-05-13) open-source or proprietary?
OpenAI: GPT-4o (2024-05-13) is a proprietary model from OpenAI. Access is API-only — there are no public weights to download.