RentGPU RentGPU
Tìm GPU →
by OpenAI

OpenAI: GPT-4.

text closed 8K ctx
Cheapest input
$30.0/M
on OpenAI API
Cheapest output
$60.0/M
on OpenAI API
Fastest
47 tok/s
on OpenRouter
Hosted equiv.
~$21.6/hr
@ 100 tok/s on OpenAI API

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...

Hosted API only

No self-host path — closed weights.

OpenAI: GPT-4'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 $30.0 $60.0 Launch ↗
OpenRouter api aggregator $30.0 $60.0 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 46.9 1115 ms 2835 ms
FAQ

Frequently asked.

How do I run OpenAI: GPT-4?
OpenAI: GPT-4 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-4?
OpenAI: GPT-4 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-4?
API pricing starts at $30.0/M input tokens and $60.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is OpenAI: GPT-4 open-source or proprietary?
OpenAI: GPT-4 is a proprietary model from OpenAI. Access is API-only — there are no public weights to download.