RentGPU RentGPU
Trouver un GPU →
by OpenAI

OpenAI: GPT-5.4 Nano.

multimodal closed 400K ctx
Cheapest input
$0.2/M
on OpenAI API
Cheapest output
$1.25/M
on OpenAI API
Fastest
70 tok/s
on OpenRouter
Hosted equiv.
~$0.45/hr
@ 100 tok/s on OpenAI API

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

Hosted API only

No self-host path — closed weights.

OpenAI: GPT-5.4 Nano'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 $0.2 $1.25 Launch ↗
OpenRouter api aggregator $0.2 $1.25 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 69.8 767 ms 1477 ms
FAQ

Frequently asked.

How do I run OpenAI: GPT-5.4 Nano?
OpenAI: GPT-5.4 Nano 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-5.4 Nano?
OpenAI: GPT-5.4 Nano 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-5.4 Nano?
API pricing starts at $0.2/M input tokens and $1.25/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is OpenAI: GPT-5.4 Nano open-source or proprietary?
OpenAI: GPT-5.4 Nano is a proprietary model from OpenAI. Access is API-only — there are no public weights to download.