RentGPU RentGPU
Trouver un GPU →
by OpenAI

OpenAI: GPT-3.5 Turbo.

text closed 16K ctx
Cheapest input
$0.5/M
on OpenAI API
Cheapest output
$1.5/M
on OpenAI API
Fastest
43 tok/s
on OpenRouter
Hosted equiv.
~$0.54/hr
@ 100 tok/s on OpenAI API

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

Hosted API only

No self-host path — closed weights.

OpenAI: GPT-3.5 Turbo'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 $0.5 $1.5 Launch ↗
OpenRouter api aggregator $0.5 $1.5 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 43.4 1101 ms 2394 ms
FAQ

Frequently asked.

How do I run OpenAI: GPT-3.5 Turbo?
OpenAI: GPT-3.5 Turbo 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-3.5 Turbo?
OpenAI: GPT-3.5 Turbo 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-3.5 Turbo?
API pricing starts at $0.5/M input tokens and $1.5/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is OpenAI: GPT-3.5 Turbo open-source or proprietary?
OpenAI: GPT-3.5 Turbo is a proprietary model from OpenAI. Access is API-only — there are no public weights to download.