DeepInfra
Low-cost API for running open-source models with simple per-token pricing.
- Status
- Generally available
- Last checked
- Checked · Oct 12, 2026
- License
- Proprietary
- Pricing
- Free tier
What it is
DeepInfra offers cheap, simple inference for popular open-source LLMs and other models via a straightforward per-token API.
Among the lowest-cost simple APIs for open-model inference.
When it fits — and when it doesn’t
A good fit for
Cheapest open-model inference
Simple per-token API
High-volume open-LLM serving
Low cost at scale
Known weaknesses
Each one links to the public issue, changelog or docs page it came from, where we have one.
- 01
Fewer production features
Less tooling than Baseten for custom deployments
What it does well
Very low per-token pricing
Among the cheapest open-model inference
Simple API
Easy drop-in for open models
Wide model selection
Popular open LLMs supported
Pricing
- Free tier
- YesFree credits to start
- Paid from
- —
- Model
- Usage-based
- Enterprise plan
- Yes
Pricing not independently confirmed — check the vendor’s page.
Performance benchmarks
How Fast Is It?
Set up DeepInfra
Setup steps, common gotchas and what to check after 30 days.
Get the badge
A small badge for DeepInfra’s README or site: its name, “Tracked on AI Navigator”, and the availability status and check month from this page. It updates as the catalog does.
Markdown
[](https://navigateaitools.com/explorer/tool/deepinfra)HTML
<a href="https://navigateaitools.com/explorer/tool/deepinfra"><img src="https://navigateaitools.com/badge/deepinfra.svg" alt="DeepInfra — tracked on AI Navigator" height="58"></a>