kitio.aiAdded Oct 28, 2026
DeepInfra
PaidLow-cost serverless API for hundreds of open-source models
What is DeepInfra?
DeepInfra is an inference cloud offering hundreds of open-source language, image, speech and embedding models through a simple pay-per-token API. It is known for some of the lowest prices on popular open models, which makes it common in cost-sensitive apps.
Endpoints are OpenAI-compatible, and you can also deploy custom models or LoRA adapters on dedicated GPUs. DeepInfra is a Hugging Face Inference Provider, so its models can be called from the Hugging Face Hub.
There are no monthly fees, and usage is billed per token for shared models or per GPU hour for dedicated ones. The company raised a Series B in May 2026 to expand its inference capacity.
Features
- Hundreds of open models
- OpenAI-compatible API
- Custom model deployment
- Embedding models
- Hugging Face provider
Tags
Releases
+ Submit new release- Listed
DeepInfra was added to the directory.
Organization
DeepInfra
🇺🇸 United States
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Paid
- Paid options from
- Not listed
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top DeepInfra alternatives
View allModels & APIs
Run and deploy open-source AI models through a simple API
Models & APIs
Fast inference and fine-tuning platform for open models
Models & APIs
Affordable model APIs and GPU cloud for open-source AI
Models & APIs
Inference cloud for open models like DeepSeek, Qwen and GLM
Compare DeepInfra
If you liked DeepInfra
The main hub for open models, datasets and AI demo apps
Freemium · $9/moModels & APIsMade in United StatesRun open models locally with one command, plus optional cloud models
Freemium · $20/moModels & APIsMade in United StatesNVIDIA's optimized model containers and hosted API catalog
FreemiumModels & APIsMade in United StatesVery fast inference API for open models on custom LPU chips
FreemiumModels & APIsMade in United States
Pros and cons
Pros
- Very low token prices
- Large catalog
- No monthly fee
Cons
- Basic dashboard
- Fewer enterprise features
- Latency varies by model
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is DeepInfra?
DeepInfra is an inference cloud offering hundreds of open-source language, image, speech and embedding models through a simple pay-per-token API. It is known for some of the lowest prices on popular open models, which makes it common in cost-sensitive apps.
How much does DeepInfra cost?
DeepInfra is paid.
Is there a free version of DeepInfra?
No. DeepInfra is a paid tool.
What are the main features of DeepInfra?
Hundreds of open models, OpenAI-compatible API, Custom model deployment, Embedding models, Hugging Face provider.
Who makes DeepInfra?
DeepInfra is made by DeepInfra.
What are the best alternatives to DeepInfra?
Popular alternatives include Replicate, Fireworks AI, Novita AI.