DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

Note: The list of supported base models is listed on the same page. If you need a base model that is not listed, please contact us at feedback@deepinfra.com
Rate limit will apply on combined traffic of all LoRA adapter models with the same base model. For example, if you have 2 LoRA adapter models with the same base model, and have rate limit of 200. Those 2 LoRA adapter models combined will have rate limit of 200.
Pricing is 50% higher than base model.
LoRA adapter model speed is lower than base model, because there is additional compute and memory overhead to apply the LoRA adapter. From our benchmarks, the LoRA adapter model speed is about 50-60% slower than base model.
You could merge the LoRA adapter with the base model to reduce the overhead. And use custom deployment, the speed will be close to the base model.
Introducing NVIDIA Nemotron 3 Nano Omni on DeepInfraDeepInfra is an official launch partner for NVIDIA Nemotron 3 Nano Omni, the first multimodal model in the Nemotron 3 family — a single open model that understands images, video, audio, documents, and text in one unified inference pass.
How to deploy google/flan-ul2 - simple. (open source ChatGPT alternative)Flan-UL2 is probably the best open source model available right now for chatbots. In this post
we will show you how to get started with it very easily. Flan-UL2 is large -
20B parameters. It is fine tuned version of the UL2 model using Flan dataset.
Because this is quite a large model it is not eas...
Search That Actually Works: A Guide to LLM RerankersSearch relevance isn’t a nice-to-have feature for your site or app. It can make or break the entire user experience.
When a customer searches "best laptop for video editing" and gets results for gaming laptops or budget models, they leave empty-handed.
Embeddings help you find similar content, bu...© 2026 DeepInfra. All rights reserved.