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.
Best AI Inference Platforms for Speed & Cost in 2026<p>Updated November 2026. TL;DR: Best Inference Models and Platforms by Workload The best inference models for most production work are open-weight, and once you have picked one, the platform serving it moves your bill more than the model does. Llama 3.3 70B costs anywhere from $0.18 to $0.84 per 1,000 identical requests across the five […]</p>
Best Muse Glimmer 30B API Providers & Ways to Run It (2026)<p>Where to run Meta’s Muse Glimmer 30B: DeepInfra at $0.30/$1.20 per 1M tokens, OpenRouter, Hugging Face, plus Ollama, llama.cpp and vLLM.</p>
Muse Glimmer 30B Pricing: API Costs vs Self-Hosting (2026)<p>Muse Glimmer 30B costs $0.30 input, $1.20 output and $0.04 cached per 1M tokens on DeepInfra. Five monthly cost scenarios, OpenRouter routes, and when an RTX 5090 or a dedicated GPU beats per-token pricing.</p>
© 2026 DeepInfra. All rights reserved.