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 Kimi K2.6 API Providers for Developers (2026)<p>Kimi K2.6 is available across a range of hosted API providers, and the right choice depends on what your workload optimizes for — latency, throughput, cost, deployment flexibility, or native feature support. This guide covers the top options by use case. For a detailed cost breakdown across workload types, see the Kimi K2.6 pricing guide. […]</p>
NVIDIA Nemotron 3 Super on DeepInfra: 120B MoE Model<p>NVIDIA’s Nemotron 3 Super runs 120 billion parameters while activating only 12 billion per token — a ratio that makes a real difference when orchestrating multiple agents in parallel. It’s built on a novel architecture called LatentMoE, a hybrid of Mamba-2, Mixture-of-Experts, and Attention layers designed from the ground up for agentic, reasoning, and long-context […]</p>
Building a Voice Assistant with Whisper, LLM, and TTSLearn how to create a voice assistant using Whisper for speech recognition, LLM for conversation, and TTS for text-to-speech.© 2026 DeepInfra. All rights reserved.