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.
Kimi K2 0905 API Benchmarks: Latency, Throughput & Cost<p>About Kimi K2 0905 Kimi K2 0905 is a state-of-the-art large language model developed by Moonshot AI, representing a significant advancement in open-weight AI capabilities. This Mixture-of-Experts (MoE) model features 1 trillion total parameters with 32 billion activated parameters per forward pass, making it highly efficient while maintaining frontier-level performance. The model supports a 256k […]</p>
Gemma 4 Pricing, Benchmarks & Real-World Cost Analysis<p>Gemma 4 puts a serious open-weight reasoning model into a genuinely competitive provider market. The same Gemma 4 26B A4B model is available across seven API providers, with blended pricing ranging from $0.10 to $0.70 per 1M tokens — real variation that changes production economics. Released April 3, 2026 by Google DeepMind under Apache 2.0, […]</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>
© 2026 DeepInfra. All rights reserved.