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.
DeepSeek V4 Pro (Max) API Benchmarks: Latency, Throughput & Cost Analysis<p>About DeepSeek V4 Pro DeepSeek V4 Pro is a Mixture-of-Experts (MoE) language model with 1.6 trillion total parameters and 49 billion activated parameters, supporting a 1 million token context window. Designed for advanced reasoning, coding, and long-horizon agent workflows, it represents the fourth generation of DeepSeek’s flagship open-weight models. The model introduces a hybrid attention […]</p>
Best API Providers for DeepSeek V4 in 2026<p>DeepSeek V4 is available across a range of hosted API providers, each with different pricing, performance, and deployment trade-offs. The model comes in two variants: V4 Pro, a 1.6 trillion total parameter Mixture-of-Experts model with 49 billion active parameters and a 1M token context window, and V4 Flash, a lighter 284B total parameter variant built […]</p>
Kimi K2.6 API Benchmarks: Latency, TPS & Cost Analysis (2026)<p>About Kimi K2.6 Kimi K2.6 is an open-source frontier model from Moonshot AI, released on April 20, 2026. It is a native multimodal agentic model built for long-horizon coding, autonomous execution, and swarm-based task orchestration. The model uses a Mixture-of-Experts (MoE) architecture with 1 trillion total parameters and 32 billion activated parameters per token, using […]</p>
© 2026 DeepInfra. All rights reserved.