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

Sandboxes: give your agents a safe place to run codePublished on 2026.08.19 by DeepInfraSandboxes: give your agents a safe place to run code

Isolated Linux microVMs you can spin up with one API call: run bash or Python, move files in and out, pause and resume, tear down when you're done. Built for agents and pipelines that need to execute untrusted code without you having to run the infrastructure yourself.

Best Kimi K3 SaaS Tools & API PlatformsPublished on 2026.08.13 by DeepInfraBest Kimi K3 SaaS Tools & API Platforms

Updated November 2026. Looking for the newer model? Moonshot has released Kimi K3.1 Pro, post-trained from Kimi K3, and it runs on DeepInfra at $1.90 / $9.50 per 1M tokens (promotional pricing), a third below Kimi K3. See the best Kimi K3.1 Pro API providers. Kimi K3, with its 2.8 trillion parameters and 1M-token context […]

Kimi K3 Pricing, Providers & Real-World CostsPublished on 2026.08.12 by DeepInfraKimi K3 Pricing, Providers & Real-World Costs

Updated November 2026. Kimi K3 matters because it pushes an unusual combination into the same decision: open weights, a 1 million token context window, and frontier-class benchmark numbers, but at pricing still high enough to force real provider shopping. Released by Moonshot AI on July 16, 2026, it is a 2.8 trillion parameter Mixture-of-Experts model […]

Kimi K3: 2.8T Open-Weight Multimodal ModelPublished on 2026.08.11 by DeepInfraKimi K3: 2.8T Open-Weight Multimodal Model

Updated November 2026. Kimi K3, developed by Moonshot AI, represents a landmark achievement in open-source artificial intelligence. As a 2.8-trillion-parameter native multimodal Mixture-of-Experts (MoE) model, Kimi K3 is engineered to handle demanding computational tasks, from complex software engineering and long-horizon agentic workflows to deep scientific research. By combining a one-million-token context window with its architectural […]

NVIDIA Nemotron 3.5 Lightning Is Live on DeepInfra: Day-Zero Access to the Fastest Open Model for AgentsPublished on 2026.08.11 by Aray SultanbekovaNVIDIA Nemotron 3.5 Lightning Is Live on DeepInfra: Day-Zero Access to the Fastest Open Model for Agents

NVIDIA Nemotron 3.5 Lightning is available on DeepInfra's serverless API from day zero. It's a 30B hybrid MoE model with 3B active parameters, a 1M-token context window, and up to 4x higher throughput for high-volume agentic workloads.

Kimi K3 Now Available on DeepInfraPublished on 2026.08.10 by DeepInfraKimi K3 Now Available on DeepInfra

Updated November 2026. Update, November 2026: Kimi K3.1 Pro is now available on DeepInfra. It’s post-trained from Kimi K3 with much larger post-training compute, swaps in sparse attention for long context, and costs $1.90 / $9.50 per 1M tokens on DeepInfra, a third below K3 (pricing as of 2026-11-17). Moonshot AI’s Kimi K3 is the […]