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

Supporting the Next Wave of AI Startups with the NVIDIA Inception ProgramPublished on 2026.11.04 by Aray SultanbekovaSupporting the Next Wave of AI Startups with the NVIDIA Inception Program

NVIDIA Inception members get 10 billion free tokens for NVIDIA Nemotron models on DeepInfra, and DeepStart now offers 50 billion free tokens on any of our 200+ models.

MiMo-V2.6-Pro Guide: Performance, Pricing & ProvidersPublished on 2026.11.03 by DeepInfraMiMo-V2.6-Pro Guide: Performance, Pricing & Providers

Updated November 2026. API Review Summary (October 2026) Attribute Value Developer Xiaomi Release Date September 21, 2026 Model Type Reasoning model (open weights) Artificial Analysis Intelligence Index 30 — ranks #5 of 29 comparable open-weights models on Artificial Analysis, where the median is 23 Speed 55 output tokens/sec Context Window 1M tokens (~1,500 A4 pages) […]

MiMo-V2.6-Pro Pricing Guide: Developer Cost BreakdownPublished on 2026.11.02 by DeepInfraMiMo-V2.6-Pro Pricing Guide: Developer Cost Breakdown

Updated November 2026. MiMo-V2.6-Pro is the kind of model that gets a pricing guide worth reading: it combines open weights, a 1M-token context window, and pricing that undercuts the typical large open-weight reasoning model. At list rates of $0.43 per million input tokens and $0.87 per million output tokens ($0.387 / $0.783 on DeepInfra’s current […]

MiMo-V2.6-Pro Is Now Available on DeepInfraPublished on 2026.11.01 by DeepInfraMiMo-V2.6-Pro Is Now Available on DeepInfra

Updated November 2026. From 19.0 to 71.9 on DeepSWE — that’s the jump Xiaomi reports between MiMo-V2.5-Pro and MiMo-V2.6-Pro, its new flagship, on real-world software engineering tasks. That puts it, on Xiaomi’s own published figures, alongside Claude Opus 5 (74.0) and GPT-5.6 Sol (73.0) on a benchmark designed to test repository-level coding rather than toy […]

Why Open Models Get Faster Weeks After LaunchPublished on 2026.10.31 by NiklasWhy Open Models Get Faster Weeks After Launch

Qwen3.8-Flash-Next was released on August 26, 2026. The same day, SGLang announced day-0 support, built with the Qwen, NVIDIA and AMD teams, and shipped a dedicated container image. vLLM served the model from its own dedicated image while the architecture-support work was still being merged. llama.cpp, the engine most people use to run models on […]

Best Jev Alternatives: Hosted APIs and Open Models (2026)Published on 2026.10.30 by Stefan FidanovBest Jev Alternatives: Hosted APIs and Open Models (2026)

Jev had competitors before it was even a month old. TypeSafe launched it on September 15, and by the first week of October OpenAI had announced a Decisions API, Cloudflare and AWS had shipped open-weight decision models, and GitHub had a shelf of open-source Jev alternatives: Laya, OpenJev, Kev, AnyJev. We ran Jev and the […]