Our position on open-weights models

7.1 Earthquake in Japan

Benchmarking Opus 5 on SlopCodeBench

Watching Go's new garbage collector move through the heap

A $500 RL fine-tune of a 9B open model beat frontier models on catalog review

Vehicle Motion Cues

How to Survive Boiling Water

About the security content of macOS Tahoe 26.6

Moonshot AI released open weights for Kimi K3 today and it&#x27;s live on Telnyx Inference. The architecture and Moonshot&#x27;s own benchmarks are in their technical blog. This post is about running it on Telnyx.What we are adding: K3 is now available via the Telnyx Inference API, hosted on GPUs that we own and operate.This matters due to the size of this model. A 2.8T model needs dedicated infra to serve well. Because we own and operate the GPUs, we can contorl throughput. with no inter-provider hops and no cloud tenant, latency is minimized.
We have GPUs in each of the US, EU, APAC, and MENA. Inference runs in the region you pick, with zero data retention. We do not store prompts or completions after the response returns.
Because we own the infra, the per-token price reflects the cost of running the model, not the cost of renting someone else&#x27;s plus their margin.We have not benchmarked K3 ourselves yet. Moonshot&#x27;s own numbers and early third-party evaluations put it at frontier level for coding and agentic work, trailing only Claude Fable 5 and GPT 5.6 Sol on aggregate. Full breakdown in their blog.Pricing on Telnyx: $2.70&#x2F;1M input tokens, $13.50&#x2F;1M output tokens, $0.27&#x2F;1M cached input tokens. Prompt caching enabled by default. Served via an OpenAI-compatible endpoint so you can test easily.Model ID: [MODEL_ID] API: <a href="https:&#x2F;&#x2F;api.telnyx.com&#x2F;v2&#x2F;ai&#x2F;chat&#x2F;completions" rel="nofollow">https:&#x2F;&#x2F;api.telnyx.com&#x2F;v2&#x2F;ai&#x2F;chat&#x2F;completions</a> Docs: <a href="https:&#x2F;&#x2F;developers.telnyx.com&#x2F;docs&#x2F;inference" rel="nofollow">https:&#x2F;&#x2F;developers.telnyx.com&#x2F;docs&#x2F;inference</a> Technical blog (Moonshot): <a href="https:&#x2F;&#x2F;www.kimi.com&#x2F;blog&#x2F;kimi-k3" rel="nofollow">https:&#x2F;&#x2F;www.kimi.com&#x2F;blog&#x2F;kimi-k3</a>

Kimi K3 Now Available via Telnyx Inference API

DConf 2026 in London

Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

PyTorch: A Reference Language

Google's Beyond Zero: Enterprise Security for the AI Era

Mondragon Corporation – a federation of co-operatives

Programming Languages Are Authoring Tools for Platforms

AI revenues are growing fast, but not fast enough

Which Odyssey translation wins a blind reading test?

TWC Classics

Kimi Linear: An Expressive, Efficient Attention Architecture

Show HN: Scala Tutorials – interactive Scala 3 lessons in the browser