Meta's Muse Wonder is live on NanoGPT. Work with text, images, audio, video and PDFs in a 1M-token context. Reasoning, tool calling and structured output are supported.

September payment statistics are ready! The headlines: @monero still biggest (do we even need to mention it), stablecoins continue their growth, BTC loses share and Zano makes a jump. https://t.co/jytvJ8aoCI

GLM 5.3 Uncensored is now on NanoGPT. The full GLM 5.3 model, adapted for lower-refusal writing, coding, reasoning and tool use. 1M context. Experimental: expect unusual behavior or inconsistent response quality.

Three new options for defensive security research: Qwen 3.8 27B, Gemma 4 26B A4B and GLM 5.3 Flash Cybersecurity are now on NanoGPT. Image understanding + tool calling. All included in the subscription at 1x usage.

GLM 5.3 Flash Uncensored: The rate limits that many of you were hitting the past days should mostly have disappeared now! This has quickly turned into one of the most used models on our service, and the provider is quickly scaling up to keep pace.

Hit us up if you're here as well! @milan_dereede will be in Amsterdam the coming days, at DashCon and Common S3nse! The NanoGPT shirt should be recognizable to any of our users!

What a busy day. Meta Spark 1.3 Contributor is now live on NanoGPT and included in the subscription!

Teams can now enforce Zero Data Retention only. Turn it on for your company or team, and team-billed requests get restricted to ZDR routes exclusively. If no route is available, the request fails rather than falling back to a non-ZDR route.

And with that, GLM 5.3 is now included in the NanoGPT subscription. Enjoy!

Tencent Hy4 Preview is now available. This 770B MoE model activates 49B parameters per token and brings a 1M-token context window to coding agents, complex tool use, long documents, large codebases, and extended workflows. https://t.co/zM1sa95xyK