Lilac

(YC S25) Lilac serves fast model inference on idle GPUs.

[Lilac @LilacML]

Very excited for M3!

[MiniMax (official) @MiniMax_AI]

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities

- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero

API: https://t.co/fHRdSV7BwZ
Token Plan: https://t.co/BDCycxepZw
🚀New! MiniMax Code: https://t.co/GvB4YiB6Ul

Weights & Tech Report in ~10 Days

[Lilac @LilacML]

@bosmeny Damm, we should have thought of that!

[Shardul Lavekar @shardullavekar]

Dreading your @AnthropicAI API bills? We just ran a benchmark of equivalent open source models on @LilacML and GLM 5.1 came on top even for the most tedious tasks.

Read our blogpost here.

https://t.co/0f15TuvNBC

Folks at @LilacML are onto something!

[Lilac @LilacML]

@guillaumedegail We're evaluating adding Deepseek models, but are currently focused on getting subscriptions out.

[Lilac @LilacML]

We now have an official discord server
https://t.co/i3Fu7uq3BM

[Lilac @LilacML]

@karpathy What an interesting timeline

[cyber•Fund @cyberfund]

Introducing the Monastery for AI-native founders.

A single builder can now outperform a publicly traded company.

$2 million. 12 weeks. Do the impossible.

[Lilac @LilacML]

@latentlocal @MiniMax_AI Let us know how they are!

Should be fast

[Lilac @LilacML]

We're excited to announce our partnership with @MiniMax_AI!

Read more at https://t.co/gafHzoT6oy

[Lilac @LilacML]

@MesserShilling @MiniMax_AI Can't help with this specific issue. But if you want to try 2.7 on Lilac send a dm!

Will grant credits for testing.

[Lilac @LilacML]

@jahooma Dms open!

[Lilac @LilacML]

@jahooma Need some providers? We're happy to help :)

[Lilac @LilacML]

We've just launched Kimi K2.6: Come try it at https://t.co/SIT3xkZBje !

[Lilac @LilacML]

Cache pricing is in 🎆 for GLM 5.1 and Kimi K2.5!

Lowest cost in the industry at the highest throughput for shared endpoints.

Read more at: https://t.co/kZAP2maasv

[Lilac @LilacML]

@OpenRouter 👀

[Lilac @LilacML]

Real time status now available to all on our endpoints -- see it by hitting https://t.co/s0YDdrFTkj or go to our website: https://t.co/KfCKzCiRFu

Fast Throughout, Low Latency, Low Price!

[Lilac @LilacML]

We are excited to be working with @InfronAI !

[Nano-GPT @NanoGPTcom]

GLM 5.1 and Kimi K2.6 are now included in the subscription, including their Thinking variants.

For these two model families, input tokens count 2x against included-input limits (for example, 1M input tokens on GLM 5.1 or Kimi K2.6 uses 2M included-input tokens).

[Lilac @LilacML]

Lilac's models are now available on https://t.co/2r3rUkm4iA -- Happy to be working with the amazing team @NanoGPTcom

[Lilac @LilacML]

GLM 5.1 up to 135 TPS per user!

See us on @NanoGPTcom breaking records at one of the lowest costs