$0.04 per 1M input tokens 128K context #1 on... the Decision Index sub-second decisions Drex is looking less like “another small model” and more like an actual decision layer for agents and LLMs especially if you don’t want to burn a huge model’s tokens just deciding what should happen nextshow more

Nace shows Drex playing a strategy game. i gave... it a harder opponent: my timeline Spoiler Guard sends each post to the new decision model and blurs the spoilers, 352 post checked in one session with sub-second calls → 128K context window, per Nace the first and only decision model at that size → #1 on the Decision Index, a Jev rival for $0.04 per 1M input tokens → no text generated, just a probability per post try it with 250M free tokens from Nace AI:show more

Drex is a MONSTER not because it’s huge it’s... actually fewer than 10B parameters but somehow this thing has 128K context, hits 93.4% accuracy across 32K–128K and makes decisions in under a second #1 on the Decision Index too small models are getting VERY good at doing the one thing they actually need to doshow more

Arena leaderboards now include Price and Context. - Price... is shown as input / output cost per 1M tokens, and context shows the maximum context window. Compare Arena scores based on what matters for your use case.show more

JEV ENGINEERING JUST CUT A CLAUDE LOOP FROM $765/MONTH... TO $3.02 the expensive part isn’t always writing code. a busy overnight loop can burn ~600 decisions just asking what to do next, whether a command is safe, or if the task is finished. trigger → Jev → allow / stop / wake → Claude only builds when needed at roughly 4,000 tokens per decision, those checks can cost ~$25.50 a night on Fable 5.1. Jev handles the same decision layer at $0.042 per 1M input tokens with output free. over 30 nights that moves the decision bill from ~$765 to $3.02. batch multiple questions into one call and it falls again to about $1.08/month. that’s the part i care about: Claude keeps the expensive work that actually needs intelligence, while Jev handles the hundreds of tiny judgment calls around it.show more

1/ 📰Missed a few days of AI news? Here's... what happened in this week's Data Points 👇 2/ 🪶Claude Haiku 5.5: $0.10/$0.50 per million tokens for prompts up to 100K, ~90% cheaper than Haiku 4.5. Super fast and highly capable. 3/ 🎯Microsoft-Decision-1: calibrated probabilities over fixed options in one pass. Built for classification, routing, agent gating. This decision model costs $0.042 per million input tokens, and output is free. Check independent benchmarks to compare it with Jev and other decision models. 4/ 🔌Meta's Muse Wonder: Comparable with top models from Google and OpenAI, costs $4/$20 per million tokens. No full safety report yet. 5/ 📄Gemini 4 Argon: the official wide release has a 1M token output limit, up from 64K. Input and output share the window. $2/$10 intro pricing (per million tokens of input/output) until Nov 30. 6/ 🐍Python 3.15 is out, but 3.10 is end of life. Update your projects to support the new features where you can (3.11 remains a good backwards-compatible option). 7/ 📬Subscribe to our Data Points newsletter for authoritative, short-form, real-time AI news: #DeepLearningAI #AIEngineering #Pythonshow more

Laya is now available on Vercel, served by Boundless... and free to use. An open-weight decision model for fast, structured decisions in agents and workflows.show more

China is literally on 🔥 Baidu from China has... launched ERNIE 4.5 and ERNIE X1 and it’s freaking cheap . Here is everything you need to know. ERNIE 4.5 - Native multimodal and Outperforms GPT 4.5 in multiple benchmarks at just 1% of GPT 4.5 price - OpenAI GPT 4.5 – Input: $75 / 1M tokens, Output: $150 / 1M tokens; - ERNIE 4.5 – Input: $0.55 / 1M tokens, Output: $2.20 / 1M tokens ERNIE X1 - A deep thinking reasoning model with multimodal capabilities on par with DeepSeek R1 at only half the price See it in action and check out the pricing details👇 📹 source : yiyan[.]baidu[.]com 1/6 ERNIE 4.5 is a multimodal which can take Audio files as well.show more

Open weights just caught up to the frontier. GLM-5.2... from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.show more

I used GPT-6 Astra Ultra to track a tennis... ball. The results are impressive until I tell you the following. Ball annotation, using 3 parallel agents took 8m 35s and 17,611 tokens. Complete workflow: 11m 49s and 30,481 tokens. The complete workflow also processed 313,914 uncached input tokens and 7,528,320 cached input tokens. That's a total of 7.87 million total, mostly context reused across frame-inspection calls.show more

openai just released Decisions API, Jev-like "system 1" multi-modal... model based on GPT6 Luna! Each egg gets cropped and sent to OpenAI (~270ms latency) and returns P(clean, dirty, cracked). One image crop consumes ~280 input tokens (~$0.03/1K imgs). Roboflow RF-DETR for detecting eggsshow more

We’ve improved prompt caching in the API for GPT-6,... helping agents run faster and cost less. Higher cache-hit rates by default mean more input tokens benefit from cached-input discounts of up to 90%.show more

GLM 5.2 INPUT FELL FROM $1.40 TO SEVEN CENTS... PER MILLION IN NINETY DAYS • what it costs now > $0.07 per million input at the cheapest of 20 providers, a 95% drop in three months. > direct still lists $1.40 in and $4.40 out, with cached input at $0.26. > Same model, same weights, twenty-fold spread depending on the door you walk through. • the free way in > New accounts on get 20M tokens: > 744B MoE, 1M context, MIT weights you can also just download and self-host. Nobody announced this. It happened one provider at a time -> and the model itself never changed. Check which provider you are actually routed through before you top up anywhere ↓show more

How to swap tokens across different chains with YOUR... Ronin Wallet Step 1: Open your Ronin Wallet Step 2: Click “Swap” Step 3: Choose the tokens you want to swap, select their respective chains, and input an amount!show more

Introducing Microsoft-Decision-1, our new model for fast decision-making. It... delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality. We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.show more

3,868 NULLs. 3,868 unique forms. No two are the... same. Register for the whitelist at: Free Mint goes live on OpenSea today, September 30, at 11 AM GMT: NULL is more than a collection of static 2D artwork. Each piece combines art with dynamic visual effects, allowing the form of a NULL to shift and transform when you interact with it. The collection is built around both art and utility. Collectors will be able to burn NULLs to generate $NULL tokens, while the Reborn mechanism introduces a second layer: burn tokens to create a new variation of NULL. Collect. Burn. Reborn. 3,868 forms enter the void. What they become next is part of the experiment.show more

China f*cked the world again DeepSeek just dropped a... killer library that saves up to 98% on tokens ur GPT Astra and Opus 5.5 it's DeepGEMM, the engine DeepSeek trains and runs its own models on faster GPU math -> more tokens per GPU -> cheaper tokens > plug the engine DeepSeek uses into your own models > squeeze more tokens per second out of the GPUs you already pay for > match or beat expert-tuned GPU libraries on speed u will pay $1.6 instead of $50 its sitting in one public repo, link belowshow more

EXCUSE ME?? IQuest raised a 320B model from its... very first token, then gave it over a million exams with three proctors on every single one the exams are real executable containers. one check runs while the environment gets prepped, one while the code executes, and a full trajectory audit after. if the model tries to peek at hidden tests, it gets flagged, so every pass it learns from is earned it's called IQuest-Q1, an open model built to live in your terminal → 15B active out of 320B, only 8 of 256 experts per token → 29T training tokens, context stretched 32K → 128K → 512K → SFT, RL in real environments, then multi-teacher distillation (MOPD) → runs inside Claude Code, Codex and other agent scaffolds my favorite speed trick: an MTP layer gets reused as a drafter that guesses the next tokens, and the main model checks them. long sessions get way cheaper on the same parameter budget the team calls this an early release. a first model with training this strict makes me want to see the second one try it:show more

We are thrilled to be a launch partner for... Meta Llama 3. Experience Llama 3 now at up to 350 tokens per second for Llama 3 8B and up to 150 tokens per second for Llama 3 70B, running in full FP16 precision on the Together API! 🤯show more

you don’t throw the cup and call it an... accident like what the actual fuck is going on and that’s not okshow more

How can agents like LLMs become decision-making partners for... humans? 💬 Excited to share a new paper + suite of envs for 𝘥𝘦𝘤𝘪𝘴𝘪𝘰𝘯-𝘰𝘳𝘪𝘦𝘯𝘵𝘦𝘥 𝘥𝘪𝘢𝘭𝘰𝘨𝘶𝘦𝘴, where agents + humans collab to solve hard everyday problems. [1/n] Site:show more