Company
Baseten provides cloud infrastructure for deploying and serving AI model inference, letting companies run and scale machine learning models in production.
Goodfire launched agent monitors on Baseten that it says watched about 1,500 Kimi K3 sessions for $51, against $233 for a model reviewing every step. Every figure so far comes from Goodfire's own tests, so operators still have to measure misses and false alarms on their own traffic.
Reality
Mercury 2.5's diffusion decoder refines many token positions at once, which is why its headline throughput moves with batch size, output length and the reasoning setting Inception ships as an adjustable knob.
Reality
V4.1-Flash retires the V4 Pro line and carries two active-parameter counts, 763B total with 8B on input tokens and 16B on output, so one sizing number no longer covers both phases of a request. Baseten had it running on day zero.
Perspective Coverage
3 publishersReality
Inception's diffusion model is the fastest endpoint in the cheap tier on both figures, but OpenRouter's median sits at less than half the vendor number and only about 15 percent above Gemini 3.5 Flash-Lite's measured 382 tok/s.
Reality
Kimi K3's 1.4 terabytes of weights take eight Nvidia GB300s just to sit in memory. Export controls keep those chips away from Moonshot. Modal, Fireworks and Baseten price the hosted result at $3 in and $15 out.
Reality
The designated successor to GenAI-Perf splits load generation from record processing so the benchmark client stops hitting Python's GIL. Teams holding a GenAI-Perf baseline inherit a port and a re-run.
Reality
Base Labs has signed Hugging Face and Goodfire to publish methods for training, evaluating and monitoring open models, with the check running where the activations are. The partners have not published an evaluation suite yet.
Reality
The credential was in history[].created_by, expanded there by a RUN command that took a build argument, inside a Harbor project anyone could pull anonymously. Baseten rotated it about 17 hours after the disclosure email.
Reality
Open-weight models take about 60 percent of the tokens on US-originating OpenRouter requests, and most of those weights come from Chinese labs, so the marketplace is now selling residency of the inference itself.
Reality
Baseten's case for owning the agent runtime is that latency and idle compute accumulate at every boundary an agent crosses between the model call and its sandbox, on numbers Blaxel reported itself.
Reality
The band it joined is one where the best closed models still finish under 10% of tasks end to end at roughly $50 and 20 minutes each, so what post-training buys a law firm is price and hosting rather than capability.
Reality
Harvey and Baseten report rubric pass rates rising from 23.3% to 62.4% across seven models once the data room sits in a Python REPL and sub-agents do the reading, while Claude Code with Opus-5 manages 24.6%.
Reality
The framework separates configuration choices that move a deployment along a latency and throughput frontier from advances that move the frontier itself, which is the distinction you need before trusting anyone's benchmark table.
Reality
Linear's $99m tender at a $2.5bn mark prices existing shares rather than new capital, while the blog beneath it puts agent-created work at half the total, a composition figure Atlassian answers with a 4x quarter off an undisclosed base.
Reality