Nathaniel Whittemore

And it won't just be the big labs.

You're also going to see the agent labs and even app layer companies experiment with their own models, their own harnesses, and their own routing systems in order to get better token efficiency, which is exactly what I meant when I said that every AI business model is now to some extent a token efficiency play.

We saw this with Cursor's Composer 2.5, which completes coding tasks in the range of the state-of-the-art from both Cloud and OpenAI, but with a radically higher efficiency.

Interestingly, we also just got something from legal AI firm Harvey along the same lines.

This week, Harvey tweeted, We partnered with Fireworks AI to train open-source models for legal.

Here's what we found.

One...

Hybrid legal agents can beat frontier models on quality and cost by routing selectively to a frontier advisor.

We tested a hybrid setup where GLM 5.1 served as the primary worker routing tasks to Opus 4.7 as an advisor when needed.

GLM invoked Opus sparingly, just 0.83 times per task on average.

The hybrid setup beat Opus on both quality and cost.

They also found that post-training can push open models to frontier-level legal performance.

With a little bit of post-training on Kimi's K2.6 model, they were able to move Kimi ahead of Opus on their legal agent benchmark and to do so for 11 times cheaper than Opus alone.

Writes Patrick Oyo, this is the multi-model routing thesis proved in production on one of the hardest benchmarks in enterprise AI.

The insight isn't that open source beat frontier.

It's that smart routing beat brute force.

Using the most expensive model for every task is not a quality strategy.

It's a laziness tax.

The teams building routing layers that send each task to the right model at the right cost are now demonstrably ahead on both dimensions simultaneously.

Inference optimization just became a first-class competitive advantage.