Writer, the AI tools and agents vendor for marketers, launched Palmyra X6, a new flagship model built as a post-training variation on Z.ai‘s open source model GLM-5.2. The company also released significant upgrades to its standard agentic harness, with both features available to clients starting Thursday. The move responds to growing customer concern about deployment costs and the difficulty of finding the right open source model for a given job.

The company estimates the new model, combined with harness infrastructure changes, will cut costs for customers by as much as 50% for basic tasks. CEO May Habib told TechCrunch that enterprises are “absolutely sick of chasing the next benchmark” and want flattening cost, a demand she says “nobody can deliver.” The new approach emphasizes complex, multi-step tasks executed faster and with fewer tokens, with harness optimization as a key lever. A recent paper from Writer researchers tested small harness efficiency changes across multiple models, finding that harness changes were often a more reliable way to reduce costs than model choice, with costs falling an average of 40% across their testing. The researchers wrote that “the harness is the one component whose efficiency multiplies across every model an organization runs—present and future.”

For Writer‘s clients, the experience remains model-agnostic: Palmyra X6 will sit alongside other Writer models or outside models imported through Azure or Amazon Bedrock. Habib also sees the cost-cutting push as driving broader distrust toward major AI labs, which have a financial incentive to drive up token use. “The cost explosion here is just unprecedented for customers, and so is the degree to which CIOs are giving up on the labs,” she said, adding that AI labs “don’t deeply understand right how to help an enterprise get benefit from AI.”