Writer Launches Palmyra X6 AI Model and Upgraded Harness to Cut Token Costs

On Thursday, Writer, a provider of AI tools and agents for marketers, launched Palmyra X6, a new flagship model built as a post-training variation of Z.ai's open source model GLM-5.2. The company claims the model, combined with upgrades to its agentic harness, will reduce customer costs by up to 50% for basic tasks. The release responds to growing enterprise concern over AI deployment expenses and the difficulty of selecting appropriate open source models. Writer also introduced significant upgrades to its standard agentic harness, both features available to clients starting Thursday. CEO May Habib emphasized that enterprises are tired of chasing benchmarks and want flattening costs. The new approach focuses on complex, multi-step tasks executed faster with fewer tokens, with harness optimization seen as a key cost lever. A recent paper by Writer researchers tested small harness efficiency changes across multiple models, finding that harness adjustments reduced costs by an average of 40%, often more reliably than model choice. The harness's efficiency multiplies across all models an organization runs, according to the researchers. Writer's clients remain model-agnostic, as Palmyra X6 will coexist with other Writer models or outside models via Azure or Amazon Bedrock. Habib also noted a growing distrust toward major AI labs, which have financial incentives to increase token usage, and criticized their lack of understanding in helping enterprises benefit from AI.