Company Announcements

Available now in Amazon Bedrock, Palmyra X5 delivers advanced reasoning capabilities with industry-leading speed and cost efficiency

SAN FRANCISCO--(BUSINESS WIRE)--Apr. 28, 2025-- Writer, the leader in enterprise generative AI, today released its newest and most advanced foundation model, Palmyra X5. The state-of-the-art adaptive reasoning model features a 1 million token context window and industry-leading speed and cost efficiency. Additionally, Writer and Amazon Web Services (AWS), an Amazon.com, Inc. company (NASDAQ: AMZN) announced today the availability of Palmyra X5 in Amazon Bedrock, a fully managed service that offers developers access to high-performing models from leading AI companies through a single API.

Trained with synthetic data for just $1 million in GPUs, Palmyra X5 delivers the dynamic reasoning capabilities and enterprise-grade reliability required to scale the next era of agents in the enterprise. In an industry first, Writer also announced that it is now setting 1 million tokens as the minimum context window size for all large language models it releases in the future, thanks to the model’s innovative transformer design and hybrid attention mechanisms that achieve breakthrough efficiency and long-context accuracy.

“In the age of agents, models offering less than 1 million tokens of context will quickly become irrelevant for business-critical use cases,” said Writer CTO and Co-Founder Waseem AlShikh. “Large context windows and high efficiency are crucial for powering agents that can call on dozens of external tools and reason through the massive amount of contextual data needed to operate within an enterprise. Palmyra X5 marks a turning point in the models Writer can deliver to power the agentic workflows our customers are building within our platform.”

Speed and efficiency for multi-step AI agents

Palmyra X5 is one of the fastest and most cost efficient large-context LLMs in the market, unlocking agent behaviors that were previously cost- or time-prohibitive. The model can absorb an entire million-token prompt in ~22 seconds, and it can return individual function-calling turns in ~.3 seconds. Palmyra X5 is priced at just $.60 per 1 million input tokens and $6 per 1 million output tokens.

On OpenAI’s MRCR 8-needle test—a long-context benchmark that hides eight identical requests in a massive conversation and challenges the model to find the correct one—Palmyra X5 scores an impressive 19.1%. With top-tier retrieval performance at a dramatically lower cost than other popular models, Palmyra X5 gives enterprises the ideal balance for scaling production agents without breaking budgets.

The release of Palmyra X5 comes on the heels of Writer’s release of AI HQ – a new centralized hub for teams to easily build, activate, and supervise AI agents, powered by Writer’s family of Palmyra models. Palmyra X5 delivers on the AI HQ vision by allowing enterprises to build and deploy more sophisticated AI agents in Writer using capabilities such as:

• Ability to call tools in external systems and call on Writer agents as tools
• Built-in retrieval augmented generation (RAG) and web connectors
• Dynamic model delegation to call on Writer’s domain-specific models, including Palmyra Fin, Palmyra Med, and Palmyra Creative
• Ability to use images as inputs
• Code generation and deployment
• Multilingual capabilities in 30+ languages
• Enterprise-grade transparency and reliability

“Palmyra represents a critical step forward for companies seeking to embed generative AI into their enterprise workflows,” said David Cushman, executive research leader at HFS. “Palmyra is purpose-built for agent development, API function calling, multimodal processing, and custom enterprise AI applications. More importantly – it’s integrated into Writer’s end-to-end platform that balances scalability with transparency—a core demand from regulators and stakeholders alike.”

With Palmyra X5, enterprises get unmatched performance for multi-step agents, such as pulling in real-time market data across a range of databases and systems to prepare detailed reports. The model also excels at processing large amounts of information, such as financial reporting, legal document analysis, medical record synthesis, and customer feedback analysis.

"At Vanguard, we continue to leverage Writer’s full-stack platform across the enterprise, arming our crew (employees) with the latest advancements in generative AI technology to support and enhance our content creation and knowledge management capabilities,” said Maulan Byron, Head of Enterprise Productivity and Enablement Platforms. “We are excited that Writer continues to innovate with cutting edge tools that support our mission to give investors the best chance for investment success.”

Palmyra X5 and Palmyra X4 now available in Amazon Bedrock

Palmyra X5 is available beginning today via Writer’s end-to-end platform and in Amazon Bedrock. Palmyra X4, Writer’s earlier generation foundation model with a 128k token context window, is also now available in Amazon Bedrock, with additional Writer models available soon.

AWS is the first cloud provider to deliver fully managed models from Writer. The introduction of Palmyra models in Amazon Bedrock expands its model portfolio, reinforcing AWS's commitment to offering customers a diverse selection of AI models for their use cases. This collaboration enables AWS and Writer customers to build and scale enterprise-grade generative AI agents without managing the underlying infrastructure.

"Building on our strong strategic collaboration with Writer, AWS is excited to offer Writer’s family of Palmyra models through Bedrock, enabling a new era of agentic innovation for organizations around the world,” said Atul Deo, Director of Amazon Bedrock at AWS. “Palmyra X5 offers impressive performance over long context inputs and enterprise-grade reliability and speed. Seamless access to Writer’s Palmyra X5 will enable developers and enterprises to build and scale AI agents and transform how they reason over vast amounts of enterprise data—leveraging the security, scalability, and performance of AWS."

Hundreds of enterprises including Accenture, Marriott, Prudential, Qualcomm, Uber, Salesforce, and Vanguard are using Writer’s Palmyra LLMs to power mission-critical AI use cases. Writer has a five-year track record of model innovation. Its family of enterprise-grade Palmyra LLMs includes self-evolving, open-source, proprietary, and domain-specific models. Palmyra models define industry-leading standards for enterprise-grade transparency and reliability, safety, performance, efficiency, and observability.

To learn more about the technology behind Palmyra X5 and how its transforming work in the enterprise, visit Writer’s Engineering blog. Find out more about Writer models in Amazon Bedrock here.

About Writer

Writer is where the world’s leading enterprises orchestrate AI-powered work. With Writer’s end-to-end platform, teams can build, activate, and supervise AI agents that are grounded in their company’s data and fueled by Writer’s enterprise-grade LLMs. From faster product launches to deeper financial research to better clinical trials, companies are quickly transforming their most important business processes for the AI era in partnership with Writer. Founded in 2020, Writer delivers unmatched ROI for hundreds of customers like Accenture, Intuit, Marriott, Uber, and Vanguard and is backed by investors including Premji Invest, Radical Ventures, ICONIQ Growth, Insight Partners, Balderton, B Capital, Salesforce Ventures, Adobe Ventures, Citi Ventures, IBM Ventures, and others. Learn more at writer.com.

View source version on businesswire.com: https://www.businesswire.com/news/home/20250428814263/en/

Media Contact:
press@writer.com

Source: Writer