Together AI integration: Evaluate open models and optimize evaluation costs in Arize AX

Arize AX has integrated Together AI as an evaluation provider, enabling AI teams to use open models for LLM-as-a-Judge evaluations, data labeling, and model comparisons without setting up custom endpoints. The integration addresses rising evaluation costs by allowing teams to test whether smaller, lower-cost models produce judgments that align sufficiently with frontier-model evaluators on their own data and criteria. Through the Arize AX Playground and evaluation workflows, users can compare models and prompts, assess reliability, and make decisions based on quality-versus-cost tradeoffs rather than benchmarks or pricing alone. Teams can connect Together AI by entering an API key in AX settings, while Arize also offers its Cost Agent to identify inefficient model use and redundant calls in production traces.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.