DeepEval vs Portkey

DeepEval is a free, open-source framework for building evaluation pipelines to test AI systems. Its Pytest-native evaluations run in CI/CD or as Python scripts, and the framework lists more than 50 research-backed metrics, including checks for hallucination, faithfulness, answer relevancy, summarization, toxicity and bias. It evaluates text, images and audio, including conversational and voice interactions, using methods such as G-Eval, DAG, QAG and JevEval. DeepEval can generate synthetic goldens from a knowledge base and model conversations across user personas. It also traces agent steps so they can be graded and inspected in a terminal or test runner. Integrations cover agent frameworks including LangChain, Pydantic AI, OpenAI Agents, LangGraph, LlamaIndex and CrewAI, alongside a range of model providers. By default, it sends basic telemetry to PostHog, excluding personally identifiable information and stored results; users can opt out with an environment variable. The maker describes DeepEval OS as for pre-production testing, with results in local files and an engineer-owned test runner. Enterprise capabilities are offered through Confident AI Evals, with self-hosted or maker-cloud deployment options.

Portkey is a platform for managing, observing, and governing generative AI across teams. Its gateway offers a unified API for models and providers across modalities, with configurable routing, failovers, retries, and load balancing. Monitoring tools include logs, traces, feedback, metadata, filters, and alerts; prompt management adds templates, a playground, API endpoints, versioning, and variables. Listed integrations include OpenAI, Anthropic, Google Gemini, Azure, Amazon Bedrock, and Ollama, as well as agent frameworks including CrewAI, LangChain, LangGraph, and the OpenAI Agents SDK. The gateway offers simple and semantic caching for repeat requests. Security features include virtual provider keys, access controls, inbound IP and geographic rules, and sensitive-data redaction. Self-hosted and local deployment options are listed, while Enterprise adds private cloud deployment and VPC hosting. Developer is free and includes 10k recorded logs/month, 3 days log retention, and 30 days metrics retention. Production costs $49 a month, billed $49/month, with 100k recorded logs/month and production support. Enterprise pricing is custom. Portkey lists San Francisco as its headquarters and March 2023 as its launch date.