3,719 tools found
Compare OpenAI and Azure OpenAI side-by-side to benchmark speed, cost, and output quality differences using identical models.
Promptfoo example evaluating Cerebras high-performance inference API - model comparison, structured JSON, tool use.
Promptfoo example routing OpenAI, Anthropic, and Groq requests through Cloudflare AI Gateway for caching and analytics.
Minimal promptfoo scaffold for benchmarking Cohere models via a promptfooconfig.yaml eval.
Configures CometAPI's OpenAI-compatible interface in promptfoo to access multiple language models.
Test AI prompts systematically with custom JavaScript providers and CSV test cases for quality assurance.
Create custom TypeScript API providers for prompt testing with CSV test cases and structured output validation.
Promptfoo example testing Databricks Foundation Model APIs, including Llama 3.3 text generation and vision models.
Promptfoo example testing ElevenLabs forced alignment - generates time-synced SRT, VTT, or JSON subtitles.
Promptfoo example removing background noise from audio with ElevenLabs isolation, chainable into transcription or alignment.
Promptfoo example testing ElevenLabs speech-to-text: diarization, Word Error Rate scoring, cost, and 30+ languages.
Promptfoo example comparing ElevenLabs TTS models - latency, quality, cost, streaming, voice tuning.
