jhd3197/Prompture
Prompture is an API-first library for requesting structured JSON output from LLMs (or any structure), validating it against a schema, and running comparative tests between models.
Built on Pydantic models with native schema validation, Prompture supports 12 LLM providers (OpenAI, Claude, Groq, Ollama, etc.) through a unified `provider/model` routing system. It includes TOON input conversion for 45-60% token savings, per-field stepwise extraction with smart type coercion, caching backends (memory/SQLite/Redis), and automatic JSON repair via secondary LLM passes. The tool use layer simulates function calling for providers without native support, while batch testing enables side-by-side model comparison with integrated usage tracking and cost calculation.
9 stars and 3,845 monthly downloads. Used by 2 other packages. Available on PyPI.
Stars
9
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Monthly downloads
3,845
Commits (30d)
0
Dependencies
9
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/jhd3197/Prompture"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
promptslab/Promptify
Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured...
character-ai/prompt-poet
Streamlines and simplifies prompt design for both developers and non-technical users with a low...
masci/banks
LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and...
promplate/partial-json-parser
Parse partial JSON generated by LLM
Hunyuan-PromptEnhancer/PromptEnhancer
PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions...