An intermediate representation for AI-assisted engineering
Compare AI products across 459 workflows using traffic estimates, features, and alternatives.
“LLM Function Calling” · Coding & Development·322 results
Start overAn intermediate representation for AI-assisted engineering

A free, community-run P2P network for running open LLMs on shared GPUs.
The AI orchestration layer that turns LLM experiments into reliable production workflows
Chat with a self-correcting Llama 3.1 70B model, right in your browser
Chat with a self-correcting Llama 3.1 70B model, right in your browser

Deploy, scale and govern LLM apps on your own compute
One OpenAI-compatible endpoint for 98+ frontier LLMs at discounted rates
Count prompt tokens and price them across 300+ LLM models instantly
Count prompt tokens and price them across 300+ LLM models instantly

One API key for DeepSeek, Qwen, GPT, Gemini, Claude and more

A cozy personal chat shell for OpenAI's o1 reasoning models
Score every AI answer for trustworthiness before it reaches your users
Score every AI answer for trustworthiness before it reaches your users
Build, host and monetize custom AI assistants without writing code
Build, host and monetize custom AI assistants without writing code

Private GenAI and LLM apps that run on CPUs

Design, test, and deploy LLM prompts with automated evaluation
Design, test, and deploy LLM prompts with automated evaluation
Zhipu AI's 745B-parameter MoE model for agentic reasoning, coding, and long-context work
Zhipu AI's 745B-parameter MoE model for agentic reasoning, coding, and long-context work
Real-time web intelligence your agents can cite

Run AI commands on any website, without leaving the page
Meter pay-as-you-go LLM API usage and turn token costs into Stripe invoices
Meter pay-as-you-go LLM API usage and turn token costs into Stripe invoices

AI smart router that sends every task to the cheapest capable model

A general-purpose conversational AI for writing, analysis, math, and code
A general-purpose conversational AI for writing, analysis, math, and code
Secure, audit, and shield every AI request with a sub-5ms LLM gateway

Version, test and ship LLM prompts like code
Version, test and ship LLM prompts like code

Understand DeepSeek's open-source agent harness and give it live tools
Understand DeepSeek's open-source agent harness and give it live tools