Project — 2026
OpenModels
Open-source registry for LLM models and inference providers. Discover, compare, and integrate AI models across multiple providers with standardized data, transparent pricing, and real-time telemetry.
82+
Models
41+
Providers
127+
Mappings
$2.08
Avg $/1M Tokens
Key Features
Model Registry
Community-maintained, schema-validated registry of 82+ LLM models from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, and more. Machine-readable and version-controlled.
Provider Comparison
Compare 41+ inference providers side-by-side — pricing, capabilities, context windows, and availability. Find the best provider for your use case.
Real-Time Telemetry
Monitor provider health, latency, and reliability through live telemetry. Health probes every 5 minutes, latency probes every 15 minutes.
REST API
Public REST API with no auth required. Query models, providers, mappings, and telemetry data programmatically from any application.
Insights & Analysis
AI industry analysis, provider comparisons, and benchmark reports. Stay informed about pricing changes, new model releases, and performance trends.
Open Source
Entire registry is open source and community-driven. Contribute new models, providers, and mappings through pull requests with automated schema validation.
Model Vendors
OpenAI
Anthropic
Meta
Mistral
DeepSeek
Microsoft
Alibaba
IBM
xAI
Inference Providers
AWS Bedrock
Azure AI
Google Cloud
Groq
Together AI
Fireworks
Replicate
NVIDIA
Hugging Face
SambaNova
How It Works
01
Browse
Explore 82+ models by capability, modality, context window, or vendor. Filter by reasoning, vision, code generation, and more.
02
Compare
See providers side-by-side with pricing, latency, and availability data. Find the best fit for your budget and performance needs.
03
Integrate
Use the public REST API to query models and providers programmatically. No auth required. Build tools on top of standardized data.
API Endpoints
GET /modelsList and search all models with filtering by vendor, capability, and modality
GET /providersList all inference providers with pricing and availability data
GET /telemetryReal-time health, latency, and reliability metrics for all providers
GET /searchFull-text search across models, providers, and mappings