0.7.3

Added

• MiniCPM-V 4.6 — OpenBMB's ultra-efficient 1B multimodal model (vision + video), edge-deployable, 256K context
• Aya Expanse 32B — Cohere For AI's 32B multilingual model, 23 languages, 8K context
• Tiny Aya — Cohere For AI's compact 3.35B multilingual model, 70+ languages, edge-optimized

0.7.2

Added

• Hy3 Preview — Tencent's 295B MoE / 21B active, fast+slow thinking, 256K context, open-weight
• Laguna M.1 — Poolside AI's 225B MoE / 23B active, agentic coding flagship, 128K context
• Mappings: Hy3 Preview on SiliconFlow and OpenRouter, Laguna M.1 on OpenRouter

0.7.1

Added

• 4 new models — MiMo-V2.5-Pro (Xiaomi), Granite 4.1 8B, Granite 4.1 30B (IBM), Cotype Nano (MTS AI)
• 2 new providers — Xiaomi MiMo, IBM watsonx.ai
• 5 new provider-model mappings for MiMo-V2.5-Pro and Granite 4.1 across OpenRouter, Xiaomi, and IBM watsonx
• Vendor logo system expanded — added logo mappings for IBM (Granite), Xiaomi MiMo, MWS AI (Cotype), GigaChat, Yandex, ISSAI (KazLLM), AlemLLM

0.7.0

Added

• 9 new providers — Amazon Bedrock, Azure AI, Replicate, Anyscale, SiliconFlow, Hugging Face Inference, Perplexity, Yandex Cloud, Sber
• 11 new models:
  • GPT-5.5 (OpenAI's most capable model for complex real-world work)
  • Muse Spark (Meta Superintelligence Labs' first model with agentic capabilities)
  • Codestral (Mistral's specialized code generation model)
  • Qwen 3.6 35B-A3B, Qwen 3.6 27B, Qwen 3.6 Plus (Alibaba's latest generation)
  • YandexGPT 5 Lite (Yandex's 8B open-weight model for Russian/English)
  • GigaChat 3.1 Ultra, GigaChat 3.1 Lightning (Sber's MoE models)
  • ISSAI KazLLM 1.0 70B (Kazakh language model from Nazarbayev University)
  • AlemLLM (Kazakhstan's 247B MoE flagship from Astana Hub)
• 27 new mappings expanding coverage of existing models across new providers (Amazon Bedrock, Azure AI, SiliconFlow, Hugging Face, Replicate, Anyscale, Perplexity, Fireworks, Groq)

Changed

• Total coverage: 70+ models · 37+ providers · 130+ mappings

0.6.0

Added

• Registry expanded to 50+ models added Llama family (3.1 8B, 3.2 3B/11B/90B, 3.3 70B, 4 Scout, 4 Maverick), Gemma 3 (1B/4B/12B/27B), Gemma 4 (E2B/E4B/26B/31B), Qwen3 (32B, 235B, Coder), QwQ-32B, Mistral Small 3.1, Phi-4, Phi-4 Mini, Whisper (audio modality), GPT-OSS (120B, 20B)
• Registry expanded to 26+ providers added SambaNova, Scaleway, Nebius, Hyperbolic, Fireworks, Baseten, Novita, NLP Cloud, Alibaba Model Studio, Modal, Inference.net with verified API endpoints
• 100+ provider-model mappings with pricing data for all new providers

0.4.0

OpenModels Registry v0.4.0

Major registry expansion – 44 models, 19 providers, 72 mappings with verified pricing data.

What's New

44 Model Definitions

Full coverage of major LLM families as of May 2026:

Vendor	Models
OpenAI	GPT-4, GPT-5, GPT-5.4, GPT-5.4 Mini, GPT-5.5, GPT-5.5 Pro, GPT-OSS 20B, GPT-OSS 120B
Anthropic	Claude 3 Opus, Claude Haiku 4.5, Claude Sonnet 4.5, Claude Sonnet 4.6, Claude Opus 4.6, Claude Opus 4.7
Google	Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 3.1 Pro, Gemma 4 31B
xAI	Grok 4, Grok 4.1 Fast, Grok 4.20, Grok 4.3
DeepSeek	DeepSeek V3, DeepSeek R1, DeepSeek V4, DeepSeek V4 Pro, DeepSeek V4 Flash
Meta	Llama 3.3 70B, Llama 4 Scout, Llama 4 Maverick
Mistral	Mistral Medium 3.5, Mistral Large 3, Mistral Small 4, Devstral 2
NVIDIA	Nemotron 3 Super 120B, Nemotron Nano 9B
Others	Kimi K2.6, Command A, Command R7B, Qwen3 Coder, Qwen 3.6, GLM-4.7, GLM-5.1, M2.7

19 Inference Providers

Anthropic · Cerebras · Cloudflare Workers AI · Cohere · Deep Infra · DeepSeek · Google AI Studio · Google (Vertex AI) · Groq · Meta · MiniMax · Mistral · Moonshot · NVIDIA NIM · OpenAI · OpenRouter · Together AI · xAI · Zhipu AI

72 Provider-Model Mappings

• Pricing verified against official documentation (OpenAI, Anthropic, xAI, Mistral, Google, DeepSeek, NVIDIA)
• NVIDIA NIM free endpoint mappings for open-weight models
• Deep Infra serverless inference with competitive pricing
• Extensible pricing model supporting cache, image, audio, reasoning tokens, and search grounding

Validation & CI

• Automated schema validation on every PR via GitHub Actions
• Referential integrity checks (mappings → models + providers)
• Duplicate ID detection
• PR comment reporting with detailed error messages

Add models, providers, or mappings via pull request — validation runs automatically.

0.2.0

Fixed

• CI workflow now correctly captures validation script exit code (was always 0 due to pipe)

Added

• Initial registry structure with models, providers, and mappings directories
• JSON Schema definitions for model, provider, and mapping validation
• Python validation script with schema, duplicate ID, and referential integrity checks
• GitHub Actions workflow for automated PR validation with comment reporting
• Extended pricing model support (cache, image, audio, reasoning, search grounding)
• Example mapping file demonstrating extensible pricing dimensions
• VERSION file for tracking registry schema version
• CHANGELOG.md for documenting changes