0.7.8

Added

• 9 new models:

  • Jamba Large 1.7 (AI21 Labs, Israel) — hybrid SSM-Transformer MoE, 256K context, enterprise-grade
  • Yi-Lightning (01.AI, China) — MoE architecture, top Chatbot Arena in Chinese/Math/Code
  • Falcon-H1 (TII, UAE) — hybrid Mamba-Transformer, outperforms Llama/Qwen in 30-70B range
  • Falcon 3 10B (TII, UAE) — #1 on HuggingFace leaderboard under 13B params
  • Palmyra X5 (Writer, USA) — 1M context window, adaptive reasoning, enterprise agents
  • DBRX (Databricks, USA) — 132B MoE (36B active), open-source enterprise model
  • Snowflake Arctic (Snowflake, USA) — 480B MoE (17B active), Apache 2.0, SQL/code specialist
  • StableLM 2 12B (Stability AI, UK) — 12.1B decoder, 2T tokens multilingual training
  • Alloma 8B Instruct (Uzbek LLM Lab, Uzbekistan) — first Uzbek-optimized LLM with custom tokenizer

• 5 new providers:

  • AI21 Labs — Jamba model family with hybrid SSM-Transformer architecture
  • Reka AI — multimodal models (text/image/video/audio) with Flash and Edge variants
  • Lambda — GPU cloud and managed inference API for open-source models
  • Snowflake Cortex AI — Arctic models integrated with Snowflake data platform
  • 01.AI — Yi model family with strong Chinese/multilingual capabilities

• New countries represented: Israel (IL), UAE (AE), Uzbekistan (UZ), UK (GB)

0.7.7

Added

• Country of origin field (country) added to all 88 models using ISO 3166-1 alpha-2 codes
• Countries represented: US, CN, FR, KZ, KR, AE, RU
• Model schema updated with optional country field

0.7.6

Added

• Solar Pro 3 — Upstage's 102B MoE language model (12B active params) with 128K context. Optimized for Korean with English and Japanese support. Strong reasoning, structured output, and agentic workflows.
• K2 Think — LLM360/MBZUAI's 32B open-weights reasoning model (Apache 2.0). Trained with RL and verifiable rewards for math, science, and code. ~2000 tok/s on Cerebras WSE.
• New provider: Upstage — Korean AI company with OpenAI-compatible API

0.7.5

Added

• Qwen 3.7 Max — Alibaba's flagship proprietary model for advanced agentic coding, complex reasoning, and long-horizon task execution. Ranked #13 in Arena AI Text, #7 in Math, #10 in Coding. Supports 1000+ tool integrations and 35-hour sustained autonomous operation.
• Qwen 3.7 Plus — Alibaba's multimodal variant optimized for vision understanding. Ranked #5 globally in Arena AI Vision leaderboard.

0.7.4

Added

• Gemini 3 Flash — Google's balanced model combining Gemini 3 Pro reasoning with Flash-line latency and cost efficiency. 1M context, configurable thinking levels, streaming function calling.
• Gemini 3.1 Flash-Lite — Google's most cost-efficient model optimized for high-volume, low-latency tasks. 2.5x faster TTFT vs Gemini 2.5 Flash, 1M context, full multimodal support.
• Mappings: Gemini 3 Flash on Google Vertex AI and Google AI Studio ($0.50/$3.00 per 1M tokens)
• Mappings: Gemini 3.1 Flash-Lite on Google Vertex AI and Google AI Studio ($0.25/$1.50 per 1M tokens)

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