[
  {
    "id": "google/lyria-3-clip-preview",
    "name": "Google: Lyria 3 Clip Preview",
    "context": 1048576,
    "modality": "text+image->text+audio",
    "input": "text+image",
    "output": "text+audio",
    "created": 1774907255,
    "description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate..."
  },
  {
    "id": "google/lyria-3-pro-preview",
    "name": "Google: Lyria 3 Pro Preview",
    "context": 1048576,
    "modality": "text+image->text+audio",
    "input": "text+image",
    "output": "text+audio",
    "created": 1774907286,
    "description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz..."
  },
  {
    "id": "qwen/qwen3-coder:free",
    "name": "Qwen: Qwen3 Coder 480B A35B (free)",
    "context": 1048576,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1753230546,
    "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over..."
  },
  {
    "id": "nvidia/nemotron-3-super-120b-a12b:free",
    "name": "NVIDIA: Nemotron 3 Super (free)",
    "context": 1000000,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1773245239,
    "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer..."
  },
  {
    "id": "nvidia/nemotron-3-ultra-550b-a55b:free",
    "name": "NVIDIA: Nemotron 3 Ultra (free)",
    "context": 1000000,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1780551208,
    "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it..."
  },
  {
    "id": "google/gemma-4-26b-a4b-it:free",
    "name": "Google: Gemma 4 26B A4B  (free)",
    "context": 262144,
    "modality": "text+image+video->text",
    "input": "image+text+video",
    "output": "text",
    "created": 1775227989,
    "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at..."
  },
  {
    "id": "google/gemma-4-31b-it:free",
    "name": "Google: Gemma 4 31B (free)",
    "context": 262144,
    "modality": "text+image+video->text",
    "input": "image+text+video",
    "output": "text",
    "created": 1775148486,
    "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function..."
  },
  {
    "id": "poolside/laguna-m.1:free",
    "name": "Poolside: Laguna M.1 (free)",
    "context": 262144,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1777388504,
    "description": "Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K..."
  },
  {
    "id": "poolside/laguna-xs.2:free",
    "name": "Poolside: Laguna XS.2 (free)",
    "context": 262144,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1777389604,
    "description": "Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering..."
  },
  {
    "id": "qwen/qwen3-next-80b-a3b-instruct:free",
    "name": "Qwen: Qwen3 Next 80B A3B Instruct (free)",
    "context": 262144,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1757612213,
    "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual..."
  },
  {
    "id": "cohere/north-mini-code:free",
    "name": "Cohere: North Mini Code (free)",
    "context": 256000,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1781723748,
    "description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized..."
  },
  {
    "id": "nvidia/nemotron-3-nano-30b-a3b:free",
    "name": "NVIDIA: Nemotron 3 Nano 30B A3B (free)",
    "context": 256000,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1765731275,
    "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully..."
  },
  {
    "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
    "name": "NVIDIA: Nemotron 3 Nano Omni (free)",
    "context": 256000,
    "modality": "text+image+audio+video->text",
    "input": "text+audio+image+video",
    "output": "text",
    "created": 1777393095,
    "description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and..."
  },
  {
    "id": "openrouter/free",
    "name": "Free Models Router",
    "context": 200000,
    "modality": "text+image->text",
    "input": "text+image",
    "output": "text",
    "created": 1769917427,
    "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that..."
  },
  {
    "id": "meta-llama/llama-3.2-3b-instruct:free",
    "name": "Meta: Llama 3.2 3B Instruct (free)",
    "context": 131072,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1727222400,
    "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it..."
  },
  {
    "id": "meta-llama/llama-3.3-70b-instruct:free",
    "name": "Meta: Llama 3.3 70B Instruct (free)",
    "context": 131072,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1733506137,
    "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model..."
  },
  {
    "id": "nousresearch/hermes-3-llama-3.1-405b:free",
    "name": "Nous: Hermes 3 405B Instruct (free)",
    "context": 131072,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1723766400,
    "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the..."
  },
  {
    "id": "openai/gpt-oss-120b:free",
    "name": "OpenAI: gpt-oss-120b (free)",
    "context": 131072,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1754414231,
    "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized..."
  },
  {
    "id": "openai/gpt-oss-20b:free",
    "name": "OpenAI: gpt-oss-20b (free)",
    "context": 131072,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1754414229,
    "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for..."
  },
  {
    "id": "nvidia/nemotron-3.5-content-safety:free",
    "name": "NVIDIA: Nemotron 3.5 Content Safety (free)",
    "context": 128000,
    "modality": "text+image->text",
    "input": "text+image",
    "output": "text",
    "created": 1780581864,
    "description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting..."
  },
  {
    "id": "nvidia/nemotron-nano-12b-v2-vl:free",
    "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)",
    "context": 128000,
    "modality": "text+image+video->text",
    "input": "image+text+video",
    "output": "text",
    "created": 1761675565,
    "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s..."
  },
  {
    "id": "nvidia/nemotron-nano-9b-v2:free",
    "name": "NVIDIA: Nemotron Nano 9B V2 (free)",
    "context": 128000,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1757106807,
    "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and..."
  },
  {
    "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
    "name": "Venice: Uncensored (free)",
    "context": 32768,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1752094966,
    "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving..."
  },
  {
    "id": "liquid/lfm-2.5-1.2b-instruct:free",
    "name": "LiquidAI: LFM2.5-1.2B-Instruct (free)",
    "context": 32768,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1768927521,
    "description": "LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support."
  },
  {
    "id": "liquid/lfm-2.5-1.2b-thinking:free",
    "name": "LiquidAI: LFM2.5-1.2B-Thinking (free)",
    "context": 32768,
    "modality": "text->text",
    "input": "text",
    "output": "text",
    "created": 1768927527,
    "description": "LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is..."
  }
]