{
  "object": "list",
  "data": [
    {
      "id": "aion-labs/aion-3.0-mini",
      "object": "model",
      "created": 1792811344,
      "owned_by": "aion-labs",
      "name": "AionLabs: Aion-3.0-Mini",
      "description": "Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...",
      "context_length": 131072,
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text->text"
      },
      "pricing": {
        "prompt": "0.00000099225",
        "completion": "0.0000019845",
        "request": "0",
        "image": "0",
        "input_cache_read": "0.00000025515"
      },
      "top_provider": {
        "context_length": 131072,
        "is_moderated": false
      }
    },
    {
      "id": "anthropic/claude-sonnet-5.5",
      "object": "model",
      "created": 1792811344,
      "owned_by": "anthropic",
      "name": "Anthropic: Claude Sonnet 5.5",
      "description": "Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...",
      "context_length": 1000000,
      "architecture": {
        "input_modalities": [
          "text",
          "image",
          "file"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text+image+file->text"
      },
      "pricing": {
        "prompt": "0.000002835",
        "completion": "0.000014175",
        "request": "0",
        "image": "0",
        "input_cache_read": "0.00000014175"
      },
      "top_provider": {
        "context_length": 1000000,
        "is_moderated": false
      }
    },
    {
      "id": "assemblyai/universal-3-5-pro",
      "object": "model",
      "created": 1792811344,
      "owned_by": "assemblyai",
      "name": "AssemblyAI: Universal-3.5 Pro",
      "description": "Universal-3.5 Pro is AssemblyAI's speech-to-text model served through its Sync API, returning a complete transcript with word-level timestamps in a single synchronous response for audio up to 20 minutes. It...",
      "architecture": {
        "input_modalities": [
          "audio"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "audio->text"
      },
      "top_provider": {
        "is_moderated": false
      }
    },
    {
      "id": "baai/bge-m3",
      "object": "model",
      "created": 1792811344,
      "owned_by": "baai",
      "name": "BAAI: bge-m3",
      "description": "The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.",
      "context_length": 8194,
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "embeddings"
        ],
        "modality": "text->embeddings"
      },
      "pricing": {
        "prompt": "0.000000014175",
        "completion": "0",
        "request": "0",
        "image": "0"
      },
      "top_provider": {
        "context_length": 8194,
        "is_moderated": false
      }
    },
    {
      "id": "black-forest-labs/flux-3-image",
      "object": "model",
      "created": 1792811344,
      "owned_by": "black-forest-labs",
      "name": "Black Forest Labs: FLUX 3 Image",
      "description": "FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers...",
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "image"
        ],
        "modality": "text->image"
      },
      "top_provider": {
        "is_moderated": false
      }
    },
    {
      "id": "bytedance-seed/seedream-4.5",
      "object": "model",
      "created": 1792811344,
      "owned_by": "bytedance-seed",
      "name": "ByteDance Seed: Seedream 4.5",
      "description": "Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details,...",
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "image"
        ],
        "modality": "text->image"
      },
      "top_provider": {
        "is_moderated": false
      }
    },
    {
      "id": "deepseek/deepseek-v4-flash",
      "object": "model",
      "created": 1792811344,
      "owned_by": "deepseek",
      "name": "DeepSeek: DeepSeek V4 Flash 0423",
      "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...",
      "context_length": 1048576,
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text->text"
      },
      "pricing": {
        "prompt": "0.0000001289925",
        "completion": "0.000000257985",
        "request": "0",
        "image": "0",
        "input_cache_read": "0.0000000257985"
      },
      "top_provider": {
        "context_length": 1048576,
        "is_moderated": false
      }
    },
    {
      "id": "elevenlabs/eleven-flash-v2",
      "object": "model",
      "created": 1792811344,
      "owned_by": "elevenlabs",
      "name": "ElevenLabs: Eleven Flash v2",
      "description": "Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a 30,000-character request limit.",
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "speech"
        ],
        "modality": "text->speech"
      },
      "top_provider": {
        "is_moderated": false
      }
    },
    {
      "id": "elevenlabs/eleven-multilingual-v2",
      "object": "model",
      "created": 1792811344,
      "owned_by": "elevenlabs",
      "name": "ElevenLabs: Eleven Multilingual v2",
      "description": "Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29 languages, and has a 10,000-character request...",
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "speech"
        ],
        "modality": "text->speech"
      },
      "top_provider": {
        "is_moderated": false
      }
    },
    {
      "id": "google/gemini-2.5-flash-image",
      "object": "model",
      "created": 1792811344,
      "owned_by": "google",
      "name": "Google: Nano Banana (Gemini 2.5 Flash Image)",
      "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...",
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "image"
        ],
        "modality": "text->image"
      },
      "top_provider": {
        "is_moderated": false
      }
    },
    {
      "id": "nvidia/nemotron-3.5-embed-1b:free",
      "object": "model",
      "created": 1792811344,
      "owned_by": "nvidia",
      "name": "NVIDIA: Nemotron 3.5 Embed 1B (free)",
      "description": "Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be...",
      "context_length": 32768,
      "architecture": {
        "input_modalities": [
          "text",
          "image"
        ],
        "output_modalities": [
          "embeddings"
        ],
        "modality": "text+image->embeddings"
      },
      "pricing": {
        "prompt": "0",
        "completion": "0",
        "request": "0",
        "image": "0"
      },
      "top_provider": {
        "context_length": 32768,
        "is_moderated": false
      }
    },
    {
      "id": "nvidia/nemotron-3.5-super-vl:free",
      "object": "model",
      "created": 1792811344,
      "owned_by": "nvidia",
      "name": "NVIDIA: Nemotron 3.5 Super VL (free)",
      "description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...",
      "context_length": 1000000,
      "architecture": {
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text+image+video->text"
      },
      "pricing": {
        "prompt": "0",
        "completion": "0",
        "request": "0",
        "image": "0"
      },
      "top_provider": {
        "context_length": 1000000,
        "is_moderated": false
      }
    },
    {
      "id": "openai/gpt-6-luna",
      "object": "model",
      "created": 1792811344,
      "owned_by": "openai",
      "name": "OpenAI: GPT-6 Luna",
      "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...",
      "context_length": 1050000,
      "architecture": {
        "input_modalities": [
          "file",
          "image",
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "file+image+text->text"
      },
      "pricing": {
        "prompt": "0.00000014175",
        "completion": "0.00000070875",
        "request": "0",
        "image": "0",
        "input_cache_read": "0.000000014175"
      },
      "top_provider": {
        "context_length": 1050000,
        "is_moderated": false
      }
    },
    {
      "id": "openai/whisper-1",
      "object": "model",
      "created": 1792811344,
      "owned_by": "openai",
      "name": "OpenAI: Whisper 1",
      "description": "Whisper is OpenAI's open-source automatic speech recognition model, available via API as `whisper-1`. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats...",
      "architecture": {
        "input_modalities": [
          "audio"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "audio->text"
      },
      "top_provider": {
        "is_moderated": false
      }
    },
    {
      "id": "qwen/qwen3-coder-30b-a3b-instruct",
      "object": "model",
      "created": 1792811344,
      "owned_by": "qwen",
      "name": "Qwen: Qwen3 Coder 30B A3B Instruct",
      "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...",
      "context_length": 262144,
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text->text"
      },
      "pricing": {
        "prompt": "0.000000099225",
        "completion": "0.0000003969",
        "request": "0",
        "image": "0"
      },
      "top_provider": {
        "context_length": 262144,
        "is_moderated": false
      }
    },
    {
      "id": "typesafe/jev-1.13.0",
      "object": "model",
      "created": 1789984193,
      "owned_by": "typesafe",
      "name": "Jev 1.13",
      "description": "Отвечает не текстом, а калиброванной вероятностью на типизированный вопрос о поданном тексте: да/нет, выбор из вариантов, оценка по шкале. Маршрут POST /v1/systemone — это не чат, поля messages у него нет. Основной язык модели — английский, остальные языки поддержаны заметно хуже: проверяйте качество на своей выборке. Известные ограничения провайдера: модель не считает, не сравнивает даты, не решает задач, требующих числовой точности, читает инструкции буквально и не генерирует текст.",
      "context_length": 64000,
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text->text"
      },
      "pricing": {
        "prompt": "0.000000059535",
        "completion": "0",
        "request": "0",
        "image": "0"
      },
      "top_provider": {
        "context_length": 64000,
        "is_moderated": false
      }
    },
    {
      "id": "typesafe/jev-latest",
      "object": "model",
      "created": 1789984193,
      "owned_by": "typesafe",
      "name": "Jev (последняя версия)",
      "description": "Плавающий алиас: провайдер обслуживает им текущую версию Jev. Цена совпадает с закреплённой версией. Отвечает не текстом, а калиброванной вероятностью на типизированный вопрос о поданном тексте: да/нет, выбор из вариантов, оценка по шкале. Маршрут POST /v1/systemone — это не чат, поля messages у него нет. Основной язык модели — английский, остальные языки поддержаны заметно хуже: проверяйте качество на своей выборке. Известные ограничения провайдера: модель не считает, не сравнивает даты, не решает задач, требующих числовой точности, читает инструкции буквально и не генерирует текст.",
      "context_length": 64000,
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text->text"
      },
      "pricing": {
        "prompt": "0.000000059535",
        "completion": "0",
        "request": "0",
        "image": "0"
      },
      "top_provider": {
        "context_length": 64000,
        "is_moderated": false
      }
    }
  ]
}