{
  "service": "Adzuki AI",
  "url": "https://adzukiai.com",
  "docs": "https://adzukiai.com/docs",
  "api_base": "https://adzukiai.com/v1",
  "wire_format": "OpenAI Chat Completions",
  "currency": "USD",
  "unit": "per 1,000,000 tokens",
  "billing": "prepaid balance, per token, no subscription",
  "restricted_for_us_federal_use": [
    "deepseek-v4-pro",
    "deepseek-v4.1-flash"
  ],
  "data_processing_location": "mainland China (model inference), US/EU (account and billing)",
  "updated": "2026-11-11",
  "models": [
    {
      "id": "doubao-seed-2.0-lite",
      "name": "Doubao-Seed-2.0-Lite",
      "vendor": "ByteDance Doubao",
      "input_per_1m": 0.0519,
      "cached_input_per_1m": 0.0104,
      "output_per_1m": 0.3111,
      "tags": [
        "budget",
        "fast"
      ],
      "pricing_page": "https://adzukiai.com/models"
    },
    {
      "id": "glm-5.3-flash",
      "name": "GLM-5.3-Flash",
      "vendor": "Zhipu AI",
      "input_per_1m": 0.0553,
      "cached_input_per_1m": 0.0159,
      "output_per_1m": 0.1936,
      "tags": [
        "budget",
        "fast"
      ],
      "pricing_page": "https://adzukiai.com/models"
    },
    {
      "id": "doubao-seed-2.1-lite",
      "name": "Doubao-Seed-2.1-Lite",
      "vendor": "ByteDance Doubao",
      "input_per_1m": 0.0691,
      "cached_input_per_1m": 0.0138,
      "output_per_1m": 0.2334,
      "tags": [
        "budget",
        "fast"
      ],
      "pricing_page": "https://adzukiai.com/models"
    },
    {
      "id": "mimo-v2.5",
      "name": "MiMo-V2.5",
      "vendor": "Xiaomi MiMo",
      "input_per_1m": 0.0927,
      "cached_input_per_1m": 0.0019,
      "output_per_1m": 0.1854,
      "tags": [
        "budget",
        "cheap cache"
      ],
      "pricing_page": "https://adzukiai.com/models"
    },
    {
      "id": "deepseek-v4.1-flash",
      "name": "DeepSeek-V4.1-Flash",
      "vendor": "DeepSeek",
      "input_per_1m": 0.1383,
      "cached_input_per_1m": 0.0028,
      "output_per_1m": 0.5531,
      "tags": [
        "balanced",
        "cheap cache"
      ],
      "pricing_page": "https://adzukiai.com/models"
    },
    {
      "id": "mimo-v2.5-pro",
      "name": "MiMo-V2.5-Pro",
      "vendor": "Xiaomi MiMo",
      "input_per_1m": 0.2781,
      "cached_input_per_1m": 0.0023,
      "output_per_1m": 0.5563,
      "tags": [
        "balanced",
        "cheap cache"
      ],
      "pricing_page": "https://adzukiai.com/mimo-v2.5-pro"
    },
    {
      "id": "minimax-m3",
      "name": "MiniMax-M3",
      "vendor": "MiniMax",
      "input_per_1m": 0.3564,
      "cached_input_per_1m": 0.0713,
      "output_per_1m": 1.4256,
      "tags": [
        "flagship",
        "long context"
      ],
      "pricing_page": "https://adzukiai.com/minimax-m3"
    },
    {
      "id": "doubao-seed-2.1-pro",
      "name": "Doubao-Seed-2.1-Pro",
      "vendor": "ByteDance Doubao",
      "input_per_1m": 0.5186,
      "cached_input_per_1m": 0.1037,
      "output_per_1m": 2.5929,
      "tags": [
        "flagship"
      ],
      "pricing_page": "https://adzukiai.com/doubao-seed-2.1-pro"
    },
    {
      "id": "glm-5.3",
      "name": "GLM-5.3",
      "vendor": "Zhipu AI",
      "input_per_1m": 0.5531,
      "cached_input_per_1m": 0.1383,
      "output_per_1m": 1.936,
      "tags": [
        "flagship"
      ],
      "pricing_page": "https://adzukiai.com/glm-5.3"
    },
    {
      "id": "deepseek-v4-pro",
      "name": "DeepSeek-V4-Pro",
      "vendor": "DeepSeek",
      "input_per_1m": 0.9051,
      "cached_input_per_1m": 0.0302,
      "output_per_1m": 2.7154,
      "tags": [
        "flagship"
      ],
      "context_tokens": 1000000,
      "max_output_tokens": 384000,
      "rate_limit_rpm": 60,
      "rate_limit_tpm": 100000,
      "capabilities": [
        "text in / text out",
        "implicit prompt caching",
        "structured output",
        "deep-thinking mode"
      ],
      "pricing_page": "https://adzukiai.com/deepseek-v4-pro"
    },
    {
      "id": "qwen3.8-max",
      "name": "Qwen-3.8-Max",
      "vendor": "Alibaba Qwen",
      "input_per_1m": 1.5086,
      "cached_input_per_1m": 0.1886,
      "output_per_1m": 4.5257,
      "tags": [
        "flagship",
        "long context"
      ],
      "pricing_page": "https://adzukiai.com/qwen3.8-max"
    },
    {
      "id": "kimi-k3.1-pro",
      "name": "Kimi-K3.1-Pro",
      "vendor": "Moonshot AI",
      "input_per_1m": 1.8571,
      "cached_input_per_1m": 0.1857,
      "output_per_1m": 9.7143,
      "tags": [
        "premium",
        "long context"
      ],
      "pricing_page": "https://adzukiai.com/kimi-k3.1-pro"
    },
    {
      "id": "kimi-k3",
      "name": "Kimi-K3",
      "vendor": "Moonshot AI",
      "input_per_1m": 2.2,
      "cached_input_per_1m": 0.22,
      "output_per_1m": 11.0,
      "tags": [
        "premium",
        "long context"
      ],
      "pricing_page": "https://adzukiai.com/models"
    }
  ]
}