{
  "_meta": {
    "source": "https://apipriceindex.com/api/deepinfra/glm-4.7-flash",
    "attribution": "apipriceindex.com",
    "license": "CC BY 4.0",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "note": "Free to reuse with attribution to apipriceindex.com.",
    "generated_at": "2026-09-05T08:15:06.210Z"
  },
  "id": "deepinfra:glm-4.7-flash",
  "name": "GLM 4.7 Flash (DeepInfra)",
  "base_model": "glm-4.7-flash",
  "provider": {
    "id": "deepinfra",
    "name": "DeepInfra",
    "url": "https://deepinfra.com"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "function-calling"
  ],
  "context_window": 202752,
  "max_output": 16384,
  "pricing": {
    "model_id": "deepinfra:glm-4.7-flash",
    "input": 0.06,
    "output": 0.4,
    "cached_input": 0.01,
    "source_url": "https://openrouter.ai/z-ai/glm-4.7-flash",
    "verified_at": "2026-09-05T08:00:57Z",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.06,
        "output": 0.4,
        "url": "https://openrouter.ai/z-ai/glm-4.7-flash",
        "verified_at": "2026-09-05T08:00:57Z"
      },
      {
        "name": "LiteLLM",
        "input": 0.06,
        "output": 0.4,
        "url": "https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json",
        "verified_at": "2026-09-03T20:47:46Z"
      },
      {
        "name": "models.dev",
        "input": 0.06,
        "output": 0.4,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [
    [
      "2026-09-03",
      0.06,
      0.4
    ]
  ],
  "latency": [],
  "license": {
    "license": "MIT",
    "tier": "permissive",
    "open_weights": true,
    "source_url": "https://huggingface.co/zai-org"
  },
  "cutoff": {
    "cutoff": "2026-01",
    "label": "January 2026",
    "source_url": "https://aiknowledgecutoff.com/"
  },
  "intelligence": {
    "score": 23.3,
    "model_name": "GLM-4.7-Flash",
    "verified_at": "2026-09-04",
    "benchmark_label": "Artificial Analysis Intelligence Index",
    "source_url": "https://artificialanalysis.ai/"
  },
  "quality": {
    "elo": 1366,
    "arena_name": "Z.ai: GLM 4.7 Flash",
    "verified_at": "2026-09-04",
    "benchmark_label": "LMArena (Chatbot Arena)",
    "source_url": "https://lmarena.ai/leaderboard/text"
  },
  "api": {
    "base_url": "https://openrouter.ai/api/v1",
    "model": "z-ai/glm-4.7-flash",
    "via": "openrouter",
    "key_env": "OPENROUTER_API_KEY",
    "docs_url": "https://openrouter.ai/z-ai/glm-4.7-flash",
    "or_provider": "DeepInfra"
  },
  "facts": [
    "GLM 4.7 Flash (DeepInfra) costs $0.06 input / $0.40 output per 1M tokens.",
    "Cached input cuts the input price by 83%.",
    "A chatbot workload (1000 in / 500 out tokens) costs $0.26 per 1,000 requests.",
    "Cross-checked: LiteLLM's public price index independently lists DeepInfra's glm-4.7-flash at $0.06/$0.40 per 1M — corroborating the price shown here (within 0%).",
    "Handles a 202,752-token context window, up to 16,384 output tokens.",
    "Open weights under MIT — permissive licence.",
    "Training knowledge cutoff: January 2026.",
    "Scores 1366 on the LMArena (Chatbot Arena) (human-preference leaderboard) for glm-4.7-flash.",
    "Scores 23.3 on the Artificial Analysis Intelligence Index for glm-4.7-flash.",
    "0% pricier than the cheapest glm-4.7-flash endpoint ($0.46 on Venice).",
    "Value: 1366 Elo at $0.46 blended = 2970 Elo points per dollar — ranking #44 of 321 priced & rated endpoints in the index.",
    "Intelligence value: 23.3 index at $0.46 blended = 50.7 index points per dollar — ranking #68 of 373 priced & AA-rated endpoints in the index."
  ]
}