Z.ai: GLM 4.5V

Description

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a "thinking mode" for deep reasoning and a "non-thinking mode" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

Raw fields snapshot

{
  "id": "z-ai/glm-4.5v",
  "name": "Z.ai: GLM 4.5V",
  "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)",
  "created": 1754922288,
  "canonical_slug": "z-ai/glm-4.5v",
  "hugging_face_id": "zai-org/GLM-4.5V",
  "source_type": "openrouter_only",
  "context_length": 65536,
  "max_completion_tokens": 16384,
  "is_moderated": false,
  "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
      "text",
      "image"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
  },
  "input_modalities": [
    "text",
    "image"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text+image->text",
  "tokenizer": "Other",
  "instruct_type": null,
  "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
  ],
  "default_parameters": {
    "temperature": 0.75,
    "top_p": null,
    "frequency_penalty": null
  },
  "per_request_limits": null,
  "top_provider": {
    "context_length": 65536,
    "max_completion_tokens": 16384,
    "is_moderated": false
  },
  "pricing": {
    "prompt": "0.0000006",
    "completion": "0.0000018",
    "input_cache_read": "0.00000011"
  },
  "PPM": {
    "prompt": 0.6,
    "completion": 1.8,
    "input_cache_read": 0.11
  },
  "openrouter_raw": {
    "id": "z-ai/glm-4.5v",
    "canonical_slug": "z-ai/glm-4.5v",
    "hugging_face_id": "zai-org/GLM-4.5V",
    "name": "Z.ai: GLM 4.5V",
    "created": 1754922288,
    "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)",
    "context_length": 65536,
    "architecture": {
      "modality": "text+image->text",
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "Other",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0.0000006",
      "completion": "0.0000018",
      "input_cache_read": "0.00000011"
    },
    "top_provider": {
      "context_length": 65536,
      "max_completion_tokens": 16384,
      "is_moderated": false
    },
    "per_request_limits": null,
    "supported_parameters": [
      "frequency_penalty",
      "include_reasoning",
      "max_tokens",
      "presence_penalty",
      "reasoning",
      "repetition_penalty",
      "response_format",
      "seed",
      "stop",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_k",
      "top_p"
    ],
    "default_parameters": {
      "temperature": 0.75,
      "top_p": null,
      "frequency_penalty": null
    },
    "expiration_date": null
  }
}