stack-z-ai.stack.json json {
"osr": "1",
"kind": "stack",
"name": "Z.ai tiers",
"description": "Z.ai only: GLM Flash Latest for everyday requests, GLM 4.5V for moderate work, GLM 5.3 for hard ones - with complexity rules and a cost-aware objective.",
"targets": [
{
"ocm": "1",
"id": "model-z-ai-glm-flash-latest",
"kind": "llm",
"name": "GLM Flash Latest",
"description": "This model always redirects to the latest model in the GLM Flash family.",
"publisher": "Z.ai",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"z-ai",
"openrouter",
"reasoning",
"tool-calling",
"image",
"video",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"video"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1310720
},
"quality_prior": 0.6,
"examples": [
"This model always redirects to the latest model in the GLM Flash family."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1787817633",
"url": "https://openrouter.ai/~z-ai/glm-flash-latest",
"key": "~z-ai/glm-flash-latest",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "~z-ai/glm-flash-latest",
"pricing": {
"input_usd_per_1m": 0.075,
"output_usd_per_1m": 0.25,
"cache_read_usd_per_1m": 0.015
},
"max_output_tokens": 131072,
"output_modalities": [
"text"
],
"reasoning": true,
"created": 1787817633
},
"cost": {
"usd_per_1k_tokens": 0.000162
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-z-ai-glm-4-5v",
"kind": "llm",
"name": "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,...",
"publisher": "Z.ai",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"z-ai",
"openrouter",
"open-weights",
"reasoning",
"tool-calling",
"image",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 65536
},
"quality_prior": 0.6,
"examples": [
"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,..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1754922288",
"url": "https://openrouter.ai/z-ai/glm-4.5v",
"key": "z-ai/glm-4.5v",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "z-ai/glm-4.5v",
"pricing": {
"input_usd_per_1m": 0.6,
"output_usd_per_1m": 1.8,
"cache_read_usd_per_1m": 0.11
},
"max_output_tokens": 16384,
"output_modalities": [
"text"
],
"hugging_face_id": "zai-org/GLM-4.5V",
"reasoning": true,
"created": 1754922288,
"benchmarks": {
"hub_downloads": 46218,
"hub_trending": 0,
"hub_likes": 722,
"hub_downloads_total": 1040140
}
},
"cost": {
"usd_per_1k_tokens": 0.0012
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-z-ai-glm-5-3",
"kind": "llm",
"name": "GLM 5.3",
"description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...",
"publisher": "Z.ai",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"z-ai",
"openrouter",
"open-weights",
"reasoning",
"tool-calling",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1310720
},
"quality_prior": 0.449,
"examples": [
"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1787086655",
"url": "https://openrouter.ai/z-ai/glm-5.3",
"key": "z-ai/glm-5.3",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "z-ai/glm-5.3",
"pricing": {
"input_usd_per_1m": 0.91,
"output_usd_per_1m": 2.86,
"cache_read_usd_per_1m": 0.169
},
"max_output_tokens": 131072,
"output_modalities": [
"text"
],
"hugging_face_id": "zai-org/GLM-5.3",
"reasoning": true,
"created": 1787086655,
"benchmarks": {
"intelligence_index": 44.9,
"coding_index": 74.8,
"agentic_index": 53.4,
"hub_downloads": 888143,
"hub_downloads_total": 888143,
"hub_trending": 48,
"hub_likes": 1867,
"osr_index": 45.9,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0.001885
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
],
"rules": [
{
"name": "hard-to-strongest",
"when": {
"min_complexity": 0.7
},
"prefer": [
"model-z-ai-glm-5-3"
]
},
{
"name": "easy-stays-cheap",
"when": {
"max_complexity": 0.3
},
"avoid": [
"model-z-ai-glm-5-3"
]
}
],
"objective": {
"quality": 0.7,
"cost": 0.8,
"latency": 0.2
},
"metadata": {
"source": {
"provider": "catalogue-stacks",
"path": "z-ai",
"ref": "2026-09-19",
"url": "https://openrouter.ai/z-ai",
"key": "catalogue-stacks/z-ai",
"catalogue": "https://openrouter.ai/api/v1",
"generated": true
}
}
}
