stack-free-models.stack.json json {
"osr": "1",
"kind": "stack",
"name": "Free models",
"description": "Every request routed among hosted models that cost nothing per token; quality decides.",
"targets": [
{
"ocm": "1",
"id": "model-deepseek-deepseek-v4-flash-0731-free",
"kind": "llm",
"name": "DeepSeek V4 Flash 0731 (free)",
"description": "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....",
"publisher": "DeepSeek",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"deepseek",
"openrouter",
"open-weights",
"reasoning",
"free",
"tool-calling",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1048576
},
"quality_prior": 0.345,
"examples": [
"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows...."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1785478908",
"url": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731:free",
"key": "deepseek/deepseek-v4-flash-0731:free",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "deepseek/deepseek-v4-flash-0731:free",
"pricing": {
"input_usd_per_1m": 0,
"output_usd_per_1m": 0
},
"max_output_tokens": 393216,
"output_modalities": [
"text"
],
"hugging_face_id": "deepseek-ai/DeepSeek-V4-Flash-0731",
"reasoning": true,
"created": 1785478908,
"benchmarks": {
"intelligence_index": 34.5,
"coding_index": 69.1,
"agentic_index": 41.7,
"osr_index": 40,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-z-ai-glm-5-2-free",
"kind": "llm",
"name": "GLM 5.2 (free)",
"description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...",
"publisher": "Z.ai",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"z-ai",
"openrouter",
"open-weights",
"reasoning",
"free",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": false,
"supports_streaming": true,
"context_window": 32768
},
"quality_prior": 0.34,
"examples": [
"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1781631930",
"url": "https://openrouter.ai/z-ai/glm-5.2:free",
"key": "z-ai/glm-5.2:free",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "z-ai/glm-5.2:free",
"pricing": {
"input_usd_per_1m": 0,
"output_usd_per_1m": 0
},
"max_output_tokens": 29491,
"output_modalities": [
"text"
],
"hugging_face_id": "zai-org/GLM-5.2",
"reasoning": true,
"created": 1781631930,
"benchmarks": {
"intelligence_index": 34,
"coding_index": 68.8,
"agentic_index": 39.4,
"osr_index": 39.7,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-qwen-qwen3-8-27b-free",
"kind": "llm",
"name": "Qwen3.8 27B (free)",
"description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...",
"publisher": "Qwen",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"qwen",
"openrouter",
"open-weights",
"reasoning",
"free",
"tool-calling",
"image",
"video",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"video"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 262144
},
"quality_prior": 0.339,
"examples": [
"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1786722910",
"url": "https://openrouter.ai/qwen/qwen3.8-27b:free",
"key": "qwen/qwen3.8-27b:free",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "qwen/qwen3.8-27b:free",
"pricing": {
"input_usd_per_1m": 0,
"output_usd_per_1m": 0
},
"max_output_tokens": 235929,
"output_modalities": [
"text"
],
"hugging_face_id": "Qwen/Qwen3.8-27B",
"reasoning": true,
"created": 1786722910,
"benchmarks": {
"intelligence_index": 33.9,
"coding_index": 68.1,
"agentic_index": 46.5,
"osr_index": 39.6,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-thinkingmachines-inkling-small-free",
"kind": "llm",
"name": "Inkling Small (free)",
"description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...",
"publisher": "Thinking Machines",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"thinkingmachines",
"openrouter",
"open-weights",
"reasoning",
"free",
"tool-calling",
"image",
"audio",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"audio"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1048576
},
"quality_prior": 0.261,
"examples": [
"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1785443117",
"url": "https://openrouter.ai/thinkingmachines/inkling-small:free",
"key": "thinkingmachines/inkling-small:free",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "thinkingmachines/inkling-small:free",
"pricing": {
"input_usd_per_1m": 0,
"output_usd_per_1m": 0
},
"max_output_tokens": 262144,
"output_modalities": [
"text"
],
"hugging_face_id": "thinkingmachines/Inkling-Small",
"reasoning": true,
"created": 1785443117,
"benchmarks": {
"intelligence_index": 26.1,
"coding_index": 52.9,
"agentic_index": 25,
"osr_index": 35.2,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
],
"rules": [
{
"name": "hard-to-strongest",
"when": {
"min_complexity": 0.7
},
"prefer": [
"model-deepseek-deepseek-v4-flash-0731-free"
]
}
],
"objective": {
"quality": 0.7,
"cost": 0.8,
"latency": 0.2
},
"metadata": {
"source": {
"provider": "catalogue-stacks",
"path": "free-models",
"ref": "2026-09-19",
"url": "https://openrouter.ai/models",
"key": "catalogue-stacks/free-models",
"catalogue": "https://openrouter.ai/api/v1",
"generated": true
}
}
}
