stack-qwen.stack.json json {
"osr": "1",
"kind": "stack",
"name": "Qwen tiers",
"description": "Qwen only: Qwen3.7 Flash for everyday requests, Qwen3.6 Flash for moderate work, Qwen3.8 Max (0902) for hard ones - with complexity rules and a cost-aware objective.",
"targets": [
{
"ocm": "1",
"id": "model-qwen-qwen3-7-flash",
"kind": "llm",
"name": "Qwen3.7 Flash",
"description": "Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...",
"publisher": "Qwen",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"qwen",
"openrouter",
"reasoning",
"tool-calling",
"image",
"video",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"video"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1000000
},
"quality_prior": 0.6,
"examples": [
"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1785190561",
"url": "https://openrouter.ai/qwen/qwen3.7-flash",
"key": "qwen/qwen3.7-flash",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "qwen/qwen3.7-flash",
"pricing": {
"input_usd_per_1m": 0.03,
"output_usd_per_1m": 0.13,
"cache_read_usd_per_1m": 0.006
},
"max_output_tokens": 65536,
"output_modalities": [
"text"
],
"reasoning": true,
"created": 1785190561
},
"cost": {
"usd_per_1k_tokens": 0.00008
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-qwen-qwen3-6-flash",
"kind": "llm",
"name": "Qwen3.6 Flash",
"description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...",
"publisher": "Qwen",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"qwen",
"openrouter",
"reasoning",
"tool-calling",
"image",
"video",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"video"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1000000
},
"quality_prior": 0.6,
"examples": [
"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1777261362",
"url": "https://openrouter.ai/qwen/qwen3.6-flash",
"key": "qwen/qwen3.6-flash",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "qwen/qwen3.6-flash",
"pricing": {
"input_usd_per_1m": 0.1875,
"output_usd_per_1m": 1.125
},
"max_output_tokens": 65536,
"output_modalities": [
"text"
],
"reasoning": true,
"created": 1777261362
},
"cost": {
"usd_per_1k_tokens": 0.000656
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-qwen-qwen3-8-max-0902",
"kind": "llm",
"name": "Qwen3.8 Max (0902)",
"description": "Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...",
"publisher": "Qwen",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"qwen",
"openrouter",
"reasoning",
"tool-calling",
"image",
"video",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"video"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1000000
},
"quality_prior": 0.454,
"examples": [
"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1788469704",
"url": "https://openrouter.ai/qwen/qwen3.8-max-0902",
"key": "qwen/qwen3.8-max-0902",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "qwen/qwen3.8-max-0902",
"pricing": {
"input_usd_per_1m": 2,
"output_usd_per_1m": 6,
"cache_read_usd_per_1m": 0.25
},
"max_output_tokens": 131072,
"output_modalities": [
"text"
],
"reasoning": true,
"created": 1788469704,
"benchmarks": {
"intelligence_index": 45.4,
"coding_index": 76.2,
"agentic_index": 56.1,
"osr_index": 46.2,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0.004
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
],
"rules": [
{
"name": "hard-to-strongest",
"when": {
"min_complexity": 0.7
},
"prefer": [
"model-qwen-qwen3-8-max-0902"
]
},
{
"name": "easy-stays-cheap",
"when": {
"max_complexity": 0.3
},
"avoid": [
"model-qwen-qwen3-8-max-0902"
]
}
],
"objective": {
"quality": 0.7,
"cost": 0.8,
"latency": 0.2
},
"metadata": {
"source": {
"provider": "catalogue-stacks",
"path": "qwen",
"ref": "2026-09-19",
"url": "https://openrouter.ai/qwen",
"key": "catalogue-stacks/qwen",
"catalogue": "https://openrouter.ai/api/v1",
"generated": true
}
}
}
