Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Qwen3.5-122B-A10B - Model - OpenSmartRoute
Modelv1.0.0
Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference eff
Reference model card from the OpenRouter listing - model qwen/qwen3.5-122b-a10b. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Facts
Vendor
Qwen
Context window
262,144 tokens
Max output
65,536 tokens
Input price
$0.26 / 1M tokens
Output price
$2.08 / 1M tokens
Input
text, image, video
Output
text
Tool calling
yes
Structured outputs
yes
Reasoning
yes
Open weights
Qwen/Qwen3.5-122B-A10B
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model qwen/qwen3.5-122b-a10b
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "model-qwen-qwen3-5-122b-a10b", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-qwen-qwen3-5-122b-a10b.ocm.jsonjson
{
"ocm": "1",
"id": "model-qwen-qwen3-5-122b-a10b",
"kind": "llm",
"name": "Qwen3.5-122B-A10B",
"description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...",
"publisher": "Qwen",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"qwen",
"openrouter",
"open-weights",
"reasoning",
"tool-calling",
"image",
"video",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"video"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 262144
},
"quality_prior": 0.162,
"examples": [
"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1772053789",
"url": "https://openrouter.ai/qwen/qwen3.5-122b-a10b",
"key": "qwen/qwen3.5-122b-a10b",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "qwen/qwen3.5-122b-a10b",
"pricing": {
"input_usd_per_1m": 0.26,
"output_usd_per_1m": 2.08
},
"max_output_tokens": 65536,
"output_modalities": [
"text"
],
"hugging_face_id": "Qwen/Qwen3.5-122B-A10B",
"reasoning": true,
"created": 1772053789,
"benchmarks": {
"intelligence_index": 16.2,
"coding_index": 45.7,
"agentic_index": 9.6,
"hub_downloads_total": 6971669,
"hub_likes": 619,
"hub_trending": 2,
"hub_downloads": 364876,
"osr_index": 29.5,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0.00117
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-qwen-qwen3-5-122b-a10b/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
