Qwen3.5-122B-A10B
VerifiedOpen-weight multimodal model for long-context text, image, and video tasks.
About Qwen3.5-122B-A10B
The design centers on a large-scale architecture optimized for simultaneous processing of multiple modalities. Its 122B parameters provide capacity for detailed cross-modal reasoning while the extended context length accommodates lengthy inputs such as full videos or extensive documents. Open weights allow full inspection and modification by the community.
Key strengths include robust performance on tasks that combine visual and textual data over long sequences without requiring external retrieval. The model maintains coherence across modalities, supporting consistent outputs in complex scenarios. Its open-weight release lowers barriers for research and commercial adaptation.
Typical usage covers video analysis, image-grounded question answering, and multimodal content creation. Developers fine-tune it for domain-specific needs such as medical imaging or educational video tools. Integration into pipelines benefits from its native support for diverse input formats.
Capabilities
How Qwen3.5-122B-A10B compares
Qwen3.5-122B-A10B (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Qwen3.5-122B-A10B ranks #57 of 122
Nova 2 LiteSources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long-context document analysis
Processes extended multimodal inputs such as lengthy reports containing text, charts, and diagrams within its 262144-token context window.
Complex visual reasoning tasks
Handles integrated text and image inputs for detailed interpretation across large volumes of data provided by Alibaba Qwen.
Multimodal research workflows
Supports sustained analysis of mixed media sources over extended sequences without losing coherence in context.
Strengths & limitations
Strengths
- +Very large 256k token context window
- +Native video input support
- +Multimodal text-image-video integration
- +Backed by Alibaba Qwen research
Limitations
- –High inference compute requirements
- –No audio modality
- –Potential quality variance on long videos
Cost calculator
Estimate what Qwen3.5-122B-A10B would cost for your usage.
Based on Qwen3.5-122B-A10B's $0.26/1M input · $2.08/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "qwen/qwen3.5-122b-a10b",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: qwen/qwen3.5-122b-a10b
Editor's verdict
Qwen3.5-122B-A10B is Alibaba Qwen's open-weight multimodal with a 262K-token context window.
At $2.08 per 1M output tokens, it is mid-priced for its class.
As an open-weight model you can self-host it or call it through a hosted API.
Best suited to very large 256k token context window and native video input support.
Frequently asked questions
The model supports a context window of 262144 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Qwen models
Sibling versions in the Qwen family from Alibaba Qwen.
Similar models
Other multimodal worth comparing.