Qwen3.5 Plus 2026-02-15
VerifiedProcesses up to a million tokens across text, images, and video.
About Qwen3.5 Plus 2026-02-15
The architecture integrates multiple modalities into a single context of one million tokens. This design lets the model maintain coherence when combining lengthy textual sources with visual or video streams. Being fully open-weight, it allows direct inspection, fine-tuning, and local deployment.
Its primary strengths lie in sustained multimodal understanding over extended sequences without external chunking. Developers can therefore build applications that analyze long videos alongside related documents or transcripts. The absence of disclosed parameter counts keeps focus on practical capability rather than scale claims.
Common usage includes video content indexing, image-grounded document analysis, and interactive multimodal agents. Research teams and enterprises apply it to tasks that demand both breadth of context and cross-modal alignment. Its open release encourages community experimentation and adaptation.
Capabilities
How Qwen3.5 Plus 2026-02-15 compares
Qwen3.5 Plus 2026-02-15 (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Qwen3.5 Plus 2026-02-15 ranks #46 of 132
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Extended Document Analysis
The model processes up to 1,000,000 tokens to summarize and reason over lengthy reports, research papers, or legal contracts in a single pass.
Video Content Review
It performs video content analysis by interpreting visual sequences alongside audio or text transcripts for tasks like event detection or summarization.
Multimodal Data Integration
Cross-modal integration allows simultaneous handling of images, text, and video to answer questions that require combining visual and linguistic information.
Strengths & limitations
Strengths
- +Supports 1M token context
- +Handles text, image, and video inputs
- +Strong multimodal fusion
- +Suitable for complex long-form tasks
Limitations
- –High resource use with full context
- –Video handling may add latency
- –Multimodal quality depends on input clarity
Cost calculator
Estimate what Qwen3.5 Plus 2026-02-15 would cost for your usage.
Based on Qwen3.5 Plus 2026-02-15's $0.26/1M input · $1.56/1M 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-plus-02-15",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: qwen/qwen3.5-plus-02-15
Editor's verdict
Qwen3.5 Plus 2026-02-15 is Alibaba Qwen's open-weight multimodal with a 1000K-token context window.
At $1.56 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 supports 1m token context and handles text, image, and video inputs.
Frequently asked questions
The model supports a context length of 1,000,000 tokens for handling extended inputs.
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.