Loading page
LightweightAlibaba
Qwen 3.5 35B
Qwen 3.5 35B is Alibaba's lightweight multimodal model supporting text, image, and video inputs with a 262K token context window.
Context 262K
Tier Lightweight
Modalities text, image, video
Input from
$0.140 / 1M tokens
across 4 providers
API Pricing
Cheapest on Deep Infra — 49% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $0.140 | $1.00 | $0.050 | |
| $0.250 | $2.00 | - | |
| $0.313 | $1.25 | $0.156 | |
| $0.400 | $0.400 | - |
Prices updated daily. Last check: Sep 8, 2026
Qwen 3.5 35B pricing by provider
Input, output, and batch rates, plus alternatives, for one provider at a time.
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
17.0 / 100
Coding
37.0 / 100
Output Speed
159 t/s
Latency (TTFT)
1.1s
Reasoning & Knowledge
- GPQA Diamond81.9%
- Humanity's Last Exam13.4%
Agentic & Tool Use
- Terminal-Bench Hard10.6%
- Terminal-Bench v2.140.8%
- τ²-bench86.3%
- τ-bench Banking4.9%
Instruction & Long Context
- IFBench44.5%
- Long-Context Reasoning63.0%
Benchmarks measured Sep 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Alibaba
- Family
- Qwen
- Tier
- Lightweight
- Context Window
- 262K
- Modalities
- Text, Image, Video
Capabilities
- Tool Calling
- No
- Open Source
- No
Strengths & Limitations
Strengths
- Supports video input processing alongside text and images
- Large 262K token context window for extensive document processing
- Fast output generation at 142.97 tokens per second
- Multimodal capabilities in a lightweight-tier model
- Sub-second time to first token at 997ms
- Part of Alibaba's established Qwen model family
- Handles complex multimedia reasoning tasks
Limitations
- No tool calling or function execution capabilities
- Proprietary model with weights not publicly available
- Lightweight tier may have reduced reasoning compared to larger models
- Limited to inference only without fine-tuning access
Key Features
•262K token context window
•Text input and generation
•Image input processing
•Video input analysis
•Multimodal reasoning
•Streaming response support
•Fast inference speeds
•Cross-modal content understanding
About Qwen 3.5 35B
Qwen 3.5 35B is a lightweight-tier model from Alibaba's Qwen family, designed to provide multimodal capabilities at a more accessible scale than larger models. As part of Alibaba's latest generation of language models, it sits in the lightweight category while maintaining sophisticated functionality across multiple input types.
The model features a 262,144 token context window and supports text, image, and video modalities, making it capable of processing complex multimedia inputs. Performance benchmarks show an output speed of 142.97 tokens per second with a time to first token of 997 milliseconds. The model handles multimodal reasoning tasks across visual and textual content, though it does not include tool calling capabilities.
Qwen 3.5 35B targets use cases requiring multimodal understanding without the computational overhead of frontier models. Its combination of video processing capabilities and substantial context window positions it for applications needing efficient multimedia analysis and content generation workflows.
Common Use Cases
Qwen 3.5 35B is well-suited for applications requiring efficient multimodal processing, particularly those involving video content analysis, multimedia document understanding, and visual question answering. Its lightweight tier makes it appropriate for high-volume content moderation, automated video summarization, educational content analysis, and customer service applications that need to process images or videos. The large context window enables processing of lengthy multimedia documents or multiple files in a single request, while the fast inference speeds support real-time applications. Organizations needing cost-effective multimodal AI without the overhead of frontier models will find it suitable for content analysis, media processing workflows, and applications where video understanding is required alongside text processing.
Frequently Asked Questions
How much does Qwen 3.5 35B cost per million tokens?
Qwen 3.5 35B pricing varies by provider and may have different rates for text versus image/video tokens. Check the pricing table above for current rates across all available providers.
What is Qwen 3.5 35B best used for?
Qwen 3.5 35B excels at multimodal tasks requiring video processing, content analysis, and multimedia document understanding. Its lightweight tier and fast inference make it ideal for high-volume applications like content moderation, video summarization, and customer service scenarios involving visual content.
Does Qwen 3.5 35B support tool calling or function execution?
No, Qwen 3.5 35B does not support tool calling or function execution capabilities. It focuses on multimodal understanding and generation tasks across text, image, and video inputs without external tool integration.