Qwen Turbo overview
Qwen Turbo specs
- Model ID
alibaba/qwen-turbo- Developer
- Alibaba Cloud
- Input
- Text, Image
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Basic Information
- Release Date: January 25, 2025
- Model Type: Large Language Model (LLM)
Overview:
Qwen Turbo is designed to enhance both the performance and efficiency of AI agents developed on the Alibaba Cloud Model Studio platform.
Key Features:
- Optimized for speed and precision in generative AI application development.
- Improves AI agent comprehension and adaptation to enterprise data, especially when integrated with Retrieval-Augmented Generation (RAG) architectures.
- Large context window (1,000,000 tokens).
Intended Use:
For developers looking to build and optimize generative AI applications with a focus on speed and efficiency. Its integration within RAG architecture marks a substantial enhancement in the capacity of AI agents, facilitating superior comprehension and adaptation to enterprise data.
Technical Details
- Architecture: Qwen utilises a transformer-based architecture, optimised for high efficiency and scalability.
Code Samples:
The model is available on the AI/ML API platform as "Qwen Turbo" .
Use cases
- real-time chatbots and virtual assistants requiring low latency
- high-throughput text and multimedia data processing pipelines
- multilingual customer service and content moderation
- interactive content creation and editing tools
- video and audio content analysis and generation
- coding assistant and programming support tools
- research and data analytics involving large textual and multimedia datasets
Capabilities
- Function calling
- Streaming
- Structured outputs
- Reasoning
- Web search
Qwen Turbo benchmarks by
Artificial Analysis
See how Qwen Turbo scores on independent evaluations. Data retrieved Nov 3, 2026.
Benchmark results
Compare 17 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
LiveCodeBench
Competitive programming problems published after training cutoffs.
MMLU-Pro
Multiple-choice knowledge and reasoning across 14 subjects.
MATH-500
Competition mathematics problems.
Qwen Turbo API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.065 | 1M tokens |
| Output | $0.26 | 1M tokens |
| Cached input | $0.013 | 1M tokens |
Qwen Turbo is deprecated on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Qwen Turbo vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
| $0.065 | $0.26 | |
| $0.15 | $0.47 | |
| $0.16 | $0.47 | |
| $0.4761 | $3.39 | |
| $4.23 | $12.7 |
Related articles
Qwen Turbo FAQ
What is the context window of Qwen Turbo?
Qwen Turbo has a 1,000,000 tokens context window and can return up to 16,384 tokens.
What inputs and outputs does Qwen Turbo support?
Qwen Turbo takes text as input and returns text.
What is the model ID for Qwen Turbo?
Use alibaba/qwen-turbo as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
When was Qwen Turbo released?
Qwen Turbo became available on September 9, 2025.
How much does Qwen Turbo cost?
Qwen Turbo is priced at input $0.065 / 1M tokens, output $0.26 / 1M tokens, cached input $0.013 / 1M tokens.
Does Qwen Turbo support streaming?
Yes, Qwen Turbo can stream responses as they are generated.
Who created Qwen Turbo?
Qwen Turbo was built by Alibaba Cloud.
What is the API endpoint for accessing Qwen Turbo?
Qwen Turbo is accessed via the endpoint https://api.aimlapi.com/v1/chat/completions using standard chat completion requests.
Does Qwen Turbo have reasoning capabilities?
Yes, Qwen Turbo includes reasoning as one of its capabilities.
Can Qwen Turbo perform function calling and use tools?
Yes, Qwen Turbo supports function calling, tool use, and parallel tool calls.

