Qwen3 1.7B (Non-reasoning)
Analysis Summary
Qwen3 1.7B (Non-reasoning) is the standard inference variant of Alibaba's 1.7B model, running without extended chain-of-thought. Compared to its reasoning sibling, math performance drops sharply (index 7.3 vs 38.7), though GPQA and MMLU-Pro remain similar, suggesting general language understanding is preserved.
For businesses, this variant is better suited to fast-response applications such as chatbots, content summarisation, or classification tasks where latency matters more than deep reasoning. The lower output price of $0.42 per million tokens makes it more cost-effective than the reasoning variant for high-volume, non-complex workloads.
Teams should not rely on this model for coding, agentic tasks, or analytical reasoning. It is a budget option for simple NLP pipelines, and its value is primarily in cost and speed rather than capability depth.
Assessed June 30, 2026
Editorial notes
Qwen3 1.7B in non-reasoning mode trades math depth for lower output cost at $0.42 per million tokens, suitable for fast, lightweight text tasks where reasoning chains are unnecessary.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen3 1.7B (Non-reasoning) compares
Qwen3 1.7B (Non-reasoning) ranks #374 of 385 AI models we track for overall intelligence, #172 of 293 for agentic tasks. At $0.11 per million input tokens it is cheaper than 62% of comparable models.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen3 1.7B (Non-reasoning) stack up?
Compare side-by-side with other professional models.
Model Information
| Provider | Alibaba |
| Release Date | April 28, 2025 |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.11 | $0.000110 |
| Output | $0.42 | $0.000420 |
Frequently asked questions about Qwen3 1.7B (Non-reasoning)
How much does Qwen3 1.7B (Non-reasoning) cost?
Qwen3 1.7B (Non-reasoning) costs $0.11 per million input tokens and $0.42 per million output tokens.
Who created Qwen3 1.7B (Non-reasoning)?
Qwen3 1.7B (Non-reasoning) is developed by Alibaba and was released on April 28, 2025.
