Qwen2.5-1.5B-Instruct
1.5B Qwen2.5, runs on a phone. Smallest Qwen useful for production assistant work.
Qwen2.5-1.5B-Instruct is a efficient AI model from Qwen. It costs $0.0300 per million input tokens and $0.0300 per million output tokens (blended $0.0300/M), with a 32,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from Qwen's published pricing; no check date on record.
- Mobile/edge
- Open weights
- Multilingual
- On-device routing
- Edge inference
Benchmarks
More from Qwen
See all 22 →Frequently asked questions
How much does Qwen2.5-1.5B-Instruct cost?
Qwen2.5-1.5B-Instruct costs $0.0300 per million input tokens and $0.0300 per million output tokens, for a blended reference rate of $0.0300 per million tokens.
What is Qwen2.5-1.5B-Instruct's context window?
Qwen2.5-1.5B-Instruct supports up to 32,000 tokens of context in a single request.
What is Qwen2.5-1.5B-Instruct best for?
Qwen2.5-1.5B-Instruct is well suited to Mobile/edge, Open weights and Multilingual.
Who makes Qwen2.5-1.5B-Instruct?
Qwen2.5-1.5B-Instruct is developed and served by Qwen. It was released in Sep 2024.
