Qwen: Qwen3 14B
The Qwen3 14B is a language model developed by qwen that supports text input and output. It has a context length of 131,072 tokens and can generate up to 16,384 completion tokens per request. The model also supports tools and reasoning capabilities. When considering which AI model to use, Qwen3 14B may be worth shortlisting for those who need text-based functionality and are willing to pay $0.24 per million output tokens in addition to the input cost of $0.12 per million. Its blended benchmark score is 6.0 across one independent benchmark, but more information on its performance is needed due to limited coverage.
Benchmark results
Independent, published benchmarks. Blended score 5.5 across 1 benchmark, last refreshed 2026-09-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 11.1 |
- Model ID
- qwen/qwen3-14b
- Vendor
- qwen
- Released
- April 2025
- Tokenizer
- Qwen3
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.12/M input and $0.24/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.07 |
| A month of a busy support chatbot | 5M in / 2M out | $1.08 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-09-14 | $0.12 | $0.24 | 131,072 |
| 2026-09-08 | $0.23 | $0.91 | 131,072 |
| 2026-09-04 | $0.12 | $0.24 | 131,072 |
| 2026-09-03 | $0.23 | $0.91 | 131,072 |
| 2026-08-10 | $0.12 | $0.24 | 131,072 |
| 2026-07-23 | $0.23 | $0.91 | 131,072 |
| 2026-07-22 | $0.12 | $0.24 | 131,072 |
| 2026-07-20 | $0.12 | $0.24 | 131,702 |
| 2026-07-19 | $0.23 | $0.91 | 131,702 |
| 2026-07-18 | $0.12 | $0.24 | 131,702 |
| 2026-07-17 | $0.10 | $0.24 | 131,702 |
Similar models
Qwen: Qwen3 32B
Qwen: Qwen3 VL 32B Instruct
Qwen: Qwen3 30B A3B
Qwen: Qwen3 8B
Qwen: Qwen3 235B A22B
Qwen: Qwen3 235B A22B Thinking 2507
Quick answers
- How much does Qwen: Qwen3 14B cost?
- $0.12 per million input tokens and $0.24 per million output tokens.
- What is Qwen: Qwen3 14B's context window?
- 131,072 tokens, roughly 196 pages of text in a single request.
- Does Qwen: Qwen3 14B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Qwen: Qwen3 14B process images?
- No, it is text-only on the input side.