Alibaba (Qwen) · Released Apr 29, 2025Qwen3 14B
Qwen instruction model for multilingual chat, reasoning, and tool use.
- Capability
- 138.2ECI · #107 of 148
- Input
- $0.35per 1M tokens
- Output
- $1.40per 1M tokens
- Context
- 131K8K max output
What it costs
- Input
- $0.35per million tokens
- Output
- $1.40per million tokens
- Blended (3:1)
- $0.613cheaper than 55% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $1.40 |
| Team assistant25M input + 5M output tokens | $15.75 |
| Production app250M input + 50M output tokens | $157.50 |
Official Alibaba API price, as listed on models.dev.
Independent benchmarks
#107 of 148 scored models
The shaded band is Epoch AI’s confidence range (133.5–140.1); the tick marks the median scored model.
Scores from Epoch AI, run independently of Alibaba (Qwen).
The details
- Lab
- Alibaba (Qwen)
- Released
- Apr 29, 2025
- Knowledge cutoff
- Apr 2025
- Context window
- 131,072 tokens
- Max output
- 8,192 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- Thinking budget
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- API model ID
qwen3-14bon Alibaba- Availability
- 1 API providerlisted on models.dev
More from Alibaba (Qwen)
About Qwen3 14B
How much does Qwen3 14B cost?
Qwen3 14B costs $0.35 input / $1.40 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $0.613 per million tokens, cheaper than 55% of the 360 priced models we track.
What is the context window of Qwen3 14B?
Qwen3 14B accepts up to 131,072 tokens per request and can write up to 8,192 tokens in one response.
How good is Qwen3 14B?
Epoch AI gives Qwen3 14B a Capabilities Index score of 138.2 (likely range 133.5–140.1), ranking it #107 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 63.8%, OTIS Mock AIME 2024–2025 66.4%.
Is Qwen3 14B open source?
Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.
What inputs does Qwen3 14B support?
Qwen3 14B accepts text and replies in text. It is a reasoning model, supports tool calling.
When was Qwen3 14B released?
Alibaba (Qwen) released Qwen3 14B on Apr 29, 2025. Its training data runs to Apr 2025.
What are the best alternatives to Qwen3 14B?
The closest current models from other labs on capability, price and release date are DeepSeek-V3.1 (DeepSeek, ECI 139.9, $0.385 / $1.25), GPT-4.1 mini (OpenAI, ECI 135.0, $0.40 / $1.60), Gemini 2.5 Flash (Google, ECI 140.8, $0.30 / $2.50) and Mistral Medium 3 (Mistral AI, ECI 134.1, $0.40 / $2.00).