Qwen Models by Alibaba
Last refreshed 2026-10-02. Next refresh: weekly.
About
Qwen (Tongyi Qianwen) is the first generation of Alibaba Cloud's open Qwen language models. It includes the base models Qwen-1.8B, Qwen-7B, Qwen-14B, and Qwen-72B, matching Qwen-Chat models aligned with human preferences, and Int4 and Int8 quantized versions. The base models were pretrained on about 2.2 to 3 trillion tokens of multilingual text, code, and math, with a focus on Chinese and English. The chat models can hold conversations, write, summarize, translate, code, solve math problems, and use tools or act as agents. Most sizes support 32K context (Qwen-14B supports 8K). Qwen2 and later generations are separate families.
Decision facts
- Best fit
- codingmath-heavy promptsagent workflows
- Capability starting point
- Fireworks Qwen-72B-Chat with 32K context
- Lowest tracked input
- Qwen-7B · $0.050/1M · Replicate API
- Closest related family
- Ovis Image
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 32K context and 72B parameters.
Use when the workload needs 4K context and 1.8B parameters.
Use when the workload needs 32K context and 72B parameters.
Use when the workload needs 32K context and 14B parameters.
Use when the workload needs 8K context and 7B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Fireworks Qwen-72B-Chat | Use when the workload needs 32K context and 72B parameters. | 2023-11 | 32K context72B parameters | Current |
| Qwen-1.8B | Use when the workload needs 4K context and 1.8B parameters. | 2023-11 | 4K context1.8B parameters | Current |
| Qwen-72B | Use when the workload needs 32K context and 72B parameters. | 2023-11 | 32K context72B parameters | Current |
| Qwen-14B | Use when the workload needs 32K context and 14B parameters. | 2023-09 | 32K context14B parameters | Current |
| Qwen-7B | Use when the workload needs 8K context and 7B parameters. | 2023-08 | 8K context7B parameters | Current |
Release Timeline
3 release groupsSpecifications(5 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Fireworks Qwen-72B-Chat | 2023-11 | 32K | 72B |
| Qwen-1.8B | 2023-11 | 4K | 1.8B |
| Qwen-72B | 2023-11 | 32K | 72B |
| Qwen-14B | 2023-09 | 32K | 14B |
| Qwen-7B | 2023-08 | 8K | 7B |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Qwen-7B | Replicate API | $0.05 | $0.25 | Serverless |
| Qwen-14B | Replicate API | $0.1 | $0.5 | Serverless |
| Qwen-14B | Fireworks AI | $0.2 | $0.2 | Provisioned |
| Fireworks Qwen-72B-Chat | Fireworks AI | $0.8 | $0.8 | Serverless |
| Qwen-72B | Fireworks AI | $0.9 | $0.9 | Provisioned |
