Qwen Models by Alibaba
5 models2023Up to 33K ctxFrom $0.05/1M input
About
Qwen is a family of 5 AI models by Alibaba, released in 2023.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
5 in view
Qwen-1.8BCurrent
Use when the workload needs 4K context and 1.8B parameters.
2023-114K context1.8B parameters
Fireworks Qwen-72B-ChatCurrent
Use when the workload needs 33K context and 72B parameters.
2023-1133K context72B parameters
Qwen-14BCurrent
Use when the workload needs 32K context and 14B parameters.
2023-0932K context14B parameters
Qwen-7BCurrent
Use when the workload needs 8K context and 7B parameters.
2023-088K context7B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Qwen-72B | Use when the workload needs 72B parameters. | 2023-11 | 72B parameters | Current |
| Qwen-1.8B | Use when the workload needs 4K context and 1.8B parameters. | 2023-11 | 4K context1.8B parameters | Current |
| Fireworks Qwen-72B-Chat | Use when the workload needs 33K context and 72B parameters. | 2023-11 | 33K 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 groups2023-11
3 current
Fireworks Qwen-72B-Chat
Current33K context72B parameters
Qwen-1.8B
Current4K context1.8B parameters
Qwen-72B
Current72B parameters
2023-09
1 current
Qwen-14B
Current32K context14B parameters
2023-08
1 current
Qwen-7B
Current8K context7B parameters
Specifications(5 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Qwen-72B | 2023-11 | — | 72B |
| Qwen-1.8B | 2023-11 | 4K | 1.8B |
| Fireworks Qwen-72B-Chat | 2023-11 | 33K | 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 |
Frequently Asked Questions
- What is Qwen used for?
- Qwen is used for coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does Qwen compare to Tongyi DeepResearch?
- Qwen by Alibaba is strongest where you need coding, while Tongyi DeepResearch by Alibaba is the closest related family to check for adjacent model selection. Qwen has 5 listed variants and reaches up to 33K context, while Tongyi DeepResearch reaches up to 131K context, so compare the specs and pricing tables before choosing a production model.
- Which Qwen model should I use?
- For the lowest listed input price, start with Qwen-7B through Replicate API at $0.05/1M input tokens. For the most capable/latest local choice, evaluate Fireworks Qwen-72B-Chat with 33K context.