Qwen2 Models by Alibaba
8 models2024Up to 128k ctxFrom $0.05/1M input
Last refreshed 2026-05-19. Next refresh: weekly.
Details
ResearcherAlibaba
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models8
Released2024
Max context128k
Capabilities
Structured Outputs5 of 8 models
About
Qwen2 is a family of 8 AI models by Alibaba, released in 2024.
Decision facts
- Best fit
- structured outputscodingmath-heavy prompts
- Capability starting point
- Qwen2-72B with 128k context and structured outputs
- Lowest tracked input
- Qwen2-7B · $0.05/1M · DeepInfra
- Closest related family
- Tongyi DeepResearch
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
8 in view
Use when the workload needs 33k context, 7B parameters, and structured outputs.
2024-0633k context7B parametersstructured outputs
Use when the workload needs 33k context, 72B parameters, and structured outputs.
2024-0633k context72B parametersstructured outputs
Qwen2-7B-InstructCurrent
Use when the workload needs 128k context and 7B parameters.
2024-06128k context7B parameters
Qwen2-72BCurrent
Use when the workload needs 128k context, 72.7B parameters, and structured outputs.
2024-06128k context72.7B parametersstructured outputs
Qwen2-57B-A14BCurrent
Use when the workload needs 57.4B parameters and structured outputs.
2024-0657.4B parametersstructured outputs
Qwen2-7BCurrent
Use when the workload needs 128k context, 7.1B parameters, and structured outputs.
2024-06128k context7.1B parametersstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Together AI Qwen2-7B-Instruct | Use when the workload needs 33k context, 7B parameters, and structured outputs. | 2024-06 | 33k context7B parametersstructured outputs | Current |
| Together AI Qwen2-72B-Instruct | Use when the workload needs 33k context, 72B parameters, and structured outputs. | 2024-06 | 33k context72B parametersstructured outputs | Current |
| Qwen2-7B-Instruct | Use when the workload needs 128k context and 7B parameters. | 2024-06 | 128k context7B parameters | Current |
| Qwen2-72B | Use when the workload needs 128k context, 72.7B parameters, and structured outputs. | 2024-06 | 128k context72.7B parametersstructured outputs | Current |
| Qwen2-57B-A14B | Use when the workload needs 57.4B parameters and structured outputs. | 2024-06 | 57.4B parametersstructured outputs | Current |
| Qwen2-7B | Use when the workload needs 128k context, 7.1B parameters, and structured outputs. | 2024-06 | 128k context7.1B parametersstructured outputs | Current |
| Qwen2-1.5B | Use when the workload needs 1.5B parameters. | 2024-06 | 1.5B parameters | Current |
| Qwen2-0.5B | Use when the workload needs 490M parameters. | 2024-06 | 490M parameters | Current |
Release Timeline
1 release group2024-06
8 current
Qwen2-0.5B
Current490M parameters
Qwen2-1.5B
Current1.5B parameters
Qwen2-57B-A14B
Current57.4B parametersstructured outputs
Qwen2-72B
Current128k context72.7B parametersstructured outputs
Qwen2-7B
Current128k context7.1B parametersstructured outputs
Qwen2-7B-Instruct
Current128k context7B parameters
Together AI Qwen2-72B-Instruct
Current33k context72B parametersstructured outputs
Together AI Qwen2-7B-Instruct
Current33k context7B parametersstructured outputs
Specifications(8 models)
| Model | Released | Context | Parameters | Structured Outputs |
|---|---|---|---|---|
| Together AI Qwen2-7B-Instruct | 2024-06 | 33k | 7B | Yes |
| Together AI Qwen2-72B-Instruct | 2024-06 | 33k | 72B | Yes |
| Qwen2-7B-Instruct | 2024-06 | 128k | 7B | No |
| Qwen2-72B | 2024-06 | 128k | 72.71B | Yes |
| Qwen2-57B-A14B | 2024-06 | — | 57.41B | Yes |
| Qwen2-7B | 2024-06 | 128k | 7.07B | Yes |
| Qwen2-1.5B | 2024-06 | — | 1.54B | No |
| Qwen2-0.5B | 2024-06 | — | 490M | No |
Available From(6 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Qwen2-7B | DeepInfra | $0.05 | $0.15 | Serverless |
| Qwen2-1.5B | Microsoft Foundry | $0.07 | $0.07 | Provisioned |
| Qwen2-7B | Microsoft Foundry | $0.15 | $0.15 | Provisioned |
| Together AI Qwen2-7B-Instruct | Together AI | $0.15 | $0.15 | Serverless |
| Qwen2-57B-A14B | DeepInfra | $0.16 | $0.16 | Serverless |
| Qwen2-7B | Fireworks AI | $0.2 | $0.2 | Serverless |
| Qwen2-72B | DeepInfra | $0.45 | $0.65 | Serverless |
| Together AI Qwen2-72B-Instruct | Together AI | $0.7 | $0.7 | Serverless |
| Qwen2-72B | Fireworks AI | $0.9 | $0.9 | Serverless |
| Qwen2-72B | Together AI | $0.9 | $0.9 | Serverless |
| Qwen2-72B | Microsoft Foundry | $1 | $2 | Provisioned |
Popular comparisons in this family
- Llama 3.1 Swallow 8B Instruct vs Qwen2-7B-Instruct87
- GPT-5.4 vs Together AI Qwen2-72B-Instruct84
- MiniCPM-V 4.6 vs Qwen2-7B-Instruct76
- Kimi K2.5 vs Together AI Qwen2-72B-Instruct73
- ELYZA Japanese Llama 2 7B vs Qwen2-7B-Instruct67
- Llama 2 7B Chat vs Qwen2-7B-Instruct64
- Gemini 2.5 Flash vs Qwen2-7B-Instruct64
- GLM-5.1 vs Together AI Qwen2-7B-Instruct54
- DeepSeek V4 Flash vs Together AI Qwen2-7B-Instruct52
- Llama 2 7B vs Qwen2-7B-Instruct51
Related Model Families
Models(8)
Together AI Qwen2-7B-Instruct
2024-0633k7B1 provider
Open Source
Together AI Qwen2-72B-Instruct
2024-0633k72B1 provider
Open Source
Qwen2-7B-Instruct
2024-06128k7B1 provider
Open Source
Qwen2-72B
2024-06128k72.71B4 providers
Open Source
Qwen2-57B-A14B
2024-0657.41B1 provider
Open Source
Qwen2-7B
2024-06128k7.07B5 providers
Open Source
Qwen2-1.5B
2024-061.54B1 provider
Open Source
Qwen2-0.5B
2024-06490M
Open Source