Qwen3 Models by Alibaba
19 models2025Up to 1m ctxFrom $0.035/1M input
About
Qwen3 is a family of 19 AI models by Alibaba, released in 2025.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
19 in view
Qwen3-105BCurrent
Use when the workload needs 128k context, 105B parameters, and tool use.
2025-12128k context105B parameterstool use
Qwen3-8BCurrent
Use when the workload needs 128k context, 8B parameters, and structured outputs.
2025-08128k context8B parametersstructured outputs
Qwen3-8B-InstructCurrent
Use when the workload needs 128k context and 8B parameters.
2025-08128k context8B parameters
Qwen3-70BCurrent
Use when the workload needs 128k context and 70B parameters.
2025-08128k context70B parameters
Qwen3-70B-InstructCurrent
Use when the workload needs 128k context and 70B parameters.
2025-08128k context70B parameters
Qwen3-235B-A22BCurrent
Use when the workload needs 128k context, 235B parameters, and structured outputs.
2025-04128k context235B parametersstructured outputs
Qwen3-32BCurrent
Use when the workload needs 40k context, 32B parameters, and structured outputs.
2025-0440k context32B parametersstructured outputs
Qwen3-MaxCurrent
Use when the workload needs 262k context, tool use, and function calling.
2025-04262k contexttool usefunction calling
Qwen3-30B-A3BCurrent
Use when the workload needs 128k context, 30B parameters, and structured outputs.
2025-04128k context30B parametersstructured outputs
Qwen3-9BCurrent
Use when the workload needs 256k context, 9B parameters, and structured outputs.
2025-04256k context9B parametersstructured outputs
Use when the workload needs 160k context, 8B parameters, and reasoning.
2025-01160k context8B parametersreasoning
Qwen3-0.6BCurrent
Use when the workload needs 40k context and 600M parameters.
2025-0140k context600M parameters
Qwen3-14BCurrent
Use when the workload needs 40k context, 14B parameters, and structured outputs.
2025-0140k context14B parametersstructured outputs
Qwen3-1.7BCurrent
Use when the workload needs 40k context and 1.7B parameters.
2025-0140k context1.7B parameters
Qwen3-4BCurrent
Use when the workload needs 40k context and 4B parameters.
2025-0140k context4B parameters
DeepSeek R1 0528 Qwen3-8BCurrent
Use when the workload needs 160k context, 671B parameters, and reasoning.
2025-01160k context671B parametersreasoning
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Qwen3-105B | Use when the workload needs 128k context, 105B parameters, and tool use. | 2025-12 | 128k context105B parameterstool use | Current |
| Qwen3-Next-80B-A3B | Use when the workload needs structured outputs. | 2025-12 | structured outputs | Current |
| Qwen-Plus | Use when the workload needs 1m context. | 2025-11 | 1m context | Current |
| Qwen3-8B | Use when the workload needs 128k context, 8B parameters, and structured outputs. | 2025-08 | 128k context8B parametersstructured outputs | Current |
| Qwen3-8B-Instruct | Use when the workload needs 128k context and 8B parameters. | 2025-08 | 128k context8B parameters | Current |
| Qwen3-70B | Use when the workload needs 128k context and 70B parameters. | 2025-08 | 128k context70B parameters | Current |
| Qwen3-70B-Instruct | Use when the workload needs 128k context and 70B parameters. | 2025-08 | 128k context70B parameters | Current |
| Qwen-Flash | Use when the workload needs 1m context. | 2025-08 | 1m context | Current |
| Qwen3-235B-A22B | Use when the workload needs 128k context, 235B parameters, and structured outputs. | 2025-04 | 128k context235B parametersstructured outputs | Current |
| Qwen3-32B | Use when the workload needs 40k context, 32B parameters, and structured outputs. | 2025-04 | 40k context32B parametersstructured outputs | Current |
| Qwen3-Max | Use when the workload needs 262k context, tool use, and function calling. | 2025-04 | 262k contexttool usefunction calling | Current |
| Qwen3-30B-A3B | Use when the workload needs 128k context, 30B parameters, and structured outputs. | 2025-04 | 128k context30B parametersstructured outputs | Current |
| Qwen3-9B | Use when the workload needs 256k context, 9B parameters, and structured outputs. | 2025-04 | 256k context9B parametersstructured outputs | Current |
| DeepSeek R1 0528 Distill Qwen3-8B | Use when the workload needs 160k context, 8B parameters, and reasoning. | 2025-01 | 160k context8B parametersreasoning | Current |
| Qwen3-0.6B | Use when the workload needs 40k context and 600M parameters. | 2025-01 | 40k context600M parameters | Current |
| Qwen3-14B | Use when the workload needs 40k context, 14B parameters, and structured outputs. | 2025-01 | 40k context14B parametersstructured outputs | Current |
| Qwen3-1.7B | Use when the workload needs 40k context and 1.7B parameters. | 2025-01 | 40k context1.7B parameters | Current |
| Qwen3-4B | Use when the workload needs 40k context and 4B parameters. | 2025-01 | 40k context4B parameters | Current |
| DeepSeek R1 0528 Qwen3-8B | Use when the workload needs 160k context, 671B parameters, and reasoning. | 2025-01 | 160k context671B parametersreasoning | Current |
Release Timeline
5 release groups2025-12
2 current
Qwen3-105B
Current128k context105B parameterstool use
Qwen3-Next-80B-A3B
Currentstructured outputs
2025-11
1 current
Qwen-Plus
Current1m context
2025-08
5 current
Qwen-Flash
Current1m context
Qwen3-70B
Current128k context70B parameters
Qwen3-70B-Instruct
Current128k context70B parameters
Qwen3-8B
Current128k context8B parametersstructured outputs
Qwen3-8B-Instruct
Current128k context8B parameters
2025-04
5 current
Qwen3-235B-A22B
Current128k context235B parametersstructured outputs
Qwen3-30B-A3B
Current128k context30B parametersstructured outputs
Qwen3-32B
Current40k context32B parametersstructured outputs
Qwen3-9B
Current256k context9B parametersstructured outputs
Qwen3-Max
Current262k contexttool usefunction calling
2025-01
6 current
DeepSeek R1 0528 Distill Qwen3-8B
Current160k context8B parametersreasoning
DeepSeek R1 0528 Qwen3-8B
Current160k context671B parametersreasoning
Qwen3-0.6B
Current40k context600M parameters
Qwen3-1.7B
Current40k context1.7B parameters
Qwen3-14B
Current40k context14B parametersstructured outputs
Qwen3-4B
Current40k context4B parameters
Specifications(19 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | Fn Calling | Tool Use | Structured Outputs |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3-105B | 2025-12 | 128k | 105B | No | No | No | Yes | Yes | No |
| Qwen3-Next-80B-A3B | 2025-12 | — | 80B (3B active) | No | No | No | No | No | Yes |
| Qwen-Plus | 2025-11 | 1m | — | No | No | No | No | No | No |
| Qwen3-8B | 2025-08 | 128k | 8B | No | No | No | No | No | Yes |
| Qwen3-8B-Instruct | 2025-08 | 128k | 8B | No | No | No | No | No | No |
| Qwen3-70B | 2025-08 | 128k | 70B | No | No | No | No | No | No |
| Qwen3-70B-Instruct | 2025-08 | 128k | 70B | No | No | No | No | No | No |
| Qwen-Flash | 2025-08 | 1m | — | No | No | No | No | No | No |
| Qwen3-235B-A22B | 2025-04 | 128k | 235B | No | No | No | No | No | Yes |
| Qwen3-32B | 2025-04 | 40k | 32B | No | No | No | No | No | Yes |
| Qwen3-Max | 2025-04 | 262k | — | Yes | Yes | No | Yes | Yes | Yes |
| Qwen3-30B-A3B | 2025-04 | 128k | 30B | No | No | No | No | No | Yes |
| Qwen3-9B | 2025-04 | 256k | 9B | No | No | No | No | No | Yes |
| DeepSeek R1 0528 Distill Qwen3-8B | 2025-01 | 160k | 8B | No | No | Yes | No | No | No |
| Qwen3-0.6B | 2025-01 | 40k | 0.6B | No | No | No | No | No | No |
| Qwen3-14B | 2025-01 | 40k | 14B | No | No | No | No | No | Yes |
| Qwen3-1.7B | 2025-01 | 40k | 1.7B | No | No | No | No | No | No |
| Qwen3-4B | 2025-01 | 40k | 4B | No | No | No | No | No | No |
| DeepSeek R1 0528 Qwen3-8B | 2025-01 | 160k | 671B | No | No | Yes | No | No | No |
Available From(9 providers)
Pricing
Comparisons
- Qwen3-Max vs GPT-4o (08-06)
- Qwen3-Max vs Claude Sonnet 4.6
- Qwen3-Max vs DeepSeek V4 Pro
- Qwen3-30B-A3B vs Mistral Large 2.1 (2411)
- Qwen3-30B-A3B vs Llama 3.3 70B
- Qwen3.6-Max vs Qwen3-Max
- GPT-5 vs Qwen3-Max
- Claude Opus 4.7 vs Qwen3-Max
Frequently Asked Questions
- What is Qwen3 used for?
- Qwen3 is used for vision and multimodal work, reasoning, and agent workflows and tool use. The family description and listed model capabilities point to those workloads as the best fit.
- How does Qwen3 compare to Tongyi DeepResearch?
- Qwen3 by Alibaba is strongest where you need vision and multimodal work, while Tongyi DeepResearch by Alibaba is the closest related family to check for adjacent model selection. Qwen3 has 19 listed variants and reaches up to 1m context, while Tongyi DeepResearch reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
Related Model Families
Models(19)
Qwen3-105B
2025-12128k105B
Open Source
Qwen3-Next-80B-A3B
2025-1280B (3B active)5 providers
Qwen-Plus
2025-111m1 provider
Qwen3-8B
2025-08128k8B3 providers
Qwen3-8B-Instruct
2025-08128k8B
Qwen3-70B
2025-08128k70B
Qwen3-70B-Instruct
2025-08128k70B
Qwen-Flash
2025-081m1 provider
Qwen3-235B-A22B
2025-04128k235B7 providers
Qwen3-32B
2025-0440k32B6 providers
Qwen3-Max
2025-04262k3 providers
Multimodal
Qwen3-30B-A3B
2025-04128k30B5 providers
Qwen3-9B
2025-04256k9B1 provider
DeepSeek R1 0528 Distill Qwen3-8B
2025-01160k8B1 provider
ReasoningOpen Source
Qwen3-0.6B
2025-0140k0.6B1 provider
Qwen3-14B
2025-0140k14B3 providers
Qwen3-1.7B
2025-0140k1.7B1 provider
Qwen3-4B
2025-0140k4B1 provider
DeepSeek R1 0528 Qwen3-8B
2025-01160k671B2 providers
ReasoningOpen Source