Qwen 7 28 Flash
Qwen 7 28 Flash is Alibaba's language model with a 998K context window and up to 33K output tokens. A Flash-tier Qwen LLM from the 7-28 release, optimized for fast, low-latency inference on general-purpose language tasks.
Alibaba's language model with a 998K context window and up to 33K output tokens. A Flash-tier Qwen LLM from the 7-28 release, optimized for fast, low-latency inference on general-purpose language tasks.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities2/13
✓
·
✓
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen 7 28 Flash | — | 998K | — | — | Current |
| Qwen3.5-Flash | 1.0M | $0.065 | $0.260 | Available | |
| Qwen 3.5 Flash | 1.0M | $0.100 | $0.400 | Available | |
| Qwen3 Coder Flash | 1.0M | $0.195 | $0.975 | Available | |
| Qwen Flash | — | 1.0M | $0.050 | $0.400 | Available |
| Qwen Flash | — | 1.0M | $0.050 | $0.400 | Available |
| Qwen MT Flash | — | 16K | $0.160 | $0.490 | Available |
| Qwen3 TTS Flash | — | — | — | — | Available |
| Qwen3 VL Flash | — | 262K | $0.200 | $1.60 | Available |
| Qwen3 VL Flash | — | 262K | $0.050 | $0.400 | Available |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek R1 0528 Qwen3 8B | — | — | 128K | $0.060 | $0.090 |
| Qwen3 9.23 Max | Max | — | — | — | — |
| Qwen 4 28 Plus | Plus | — | 129K | — | — |
| Qwen 3 32B | — | 128K | — | — | |
| Qwen3.5 Plus 2026-02-15 | Plus | 1.0M | $0.260 | $1.56 | |
| Qwen 1 25 Plus | Plus | — | 129K | — | — |
| Qwen3.5 Max | Max | — | 258K | — | — |
| Qwen3.6 Plus | Plus | 1.0M | $0.325 | $1.95 | |
| Qwen3.6 Plus Preview | Plus | 1.0M | — | — | |
| Qwen 3.5 Plus | Plus | 1.0M | $0.115 | $0.688 |