Alibaba
100.00%Context131.1K
Max output32.8K
p50 latency520 ms
Throughput129.0 t/s
Input price$0.4
Output price$4
Zero retentionNo training
Model directory
Baseer model profileLanguage model
alibaba/qwen3-vl-thinking
Qwen3 VL 235B A22B Thinking
Qwen3 series VL models feature significantly enhanced multimodal reasoning capabilities, with a particular focus on optimizing the model for STEM and mathematical reasoning. Visual perception and recognition abilities have been comprehensively improved, and OCR capabilities have undergone a major upgrade.
Input / 1M tokens$0.4
Output / 1M tokens$3.95
Maximum context131.1K
Inference providers2
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Novita
100.00%Context131.1K
Max output32.8K
p50 latency949 ms
Throughput106.0 t/s
Input price$0.98
Output price$3.95
No training
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Alibaba | 131.1K | 32.8K | 520 ms | 129.0 t/s | 100.000% | $0.4 | $4 | |
Novita | 131.1K | 32.8K | 949 ms | 106.0 t/s | 100.000% | $0.98 | $3.95 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageFileAdvanced reasoningVisionTool useFile inputTools
Technical profile
- Model type
- Language model
- Release date
- Sep 23, 2025
- Knowledge cutoff
- 2025-09
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
alibaba/qwen3-vl-thinkingModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.