Qwen2.5 VL 32B Instruct is
Alibaba's language model with a 131K context window and up to 8K output tokens, available from 4 providers, starting at $0.200 / 1M input and $0.600 / 1M output. A 32-billion-parameter vision-language model from the Qwen2.5-VL series, fine-tuned with reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving.
Capabilities
Input2/5
✓
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities1/13
·
·
✓
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
DeepInfra | $0.200 | $0.600 | — | — |
OpenRouter | $0.200 | $0.600 | — | — |
Fireworks AI | $0.900 | $0.900 | — | — |
Alibaba Qwen | $1.40 | $4.20 | $0.700 | $2.10 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen2.5 VL 32B Instruct | 131K | $0.200 | $0.600 | Current | |
| Qwen2.5 VL 72B Instruct | 131K | $0.130 | $0.400 | Available | |
| Qwen2.5 VL 3B Instruct | — | 131K | $0.200 | $0.200 | Available |
| Qwen2.5 VL 7B Instruct | — | 131K | $0.200 | $0.200 | Available |
| RolmOCR | — | 128K | $0.200 | $0.200 | Available |