Qwen2.5 VL 32B Instruct
Qwen2.5 VL 32B Instruct is Alibaba's language model with a 128K context window and up to 8K output tokens, available from 2 providers, starting at $0.2 / 1M input and $0.6 / 1M output. A 32-billion-parameter multimodal vision-language LLM from Alibaba's Qwen2.5-VL series, capable of understanding and reasoning over both images and text.
Capabilities
Input1/5
Text·
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.2 | $0.6 | |
| $0.9 | $0.9 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Qwen2.5 VL 32B Instruct, ranked by cheapest on-demand price. The model needs about 77 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP20s |  Azure | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | westus2 | |
| g7e.2xlarge |  AWS | RTX PRO Server 6000 | 96 GB | $3.36/hr | us-east-1 | |
| Standard_NC24ads_A100_v4 | Azure | NVIDIA A100 | 80 GB | $3.67/hr | westus2 | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Voyage Multimodal 3.5 | — | — | — | — | Available |
| Qwen2.5 VL 72B Instruct | 131K | $0.130 | $0.400 | Available | |
| Qwen2.5 VL 32B Instruct | — | 128K | $0.200 | $0.600 | Current |
| Qwen2.5 VL 3B Instruct | — | 128K | $0.200 | $0.200 | Available |
| Qwen2.5 VL 7B Instruct | — | 128K | $0.200 | $0.200 | Available |
| Rolm OCR | — | 128K | $0.200 | $0.200 | Available |