Qwen2 VL 72B Instruct
Qwen2 VL 72B Instruct is Alibaba's language model with a 131K context window and up to 2K output tokens, available from 3 providers, starting at $0.13 / 1M input and $0.4 / 1M output. A 72-billion-parameter multimodal vision-language LLM from Alibaba's Qwen2-VL series, offering high-capacity visual reasoning and image-text generation.
Capabilities
Input1/5
Text·
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $2.29 | $6.88 | $1.15 | $3.44 | |
| $0.9 | $0.9 | — | — | |
| $0.13 | $0.4 | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Qwen2 VL 72B Instruct, ranked by cheapest on-demand price. The model needs about 173 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_NP40s |  Azure | 4× AMD Alveo U250 FPGA (64GB) | 256 GB | $6.60/hr | westus2 | |
| g2-standard-96 |  GCP | 8× nvidia-l4 | 192 GB | $7.98/hr | us-east4 | |
| g7e.12xlarge |  AWS | 2× RTX PRO Server 6000 | 192 GB | $8.29/hr | us-east-1 | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen2 VL 72B Instruct | — | 131K | $0.130 | $0.400 | Current |
| Qwen2 VL 2B Instruct | — | 33K | $0.100 | $0.100 | Available |
| Qwen2 VL 7B Instruct | — | 131K | $0.020 | $0.060 | Available |