Last refreshed 2026-06-29. Next refresh: weekly.
Why use Qwen2.5-VL-72B on Novita AI?
Novita AI offers Qwen2.5-VL-72B with pay-as-you-go pricing at $0.80/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Input / 1M
$0.80
Output / 1M
$0.80
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: qwen2.5-vl-72b-instructModel ID
qwen2.5-vl-72b-instructRequest example
Curated snippets for this provider have not been sourced yet.
Gotchas
- Use provider model ID "qwen2.5-vl-72b-instruct", not the LLMReference slug "qwen2.5-vl-72b".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.80 |
| Output tokens | $0.80 |
Capabilities
VisionMultimodal
About Qwen2.5-VL-72B
Qwen: Qwen2.5 VL 72B Instruct available via OpenRouter. Pricing: $0.8/1M input, $0.8/1M output.
FAQ
What does Qwen2.5-VL-72B cost on Novita AI?
On Novita AI, Qwen2.5-VL-72B costs $0.8 per 1M input tokens and $0.8 per 1M output tokens.
What is the context window for Qwen2.5-VL-72B on Novita AI?
Qwen2.5-VL-72B supports a 33k token context window on Novita AI.
What API model ID do I use for Qwen2.5-VL-72B on Novita AI?
Use the model ID qwen2.5-vl-72b-instruct when calling Novita AI's API.
Who created Qwen2.5-VL-72B?
Qwen2.5-VL-72B was created by Alibaba as part of the Qwen2.5 model family.
Is Qwen2.5-VL-72B open source?
Qwen2.5-VL-72B is open source under Apache 2.0 according to the seed data.
Get Started
Model Specs
Released2025-01-26
Parameters72B
Context33k
ArchitectureDecoder Only