arcee-ai/spotlight
Model Card
Arcee Spotlight is a 7B parameter vision-language model derived from Qwen 2.5-VL, fine-tuned for image-text grounding tasks like captioning, visual question-answering, and diagram analysis. It offers a 32k-128k token context window enabling multimodal conversations combining documents with images. The model matches or outperforms larger VLMs like LLaVA-1.6 13B while running efficiently on consumer GPUs.
Context Window
N/A
tokens
Max Output
65,537
tokens
Input Cost
$0.18
per million tokens
Output Cost
$0.18
per million tokens
API Usage Example
Add Arcee AI: Spotlight to your app with just a few lines of code.
No API keys, no backend, no configuration required.
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "arcee-ai/spotlight"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Get started with Puter.js
Add Arcee AI: Spotlight to your app without worrying about API keys or setup.
Read the Docs View Tutorials