Loading...
Loading...
Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal conversations that combine lengthy documents with one or more images. Training emphasized fast inference on consumer GPUs while retaining strong captioning, visual‐question‑answering, and diagram‑analysis accuracy. As a result, Spotlight slots neatly into agent workflows where screenshots, charts or UI mock‑ups need to be interpreted on the fly. Early benchmarks show it matching or out‑scoring larger VLMs such as LLaVA‑1.6 13 B on popular VQA and POPE alignment tests.
Preço/1M
$0.18
287th mais barato
42% abaixo da mediana
Top 43%
Janela de Contexto
131K
145th maior
Top 63%
Entrada
$0.18
por 1M tokens
Saída
$0.18
por 1M tokens
Combinado
$0.18
por 1M tokens
Mais barato que 57% dos modelos. Preço mediano é $0.31/1M tokens.
Diário
$0.18
Mensal
$5.40
Janela de Contexto
131K
tokens
Maior que 37% dos modelos
Saída Máxima
66K
tokens
50% do contexto
Comparação de Janela de Contexto