---
name: Bevformer
slug: bevformer
type: LLM
providers:
  - nvidia
description: Nemotron multimodal model for visual reasoning and agentic AI workflows
tags:
  - open-source
  - llm
is_open_source: true
context_window: 128000
max_output: 8192
pricing:
  - image: 0
    input: 0
    output: 0
    provider: nvidia
release_date: '2025-03-18'
capabilities:
  audio: false
  vision: false
  tool_use: false
  citations: false
  reasoning: false
---
Bevformer is a LLM model.
Nemotron multimodal model for visual reasoning and agentic AI workflows