Llama 4 Scout
by NanoGPT · family llama · listed Sep 2025TVW
Open multimodal Llama model for long-context analysis and efficient agents
Current rates USD per 1M tokens
Input$0.085
Output$0.46
Cache read$0.0425
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
meta-llama/llama-4-scout- Context window
- 328K tokens
- Max output
- 66K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-09-05
- Last updated
- 2025-09-05
← All NanoGPT listings