Llama-4-Maverick-17B-128E-Instruct-FP8
by Vercel AI Gateway · family llama · listed Apr 2025TVW
Open multimodal Llama model for strong reasoning and fast responses
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
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-4-maverick- Context window
- 128K tokens
- Max output
- 4K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Aug 2024
- Released
- 2025-04-05
- Last updated
- 2025-04-05
← All Vercel AI Gateway listings