This model delivers exceptional performance for advanced reasoning, complex problem-solving, and instruction-following tasks. Great for high-throughput applications, real-time AI assistants, and enterprise workflows requiring both intelligence and speed.
llama-4-maverick-17b-128e
temperature=0.6
, min_p=0.01
, and top_p=0.9
.Tier | Requests/min | Input Tokens/min | Output Tokens/min | Daily Tokens |
---|---|---|---|---|
Free | 30 | 60k | 8k/request | 1M |
Chat Completions
Completions