AI modelBase plan
MiniMax M3
MiniMax M3 via Fireworks: agentic model for complex tool use, productivity tasks, Agent Teams, and long-horizon workflows with a 512k-token context window. Supports image input and function calling. Does not support web search.
You always get the exact model you pick — we never silently route you to another.
Specifications
| Intelligence | High |
|---|---|
| Speed | Medium |
| Context window | 512,000 tokens |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not specified in available sources |
| Input price | $0.30 / 1M tokens |
| Output price | $1.20 / 1M tokens |
| Request cost | 2 base requests |
| Plan tier | Base |
| Input | Text, Image |
| Output | Text |
| Features | Cached input: $0.06 / 1M tokens, Function calling supported, Fine-tuning not supported on Fireworks serverless |
| Model ID | minimax-m3 |