MiniMax-M2.1-lightning
Pricing & Specs
MiniMax · $0.6 input / $4.8 output per 1M tokens · 196.608K context window
The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on MiniMax-M2.1-lightning costs about $0.0030 — roughly $3.00 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.
MiniMax-M2.1-lightning API Pricing
| Tokens | Price |
|---|---|
| Input | $0.6 / 1M tokens |
| Output | $4.8 / 1M tokens |
| Cached input | $0.06 / 1M tokens |
Cached input tokens are billed when caching is enabled.
What that means in practice
MiniMax-M2.1-lightning Specs
| Spec | Value |
|---|---|
| Context window | 196.608K tokens |
| Max output tokens | 128K tokens |
| Input modalities | text |
| Output modalities | text |
| Latency (measured by OpenMark) | ~1.4s median response |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | No |
FAQ
How much does MiniMax-M2.1-lightning cost?
MiniMax-M2.1-lightning costs $0.6 per 1M input tokens and $4.8 per 1M output tokens ($0.06 per 1M cached input tokens).
What is MiniMax-M2.1-lightning's context window?
MiniMax-M2.1-lightning has a 196.608K-token context window. Maximum output is 128K tokens.
Can I test MiniMax-M2.1-lightning on my own task?
Yes. OpenMark lets you benchmark MiniMax-M2.1-lightning against 100+ models on your own task with real API calls — no API keys needed, free tier available.
Is MiniMax-M2.1-lightning the right model for YOUR task?
Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.