MiniMax API Pricing & Model Comparison
We track 1 MiniMax models, with input pricing from $0.30 to $0.30 per million tokens. The line-up's blended rate runs 81% below the catalog average. Below: price, context, speed and value compared across the range.
For cost, MiniMax's cheapest option is MiniMax-M3 ($0.30 input / $1.20 output); the quality ceiling is MiniMax-M3 at a quality score of 89. On a 50,000-turn-per-month support workload that is $60 versus $60 — the spread inside a single provider is often wider than the spread between providers.
On value (quality score ÷ output price) the pick of the MiniMax range is MiniMax-M3. The largest context window is 1000K, offered only by MiniMax-M3, and the fastest output is MiniMax-M3 at 95 tok/s. Modalities across the line-up: Text.
Models and pricing
Sorted by blended rate, cheapest first (3:1 input-to-output mix). Follow a model name for full specs and monthly cost estimates.
| Model | Input /1M | Output /1M | Blended /1M | Quality | Context | Speed | Value | Use cases |
|---|---|---|---|---|---|---|---|---|
| MiniMax-M3 | $0.30 | $1.20 | $0.52 | 89 | 1000K | 95 tok/s | 74.2 | CodingReasoningLong ContextAffordable |
Frequently asked questions
Which MiniMax model is cheapest?
MiniMax-M3, at $0.30 input and $1.20 output per million tokens, with a quality score of 89.
What is MiniMax's flagship model?
By quality score it is MiniMax-M3 (89), priced at $0.30 input / $1.20 output with a 1000K context window.
Does MiniMax pricing change?
Yes. llmprice.app runs a daily collection job and refreshes these figures, but there can be a lag after a provider re-prices — confirm against MiniMax's official pricing page before committing.
Prices and specs are collected daily by llmprice.app. Confirm against the official pricing page before production use.