MiniMax (minimaxi.com)
MiniMax-M2.5-highspeed Pricing
API pricing for MiniMax-M2.5-highspeed by MiniMax (minimaxi.com). Input tokens cost $0.6/1M, output tokens cost $2.4/1M with 205K context window.
Last updated:
ReasoningTools
Input Cost
$0.6
per 1M tokens
Output Cost
$2.4
per 1M tokens
Context Window
205K
tokens
Cost Calculator
Estimated Cost:
$0.00
Model Details
Provider MiniMax (minimaxi.com)
Model ID MiniMax-M2.5-highspeed
Context Window 205K tokens
Max Output 131072 tokens
Cache Read Cost $0.06/1M
Release Date 2026-02-13
Compare Alternatives
| Model | Input | Output | Context |
|---|---|---|---|
| MiniMax-M2.5-highspeed (this model) | $0.6 | $2.4 | 205K |
| MiniMax-M2.5-highspeed MiniMax (minimax.io) | $0.6 | $2.4 | 205K |
| MiniMax-M2.7-highspeed MiniMax (minimax.io) | $0.6 | $2.4 | 205K |
| MiniMax-M2.7-highspeed MiniMax (minimaxi.com) | $0.6 | $2.4 | 205K |
| Nemotron 3 Ultra 550B A55B Nvidia | $0.5 | $2.5 | 1M |
| Grok Build 0.1 xAI | $1 | $2 | 256K |
Available from Resellers
MiniMax-M2.5-highspeed is also available through these resellers and gateways:
| Reseller | Model | Input | Output |
|---|---|---|---|
| 302.AI | MiniMax-M2 | $0.33 | $1.32 |
| 302.AI | MiniMax-M2.1 | $0.3 | $1.2 |
| 302.AI | MiniMax-M2.7 | $0.3 | $1.2 |
| 302.AI | MiniMax-M2.7-highspeed | $0.6 | $4.8 |
| Abacus | MiniMax-M2.7 | $0.3 | $1.2 |
| AIHubMix | Coding MiniMax M2.7 | $0.2 | $0.2 |
| AIHubMix | Coding MiniMax M2.7 Highspeed | $0.2 | $0.2 |
| AIHubMix | MiniMax M2.7 | $0.3 | $1.2 |
| AKI.IO | MiniMax-M2.5 | $0.25 | $1.2 |
| Amazon Bedrock | MiniMax M2 | $0.3 | $1.2 |