MiniMax-M2.5-highspeed API
About
Build advanced reasoning agents with MiniMax-M2.5-highspeed, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.60/1M input and $2.40/1M output tokens, native tool calling support, open weights architecture. Access MiniMax-M2.5-highspeed via the DevPass (LLM Gateway) API with up to 131K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsOpen
Limits
Context Window
205K
Tokens
Input Limit
205K
Tokens
Max Output
131K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.60
Output
$2.40
Caching (per 1M tokens)
Read
$0.03
Write
$0.38
Frequently Asked Questions
MiniMax-M2.5-highspeed by DevPass (LLM Gateway) costs $0.60 per 1M input tokens and $2.40 per 1M output tokens. Cached reads cost $0.03 per 1M tokens. Cache writes cost $0.38 per 1M tokens.
Model Details
ID
minimax-m2.5-highspeed
Provider
DevPass (LLM Gateway)Family
minimax
Release Date
Feb 13, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
LLMGATEWAY_API_KEY
API Base URL
https://api.llmgateway.io/v1