MiniMax M2.5 API
About
Build advanced reasoning agents with MiniMax M2.5, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.34/1M input and $1.19/1M output tokens, native tool calling support, open weights architecture. Access MiniMax M2.5 via the Venice AI API with up to 33K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
198K
Tokens
Input Limit
198K
Tokens
Max Output
33K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.34
Output
$1.19
Caching (per 1M tokens)
Read
$0.04
Frequently Asked Questions
MiniMax M2.5 by Venice AI costs $0.34 per 1M input tokens and $1.19 per 1M output tokens. Cached reads cost $0.04 per 1M tokens.
Model Details
API Integration