MiniMax-M2.7 API
About
Process massive datasets with MiniMax-M2.7, featuring an expansive 205K context window for long-document analysis. This model delivers cost-effective pricing at $0.35/1M input and $1.33/1M output tokens, native tool calling support, open weights architecture. Access MiniMax-M2.7 via the Charm Hyper API with up to 20K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
205K
Tokens
Input Limit
205K
Tokens
Max Output
20K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.35
Output
$1.33
Caching (per 1M tokens)
Write
$0.17
Frequently Asked Questions
MiniMax-M2.7 by Charm Hyper costs $0.35 per 1M input tokens and $1.33 per 1M output tokens. Cache writes cost $0.17 per 1M tokens.
Model Details
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
HYPER_API_KEY
API Base URL
https://hyper.charm.land/v1