TheRouter.aiTheRouter.ai
Back to Models

MiniMax M2.5 Highspeed

minimaxminimax/m2.5-highspeed

MiniMax M2.5 Highspeed variant with ~100 tokens/sec output speed. Same capabilities as M2.5 at 2x cost for latency-sensitive applications.

Context Length
205K
Max Output
66K
Input Price
$0.960/ 1M tokens
Output Price
$3.84/ 1M tokens

Modalities

text→text

Pricing Breakdown

TypeRate
Input$0.960 / 1M tokens
Output$3.84 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstop

API Usage Examples

China users: replace api.therouter.ai with api.therouter.com.cn in the examples below for lower latency.

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "minimax/m2.5-highspeed",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'