whichllm — Browse and compare AI model specs and pricing

Merge Gateway

MiniMax M2.5 Highspeed model ID, context window & pricing

minimax

Quick facts

Model ID minimax/minimax-m2.5-highspeed
Source Merge Gateway
Context Window 204800
Pricing $0.60 input / $2.40 output per 1M tokens
Capabilities tool calling, reasoning, temperature control, open weights

Model overview

MiniMax M2.5 Highspeed is an AI model from Merge Gateway with 204800 token context window and text input support.

Published pricing is $0.60 input and $2.40 output per 1M tokens.

  • Workloads that use text inputs with text outputs.
  • Agent and tool workflows that need function calling.
  • Reasoning-heavy prompts where stepwise problem solving matters.
Model ID minimax/minimax-m2.5-highspeed
Provider Merge Gateway
Family minimax
Status -
Knowledge Cutoff -
Release Date 2026-02-13
Input Modalities text
Output Modalities text
Context Window 204800
Input Limit -
Output Limit 8192
Tool Calling Yes
Reasoning Yes
Structured Output No
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.60
Output Cost / 1M tokens $2.40
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.06
Cache Write Cost / 1M tokens $0.38