MiniMax

MiniMax-M2.5-highspeed

High-speed MiniMax-M2.5 variant (M2.5-Lightning) with aligned core capabilities, tuned for low-latency and high-throughput agent workloads

Category Text Model ID MiniMax-M2.5-highspeed

Model TypeHigh-Speed Reasoning Model (M2.5-Lightning)

Inference Speed~100 TPS

Cache Write¥5.25 / M tokens

Pricing & Specs

💰 Pricing

Input¥4.2 / M tokens

Output¥33.6 / M tokens

Cache Hit¥0.42 / M tokens

⚙️ Specs

Model TypeHigh-Speed Reasoning Model (M2.5-Lightning)

Inference Speed~100 TPS

Cache Write¥5.25 / M tokens

Cache Read¥0.42 / M tokens

Capability PositioningAligned with MiniMax-M2.5 core capabilities

Best-Fit ScenariosLow-Latency Chat, Concurrent Agents, Real-Time Toolchains

Release Date2026-02-12

API CompatibilityOpenAI, Claude API, Claude Code

API Examples

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.xairouter.com/v1"
)

response = client.chat.completions.create(
    model="MiniMax-M2.5-highspeed",
    messages=[
        {"role": "user", "content": "Summarize this content in bullet points and provide 3 key takeaways."}
    ]
)

print(response.choices[0].message.content)

cURL (OpenAI API)

curl https://api.xairouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "MiniMax-M2.5-highspeed",
    "messages": [
      {"role": "user", "content": "Summarize this content in bullet points and provide 3 key takeaways."}
    ]
  }'

Python (Claude SDK)

import anthropic
import os

# Set environment variables
os.environ["ANTHROPIC_BASE_URL"] = "https://api.xairouter.com"

client = anthropic.Anthropic(
    api_key="your-api-key",
    base_url="https://api.xairouter.com"
)

message = client.messages.create(
    model="MiniMax-M2.5-highspeed",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Summarize this content in bullet points and provide 3 key takeaways."}
    ]
)

print(message.content[0].text)

cURL (Claude API)

curl https://api.xairouter.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "MiniMax-M2.5-highspeed",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Summarize this content in bullet points and provide 3 key takeaways."}
    ]
  }'

Developer Assist

# Linux/macOS
export ANTHROPIC_AUTH_TOKEN=sk-Xvs...  # Your API Key
export ANTHROPIC_BASE_URL=https://api.xairouter.com
export ANTHROPIC_DEFAULT_OPUS_MODEL=MiniMax-M2.5-highspeed
export ANTHROPIC_DEFAULT_SONNET_MODEL=MiniMax-M2.5-highspeed
export ANTHROPIC_DEFAULT_HAIKU_MODEL=MiniMax-M2.5-highspeed

# Windows CMD
set ANTHROPIC_AUTH_TOKEN=sk-Xvs...
set ANTHROPIC_BASE_URL=https://api.xairouter.com
set ANTHROPIC_DEFAULT_OPUS_MODEL=MiniMax-M2.5-highspeed
set ANTHROPIC_DEFAULT_SONNET_MODEL=MiniMax-M2.5-highspeed
set ANTHROPIC_DEFAULT_HAIKU_MODEL=MiniMax-M2.5-highspeed

# Windows PowerShell
$env:ANTHROPIC_AUTH_TOKEN="sk-Xvs..."
$env:ANTHROPIC_BASE_URL="https://api.xairouter.com"
$env:ANTHROPIC_DEFAULT_OPUS_MODEL="MiniMax-M2.5-highspeed"
$env:ANTHROPIC_DEFAULT_SONNET_MODEL="MiniMax-M2.5-highspeed"
$env:ANTHROPIC_DEFAULT_HAIKU_MODEL="MiniMax-M2.5-highspeed"

# Start Claude Code
claude

# Now you can use MiniMax-M2.5-highspeed directly for development

← Back to Models