MiniMax / minimax-m2.5
MiniMax M2.5 stands out for MiniMax agent model balancing real-work efficiency and cost and Strong across full-stack coding, search, and office tasks. It is best suited to cost-aware agent backends and coding and office automation.
Context
200K
token
Input
$0.27
/ 1M tokens
Output
$1.08
/ 1M tokens
Quality
#72
Elo 1104
Overview
MiniMax M2.5 stands out for MiniMax agent model balancing real-work efficiency and cost and Strong across full-stack coding, search, and office tasks. It is best suited to cost-aware agent backends and coding and office automation.
Prompt cache
Supports prompt caching patterns for repeated context and longer production conversations.
Streaming
Supports streamed responses for chat, assistants, and interfaces that need visible incremental output.
Tool calling
Can call tools or functions, so product flows can connect model output to backend actions.
Model maker
MiniMax
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
OpenAI-compatible Chat Completions
Base URL: https://api.sealink.io/v1
Pricing
Light production run
100K input + 25K output
$0.054
Higher-volume run
1M input + 250K output
$0.54
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
minimax-m2.5base_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEYcurl https://api.sealink.io/v1/chat/completions \-H "Authorization: Bearer $SEALINK_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "minimax-m2.5","messages": [{"role": "user", "content": "Hello."}]}'
from openai import OpenAIclient = OpenAI(base_url="https://api.sealink.io/v1", api_key="<your-sealink-key>")resp = client.chat.completions.create(model="minimax-m2.5",messages=[{"role": "user", "content": "Hello."}],)print(resp.choices[0].message.content)
import OpenAI from "openai";const client = new OpenAI({baseURL: "https://api.sealink.io/v1",apiKey: process.env.SEALINK_API_KEY,});const resp = await client.chat.completions.create({model: "minimax-m2.5",messages: [{ role: "user", content: "Hello." }],});console.log(resp.choices[0].message.content);