Home / Guides / Models

MiniMax M2.7 API: price, context and code

Updated 2026-10-18 · MiniMax's coding and agent model at MiniMax's own price, through OpenAI- and Anthropic-compatible APIs, with code samples.

Connection details

Base URL (OpenAI compatible)
https://api.aifans.fan/v1
Base URL (Anthropic compatible)
https://api.aifans.fan
API key
Create one in the console; it starts with sk- (no account yet? sign up)
Recommended models
deepseek-v4.1-flash, deepseek-v4-pro (all models and prices)

MiniMax M2.7 is MiniMax's model for coding and agent workflows, with tool calls. AIFans API serves it through OpenAI- and Anthropic-compatible endpoints: point your tool at our base URL and use minimax-m2.7 as the model name.

Price

USD per 1M tokensMaker's own priceHereSaving
Input$0.3$0.2984about the same
Cached input$0.06$0.0596about the same
Output$1.2$1.1939about the same
  • The same price per token as MiniMax charges itself — we do not mark it up, and there is no subscription, no minimum spend and no monthly fee. Failed calls are never billed.
  • Thinking is billed as output tokens, so leave max_tokens room (1000 or more).
  • Online top-ups carry a payment processing fee of 5.5% (minimum $0.8), added at checkout and shown before you pay; it is not part of your credit.

What it can do

  • A context window of about 200K tokens.
  • Answers of up to 128K tokens.
  • Tool calls, for agents that search, run code or call your own functions.
  • Text in, text out.

Why call it here instead of direct

  • One account and one key for M2.7 and every other model on the models page: switch models by changing one string, with no second sign-up, no second balance and no second invoice.
  • Both API shapes: the OpenAI Chat Completions API and the Anthropic Messages API, so Claude Code and the OpenAI SDKs both work against the same key.
  • Every call is itemised in the console with its tokens and price, and each key can carry a daily, monthly and total spending cap.
  • Servers in Singapore, close to Southeast Asia, India and East Asia.

Call it with the OpenAI SDK

# pip install openai
from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.aifans.fan/v1")
resp = client.chat.completions.create(
    model="minimax-m2.7",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=1000,
)
print(resp.choices[0].message.content)

Use it in Claude Code

Put this in ~/.claude/settings.json; the Claude Code guide has the details.

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.aifans.fan",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
    "ANTHROPIC_MODEL": "minimax-m2.7",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "minimax-m2.7",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "minimax-m2.7",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "minimax-m2.7",
    "CLAUDE_CODE_SUBAGENT_MODEL": "minimax-m2.7"
  }
}

Related guides