MiniMax M2.7

by MiniMax · served by SonarCompute

Open-weight model tuned for software-engineering work, priced for high-volume pipelines.

Get an API key — $5 free See the code

$5 in free credits on signup · no card required

$0.30 / 1M

Input tokens

$1.20 / 1M

Output tokens

180K

Context window

78 tok/s

Throughput target

FP8

Precision

Model ID — click to copy

// OVERVIEW

What MiniMax M2.7 is good at

MiniMax M2.7 is the workhorse option on our roster: an open-weight model tuned specifically for software-engineering tasks: agentic coding, log analysis, troubleshooting and refactoring. It trades a little raw scale against Kimi K2.6 for roughly half the per-token price.

That pricing profile makes M2.7 the sensible default for high-volume pipelines: CI review bots, log triage, batch refactoring, test generation, and anywhere else the workload is measured in millions of tokens a day and unit economics decide which model you can afford to keep running.

We serve M2.7 in FP8 with streaming on by default and exact usage accounting in every response. Like everything on SonarCompute, requests are processed in memory: no prompt logging, no training on customer data.

agentic coding · log analysis · troubleshooting · refactoring

// QUICKSTART

One-line switch from OpenAI

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.sonarcompute.com/v1",
    api_key=os.environ["SONARCOMPUTE_KEY"])

client.chat.completions.create(
    model="minimax/minimax-m2.7",
    stream=True,
    messages=[{"role": "user",
               "content": "…"}])

Works with the official OpenAI SDKs, LangChain, LiteLLM and any client that accepts a custom base URL. Streaming (SSE) and usage accounting included.

// FAQ

Questions we actually get

Is the MiniMax M2.7 API OpenAI-compatible?

Yes. Point the official OpenAI SDK at https://api.sonarcompute.com/v1, use model id minimax/minimax-m2.7, and /chat/completions works as-is, including SSE streaming.

How much does MiniMax M2.7 cost per million tokens?

$0.30 per 1M input tokens and $1.20 per 1M output tokens — roughly half the price of Kimi K2.6, metered exactly.

How do I get a MiniMax M2.7 API key?

Create an account at app.sonarcompute.com — new accounts start with $5 in free credits and no card is required.

What context window does MiniMax M2.7 support?

180K tokens.

Do you log my prompts?

No. Prompts and completions are processed in memory and are not retained after the response is delivered. Details are in our Data Retention & Logging Disclosure.

Also served: Kimi K2.6

Compare pricing and specs on the models overview, or create an account and test both on the same $5 of free credits.

Create an account Kimi K2.6 →