MiniMax

Operational· 100% uptime, 7 days

MiniMax M2.7 API

The MiniMax M2.7 API for coding and agents, 57% below MiniMax's list price

Price per 1M tokens57%off

Input: $0.13~~$0.30~~
Output: $0.51~~$1.20~~
Cached input: $0.013

Get your API key Try it in the playground

Model IDminimax-m2.7

chat.py

from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="minimax-m2.7",
    messages=[{"role": "user", "content": "Explain quicksort in two sentences."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK.

Context window: 205K tokens
Input: Text
Output: Text
Released: Mar 18, 2026
Uptime, 7 days: 100%

Pricing

MiniMax M2.7 API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription and no minimum. Requests that fail are never billed.

Rate	zurelay	MiniMax list	You save
Input per 1M tokens	$0.13	~~$0.30~~	57%off
Output per 1M tokens	$0.51	~~$1.20~~	57%off
Cached input per 1M tokens	$0.013	—	—

One rate at every prompt length, up to the full 205K context window. Streaming, tool calls and structured outputs cost nothing extra.

Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M

Output tokens per month10M

zurelay

$11.60

MiniMax list price

$27.00

You save every month$15.40

$184.80 a year

Overview

What is MiniMax M2.7?

MiniMax M2.7 is MiniMax's model for agentic coding and professional work, released on March 18, 2026, with about 230B total and 10B active parameters. The zurelay MiniMax M2.7 API serves it through one OpenAI-compatible endpoint with a 204,800-token context window, at 57% below MiniMax's list price.

MiniMax released M2.7 on March 18, 2026 as the MiniMax-M2.7 and M2.7-highspeed API models, and published the weights on Hugging Face in April 2026. It is a Mixture-of-Experts model with about 230B total parameters, of which about 10B are active per token. MiniMax calls it its first model to take part in its own evolution: during development it helped debug training runs and modify its own agent scaffold. On zurelay the MiniMax M2.7 API model ID is minimax-m2.7, and it costs $0.13 per 1M input tokens and $0.51 per 1M output tokens.

MiniMax's reported results center on software engineering and office work. M2.7 scores 56.22% on SWE-Pro, 55.6% on VIBE-Pro for end-to-end project delivery, 57.0% on Terminal Bench 2 and 76.5 on SWE Multilingual. On GDPval-AA it reached an Elo of 1495, which MiniMax called the highest among open-source models at launch. MiniMax also reports 97% skill adherence across more than 40 complex skills, and native support for Agent Teams, where several agents collaborate on one task.

M2.7 is a text-in, text-out reasoning model. It thinks before it answers and interleaves reasoning with tool calls, carrying its reasoning forward across steps of an agent loop. Its context window is 204,800 tokens. MiniMax recommends streaming for its reasoning models and suggests temperature 1.0 and top_p 0.95.

The weights come under MiniMax's non-commercial license, so commercial use of the weights needs written authorization from MiniMax. MiniMax released M3 on June 1, 2026. M2.7 remains on MiniMax's API, and MiniMax has not announced a retirement date for it.

Strengths

Where MiniMax M2.7 shines. And what teams build with it.

Agentic software engineering

MiniMax reports 56.22% on SWE-Pro and 57.0% on Terminal Bench 2, plus 55.6% on VIBE-Pro for end-to-end project delivery.

Small active footprint

Only about 10B of its roughly 230B parameters run per token. MiniMax designed the M2 series end to end for agent deployment.

Follows complex skills

MiniMax reports 97% adherence across more than 40 complex skills, each longer than 2,000 tokens.

Open weights

The weights are public on Hugging Face under MiniMax's non-commercial license, so you can inspect and test the model yourself.

Use cases

Coding agents
Bug fixing, multi-file changes and terminal tasks inside agent harnesses.
Log analysis and debugging
Read logs to find bugs and review code for security issues, work MiniMax highlights for M2.7.
Office deliverables
Produce reports, analyses and other professional documents, the kind of work GDPval-AA measures.
Multi-agent systems
Run several agents that split and coordinate one task, using M2.7's native Agent Teams support.

Get started

Call MiniMax M2.7 in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to zurelay.

1
Create a key
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
Get your API key
2
Point your SDK at zurelay
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1
3
Use minimax-m2.7
Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.
minimax-m2.7

Works with the tools you already use

Compare

Similar models. All on the same key.

58%off

Gemini 3.7 Flash

$0.32 / $1.59 per 1M tokens

Pick Gemini 3.7 Flash when you need image, video, audio or PDF input or a context window over 1M tokens.

Gemini 3.7 Flash API

58%off

Gemini 3.5 Flash-Lite

$0.12 / $1.04 per 1M tokens

Pick Gemini 3.5 Flash-Lite for fast, high-volume steps with multimodal input and a 1M-token context.

Gemini 3.5 Flash-Lite API

88%off

DeepSeek V4.1 Flash

$0.037 / $0.15 per 1M tokens

Pick DeepSeek V4.1 Flash for a 1M-token context, image input and responses up to 384K tokens.

DeepSeek V4.1 Flash API

FAQ

MiniMax M2.7 API questions.

Anything else, write to sales@zurelay.com and an engineer will answer.

How much does the MiniMax M2.7 API cost?

On zurelay, minimax-m2.7 costs $0.13 per 1M input tokens and $0.51 per 1M output tokens, with cached input at $0.013. MiniMax's list price is $0.30 input and $1.20 output per 1M, so you save 57%. Reasoning tokens count as output.

Is there a cheaper MiniMax API than MiniMax's own?

Yes. zurelay serves minimax-m2.7 at 57% below MiniMax's list price for the standard MiniMax-M2.7 model. You pay from prepaid credit with no subscription, and failed requests are never billed.

How do I call the MiniMax M2.7 API with the OpenAI SDK?

Install the official openai package, set base_url to https://api.zurelay.com/v1 and use your zurelay API key. Then send a Chat Completions request with model set to "minimax-m2.7". zurelay also accepts MiniMax's own name, MiniMax-M2.7, so existing code only needs a new base URL and key.

What is the MiniMax M2.7 context window?

MiniMax lists a 204,800-token context window for MiniMax-M2.7. The model takes text input and writes text; it does not read images.

Is MiniMax M2.7 open source?

The weights are public on Hugging Face, but under MiniMax's non-commercial license rather than an open-source license. Commercial use of the weights requires written authorization from MiniMax. Personal use and non-profit research are allowed.

What is MiniMax M2.7 best at?

Agentic coding and professional work: fixing bugs across a repository, terminal tasks, log analysis, and multi-step office deliverables. It suits long agent loops, because it keeps reasoning between tool calls.

What is the difference between MiniMax-M2.7 and M2.7-highspeed?

MiniMax sells M2.7 in two API versions that it says give identical results: MiniMax-M2.7 and a faster, higher-priced M2.7-highspeed. zurelay's minimax-m2.7 is compared against the standard MiniMax-M2.7 list price.

Does the MiniMax M2.7 API support streaming and rate limits?

Yes. Set stream: true, and add stream_options.include_usage to get token counts in the final chunk. Each zurelay API key can have its own monthly budget and requests-per-minute cap. Failed requests are retried on another route and never billed.

Is it the same model as MiniMax's M2.7?

Yes, it is MiniMax's M2.7 model. Responses are sampled, so wording varies between runs, and zurelay does not promise byte-identical output. zurelay is independent and is not affiliated with or endorsed by MiniMax.

More models on zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at zurelay, and every request costs up to 85% less from the first token.

Get your API key Talk to an engineer

MiniMax M2.7 API

MiniMax M2.7 API pricing. A fraction of the list price.

What is MiniMax M2.7?

Where MiniMax M2.7 shines. And what teams build with it.

Agentic software engineering

Small active footprint

Follows complex skills

Open weights

Coding agents

Log analysis and debugging

Office deliverables

Multi-agent systems

Call MiniMax M2.7 in three steps.

Create a key

Point your SDK at zurelay

Use minimax-m2.7