MiniMaxText Generation/v1/ai/chat

MiniMax M3 API

Access MiniMax M3 through one API key. MiniMax's latest flagship with 1M context.

MiniMax's latest flagship. Strong bilingual reasoning and a 1M token context window at a very low price.

No credit card required. Takes 30 seconds.

MiniMax M3 API pricing

Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated September 27, 2026.

Token type	Price
Input	$0.44 / 1M tokens
Output	$1.77 / 1M tokens
Context window	1.0M tokens

What it costs	Per job	Per 1,000
Chat reply1K input + 500 output tokens	$0.0013	$1.33
RAG answer8K input + 800 output tokens	$0.0049	$4.94
Agent step with tools30K input + 2K output tokens	$0.017	$16.74
Long document summary100K input + 2K output tokens	$0.048	$47.54

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see MiniMax M3 respond in real time.

POST/v1/ai/chatminimax/minimax-m3

Message *

Max Tokens

Maximum tokens in the response.

Stream

Real-time tokens

Hit "Send Request" to see the response

MiniMax M3 specs

Provider	MiniMax
Model ID	minimax/minimax-m3
Endpoint	/v1/ai/chat
Type	Text Generation
Context window	1.05M tokens
Max output	33K tokens
Reasoning	No
OpenAI-compatible	Yes — /v1/ai/chat/completions

How to get a MiniMax M3 API key

1
Create a free account
Sign up at yepapi.com with Google or email. It takes about 30 seconds and needs no card.
2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
3
Call MiniMax M3
Send a request to /v1/ai/chat with the x-api-key header and model "minimax/minimax-m3".
4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.

Strengths

✓

Latest MiniMax flagship

M3 is MiniMax's newest top-tier model, carrying the lab's strongest reasoning and generation capability across its lineup.

✓

1M token context

A 1,048,576-token context window lets M3 reason over very large documents and codebases in a single request, with up to 32,768 output tokens.

✓

Bilingual CN/EN

Trained for strong Chinese and English performance, it handles cross-language reasoning and content where many Western-trained models fall short.

✓

Very low cost

At $0.44 per 1M input and $1.77 per 1M output tokens, it brings flagship capability and a million-token window at a notably low price.

Quick start

Copy this snippet and start making calls with MiniMax M3.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "minimax/minimax-m3",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

MiniMax M3 vs similar models

Every model below runs on the same API key — switch by changing the model ID.

Model	Provider	Price	Context
MiniMax M3	MiniMax	$0.44 in / $1.77 out per 1M	1.0M
MiniMax M3.1 Flash	MiniMax	$0.22 in / $0.89 out per 1M	1.0M
MiniMax M2.5	MiniMax	$0.40 in / $1.40 out per 1M	205K
MiniMax M2.7	MiniMax	$0.44 in / $1.77 out per 1M	205K
Nemotron 3 Super	NVIDIA	$0 in / $0 out per 1M	262K
Qwen3.7 Flash	Qwen	$0.04 in / $0.19 out per 1M	1M
Solar Mini 4	Upstage	$0.07 in / $0.30 out per 1M	524K
Nemotron 3.5 Lightning	NVIDIA	$0.10 in / $0.30 out per 1M	262K

Why use MiniMax M3 through YepAPI?

✓One API key for all models — no separate accounts

✓OpenAI SDK compatible — just change the base URL

✓No monthly minimums — pay per token

✓Switch models with one line of code

✓Full provider passthrough — citations, search results, and all extras included

✓Streaming and non-streaming support on every model

✓Works with Cursor, Claude, LangChain, and any LLM tool

✓Unified billing across all providers

MiniMax M3 API: bilingual flagship with 1M-token context

MiniMax M3 is the lab's latest flagship model, combining strong bilingual Chinese-English reasoning with a one-million-token context window at a low price.

On YepAPI you call MiniMax M3 through a single OpenAI-compatible endpoint at $0.44 per 1M input and $1.77 per 1M output tokens, with a 1,048,576-token context window.

What is MiniMax M3?

MiniMax M3 is the newest flagship from MiniMax, a Chinese AI lab known for strong bilingual models. M3 leads its lineup on reasoning and generation while carrying a 1,048,576-token context window and up to 32,768 output tokens, so it can take in very large inputs and reason across them. Its defining strength is balanced Chinese and English performance: it is trained to reason and write fluently in both, which makes it a strong pick for cross-language and China-market applications where models trained mainly on English data tend to weaken. The combination of flagship quality, huge context, and low price makes it a high-value option.

Build with MiniMax M3 via YepAPI

Access MiniMax M3 through YepAPI's OpenAI-compatible /v1/ai/chat endpoint. Point your OpenAI SDK at YepAPI and set the model string to minimax-m3; moving to another model later is a one-string change. A single YepAPI key also reaches every other model plus SEO, SERP, and web-scraping tools, so you can scrape and rank content in Chinese or English, then have M3 summarize or generate from it within one integration and one bill.

MiniMax M3 API pricing — $0.44 / $1.77 per 1M tokens

MiniMax M3 costs $0.44 per 1M input tokens and $1.77 per 1M output tokens on YepAPI. For a flagship model with a million-token window and genuine bilingual strength, that is aggressive pricing. It lets you run large-context bilingual workloads continuously without flagship-tier costs, and because your key spans every model, you can mix M3 with cheaper options for routine sub-tasks.

MiniMax M3 for bilingual and China-market applications

M3 is the right choice when Chinese-language quality matters as much as English: building assistants for bilingual audiences, localizing and adapting content for the China market, translating with cultural nuance, and reasoning over mixed-language document sets. The million-token context lets it handle large bilingual corpora in one pass, and its flagship reasoning keeps quality high across both languages where single-language models degrade.

Try MiniMax M3 free

New YepAPI accounts get $5 in free credit with no card required. Use it to test MiniMax M3 on your Chinese and English prompts, validate bilingual quality, and compare cost against other flagships before you commit.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
Marcus T.
SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
Priya S.
Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Jake R.
Indie Hacker

Frequently asked questions

MiniMax's latest flagship. Strong bilingual reasoning and a 1M token context window at a very low price.

MiniMax M3 costs $0.44 per 1M input tokens and $1.77 per 1M output tokens through YepAPI, billed per request with no monthly fee. For example, a chat reply (1K input + 500 output tokens) costs about $0.0013.

Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for MiniMax M3 and every other model — no separate MiniMax account or waitlist.

New YepAPI accounts in most countries get free signup credit, enough to test MiniMax M3 without a card. After that you pay per request at the rates above — there is no subscription.

Use "minimax/minimax-m3" as the model on /v1/ai/chat. The short alias "minimax-m3" also works.

Yes. Point the OpenAI SDK at https://api.yepapi.com/v1/ai with your YepAPI key and set model to "minimax/minimax-m3". Streaming works the same way, so existing OpenAI code only needs the base URL and key changed.

MiniMax M3 supports a 1.0M token context window with up to 33K output tokens per request.

Ready to use MiniMax M3?

$5 free credit on signup. No credit card required. Pay per call.

Get API Key — Free $5 Credit Read Docs

Explore more models

MiniMax M3.1 Flash

MiniMax

Access MiniMax M3.1 Flash through one API key. MiniMax Fast Multimodal Agent Model.

1.0M ctx$0.22/M in

MiniMax M2.7

MiniMax

Access MiniMax M2.7 through one API key. Bilingual flagship model with massive output.

205K ctx$0.44/M in

MiniMax M2.5

MiniMax

Access MiniMax M2.5 through one API key. Affordable bilingual model.

205K ctx$0.40/M in

DeepSeek V4 Flash

DeepSeek

Access DeepSeek V4 Flash through one API key. 1M context, MoE speed, budget pricing.

1.0M ctx$0.13/M in

MiMo-V2.6-Pro

Xiaomi

Access MiMo-V2.6-Pro through one API key. Xiaomi 1T-Parameter Flagship.

1.1M ctx$0.64/M in

Qwen 3.5 27B

Qwen

Access Qwen 3.5 27B through one API key. Dense model for consistent performance.

262K ctx$0.40/M in

More Text Generation models

All MiniMax models →All AI models →