How is the minimax-m3 API billed?

minimax-m3 is pay-as-you-go from ¥6.8238 / M. The exact rate is listed in the pricing table on this page and billed at EasyAPI's public price, with no subscription required.

How do I call minimax-m3 through the API?

EasyAPI exposes an OpenAI-compatible API: create an API key in the console, set base_url to https://token.easyapi.com and model to minimax/minimax-m3, then send requests to /v1/chat/completions. The Quick Start on this page includes cURL, Python and TypeScript examples; official OpenAI SDKs only need the base_url swapped.

Which request formats does minimax-m3 support?

OpenAI Chat Completions format including streaming (stream). Official OpenAI and Anthropic SDKs work by swapping base_url; see the Parameters table on this page for the full list.

How do I get started with minimax-m3?

Sign up for EasyAPI, create an API key in the console and top up your balance to call minimax-m3 pay-as-you-go, no subscription needed. You can also try it in the online Playground first, then copy the Quick Start example.

minimax-m3

Name: minimax-m3
Brand: MiniMax
Price: 6.8238 CNY
Availability: InStock

文本

MiniMax\\'s first multimodal release, accepting image and video input. Long-context inference runs cheaper and faster, and it handles multi-step agent workflows and computer-use scenarios.

Input price

¥6.823815% off

Market: ¥8.028

/ M

Output price

¥27.295215% off

Market: ¥32.112

/ M

Cache read

¥0.682415% off

Market: ¥0.8028

/ M

Cache write

¥015% off

/ M

Input

Text

Output

Text

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token

shell

export EASYAPI_API_KEY=sk-xxxxxxxx

Make your first request

Use minimax/minimax-m3 with the EasyAPI API:

cURL

curl https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{
  "model": "minimax/minimax-m3",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

curl

curl -N https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"minimax/minimax-m3","messages":[{"role":"user","content":"Hello!"}],"stream":true}'

Endpoint

Sends a chat completion request. Supports streaming and non-streaming modes.

POSThttps://token.easyapi.com/v1/chat/completions

Authorization: Bearer $EASYAPI_API_KEY
Content-Type: application/json
Model: minimax/minimax-m3

Send a chat completion request, with streaming or non-streaming responses. Docs

GEThttps://token.easyapi.com/v1/models

Authorization: Bearer $EASYAPI_API_KEY

List the models available to the current account. Docs

Parameters

Name	Type	Default	Description
`model`	string	—	Model ID, e.g. openai/gpt-4o or anthropic/claude-3-5-sonnet
`messages`	array	—	List of conversation messages, each with role and content
`stream`	boolean	false	When true, the response is streamed via SSE
`temperature`	float	1	Sampling temperature; higher values are more random
`max_tokens`	integer	—	Maximum number of tokens generated in a single reply
`top_p`	float	1	Nucleus sampling; limits the cumulative probability of candidate tokens
`frequency_penalty`	float	0	Frequency penalty; reduces repeated wording
`presence_penalty`	float	0	Presence penalty; encourages new topics

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

minimax-m3 FAQ

How is the minimax-m3 API billed?: minimax-m3 is pay-as-you-go from ¥6.8238 / M. The exact rate is listed in the pricing table on this page and billed at EasyAPI's public price, with no subscription required.
How do I call minimax-m3 through the API?: EasyAPI exposes an OpenAI-compatible API: create an API key in the console, set base_url to https://token.easyapi.com and model to minimax/minimax-m3, then send requests to /v1/chat/completions. The Quick Start on this page includes cURL, Python and TypeScript examples; official OpenAI SDKs only need the base_url swapped.
Which request formats does minimax-m3 support?: OpenAI Chat Completions format including streaming (stream). Official OpenAI and Anthropic SDKs work by swapping base_url; see the Parameters table on this page for the full list.
How do I get started with minimax-m3?: Sign up for EasyAPI, create an API key in the console and top up your balance to call minimax-m3 pay-as-you-go, no subscription needed. You can also try it in the online Playground first, then copy the Quick Start example.

Related models

All models

minimax-m2.1

MiniMax

性价比导向的通用模型，在对话与内容生产任务中速度和质量较均衡。

文本

15% off

Input price

¥1.7628/ M

Output price

¥6.9944/ M

Cache read

¥0.1763/ M

Cache write

¥2.2177/ M

minimax-m2.5-highspeed

MiniMax

M2.5 系列的加速版本，推理质量与标准版一致，吞吐约提升至三倍，主打编程与智能体工具调用，适合对延迟敏感的 Agent 交互与批量任务。

文本

15% off

Input price

¥3.4119/ M

Output price

¥13.6476/ M

Cache read

¥0.1706/ M

Cache write

¥2.1324/ M

minimax-m2.7

MiniMax

多智能体协作模型，支持复杂任务规划与生产级工作流执行

文本

30% off

Input price

¥1.4526/ M

Output price

¥5.8105/ M

Cache read

¥0.2905/ M

Cache write

¥0/ M

minimax-m2.7-highspeed

MiniMax

M2.7 高速版，输出与标准版一致但推理更快，面向编程、Agent 工具调用与办公自动化等对延迟敏感的场景。

文本

15% off

Input price

¥3.4119/ M

Output price

¥13.6476/ M

Cache read

¥0.3412/ M

Cache write

¥2.1324/ M

Input

Output

Input

Output

Get your API key

Make your first request

Enable streaming

Endpoint

Parameters

Using third-party SDKs

minimax-m3 FAQ

Related models

Popular comparisons for minimax-m3