Skip to content

MiniMax-M3

minimax/minimax-m3

MiniMax-M3 (June 2026), MiniMax's flagship open-weight MoE (about 428B total, 23B active) with sparse attention and adaptive thinking, served at a 512K context by DeepInfra and Together.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/minimax-m3",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Input Price
$0.238 / 1M tokens
Output Price
$0.935 / 1M tokens
Context
524.3K tokens
Output Cap
524.3K tokens

Capabilities

Explore what MiniMax-M3 supports, then use the API section for a request tailored to this model.

Max tokens

Model Information

Provider
DeepInfra
Product
Language Models
Release Date
Jun 1, 2026
Model Max Output
131.1K tokens
Data Policy
Not specified
Region
US, Global
Input
Text
Output
Text
Provider Documentation

Playground

Try MiniMax-M3 by DeepInfra. Requests use the selected workspace’s credits and API pricing.

MiniMax-M3Credits —
MiniMax-M3
⌘ / Ctrl + Enter to send

Providers

Compare available endpoints, pricing, and context limits for MiniMax-M3.

ProviderContextOutput CapInput PriceOutput PriceEndpoint
DeepInfra524.3K tokens131.1K tokens$0.238 / 1M tokens$0.935 / 1M tokens
deepinfra/minimaxai-minimax-m3
Together AI524.3K tokens524.3K tokens$0.255 / 1M tokens$1.02 / 1M tokens
together/minimaxai-minimax-m3

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValueEndpoint
Max input tokens524288deepinfra/minimaxai-minimax-m3
Max output tokens131072deepinfra/minimaxai-minimax-m3
Max input tokens524288together/minimaxai-minimax-m3
Max output tokens524288together/minimaxai-minimax-m3

Provider Notes

Several hosts serve this model. A request to this ID can be answered by any of them; a host-pinned ID selects one.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/minimax-m3",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modelminimax/minimax-m3 — Required model identifier.
max_tokensView Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValueEndpoint
Max input tokens524288deepinfra/minimaxai-minimax-m3
Max output tokens131072deepinfra/minimaxai-minimax-m3
Max input tokens524288together/minimaxai-minimax-m3
Max output tokens524288together/minimaxai-minimax-m3

Similar Models

Explore more language models and compare their capabilities.

ModelContextInput PriceOutput Price
inclusionAI/Ling-3.0-flash-VLDeepInfra131.1K tokens$0.051 / 1M tokens$0.153 / 1M tokens
ibm-granite/granite-4.2-8bDeepInfra131.1K tokens$0.051 / 1M tokens$0.2125 / 1M tokens
DeepSeek V4 Pro 0813DeepInfra1M tokens$1.105 / 1M tokens$2.21 / 1M tokens
Muse Glimmer 30BDeepInfra131.1K tokens$0.255 / 1M tokens$1.02 / 1M tokens
inclusionAI/Ling-3.0-flashDeepInfra131.1K tokens$0.051 / 1M tokens$0.153 / 1M tokens
DeepSeek V4 Flash 0731DeepInfra1M tokens$0.051 / 1M tokens$0.153 / 1M tokens
View All Language Models