MiniMax M3

Fireworks

Get an API key

MiniMax's low-cost open-weight frontier model with native multimodality and 512K context.

Streaming JSON mode Tool calling Vision Reasoning Long context Multilingual

Modalities: IntextimageOuttext
Input / output: $0.30 / $1.20USD per 1M tokens
Context: 512K
Providers: 6 live
Released: May 31, 2026

Chat with MiniMax M3 free →

Playground

Preparing playground

Providers


primary	6.2s	100%
fallback	—	—
fallback	—	—
emergency	—	—
emergency	—	—
emergency	—	—

Performance

Response latency estimates

Time to first token

Generation speed · tok/s

Request success

Text-model timing and speed, plus API request success. Daily latency percentiles are estimates. Your request logs

API

POST/api/v1/chat/completionsOpenAI-compatible

minimax-m3

curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'

messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choiceresponse_formatimage_url content partsreasoningreasoning_effort

Pricing

Input: $0.30/M tokens
Cached input: $0.03/M tokens
Output: $1.20/M tokens

Published USD rates. Actual cost depends on input, output, cache usage and request options.