MiniMax M3 Preview API

MiniMax M3 Preview is a large language model by MiniMax, available on the Venice API as minimax-m3-preview. It runs privately, with zero data retention.MiniMax-M3 preview is a 1.4T-parameter frontier model from MiniMax for coding, agentic workflows, and complex reasoning, served at fp8 with a 512K context window.

MiniMax M3 Preview API pricing

Model ID	Variant	Privacy	Price
`minimax-m3-preview`	Standard	Private	$0.30 input /$ 1.20 output per 1M tokens

MiniMax M3 Preview specifications

Spec	Value
Provider	MiniMax
Released	Jun 12, 2026
Privacy	Private
Open weights	Yes
Context window	512K tokens
Max output	64K tokens
Reasoning effort	Not adjustable
Served precision	FP8

How to use the MiniMax M3 Preview API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "minimax-m3-preview" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3-preview",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'

MiniMax M3 Preview API FAQ

How much does the MiniMax M3 Preview API cost?

0.30 per 1M input tokens and

1.20 per 1M output tokens, with cached input at $0.06 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the MiniMax M3 Preview model ID?

Use minimax-m3-preview as the model parameter.

Is the MiniMax M3 Preview API private?

MiniMax M3 Preview is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of MiniMax M3 Preview?

512K tokens of context, with up to 64K output tokens per response.

What does MiniMax M3 Preview support?

MiniMax M3 Preview supports function calling, reasoning, image input, web search and prompt caching.

Which endpoint does the MiniMax M3 Preview API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

GPT-5.6 Luna API: $0.25 input /$ 1.50 output per 1M tokens
GPT-5.6 Luna Pro API: $0.25 input /$ 1.50 output per 1M tokens
Qwen 3.5 35B A3B API: $0.31 input /$ 1.25 output per 1M tokens
Mercury 2 API: $0.31 input /$ 0.94 output per 1M tokens

Explore

By modality