# MiniMax M3.1 Flash Preview

> MiniMax M3.1 Flash Preview is the first model in MiniMax's M3.1 line, released on September 27, 2026. MiniMax tunes it for speed and stability in everyday development work — bug fixes, feature builds, agentic coding — rather than for the hardest one-off problems.

Canonical: https://routemux.com/minimax/minimax-m3.1-flash-preview
Provider: MiniMax

## Key facts

| Field | Value |
| --- | --- |
| Model ID | minimax/minimax-m3.1-flash-preview |
| Official model ID | MiniMax-M3.1-Flash-Preview |
| Context window | 1M |
| Max output | 524K |
| Input modalities | text, image |
| Output modalities | text |
| Capabilities | Vision, Reasoning, Tool Calling, Coding, Cache |
| Upstream release | 2026-09-27 |
| Availability | available |

## Pricing

- RouteMux input: $0.03 per 1M tokens
- RouteMux output: $0.12 per 1M tokens
- Cache read: $0.006 per 1M tokens
- Official price source: minimax_m3_parity, verified 2026-09-29

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- openai_chat
- openai_responses
- anthropic_messages

## What is MiniMax M3.1 Flash Preview

MiniMax M3.1 Flash Preview is the first model in MiniMax's M3.1 line, released on September 27, 2026. MiniMax tunes it for speed and stability in everyday development work — bug fixes, feature builds, agentic coding — rather than for the hardest one-off problems.

It keeps the M3 footprint: a 1M-token context window, text and image input, tool calling and prompt caching, answering on OpenAI Chat Completions, OpenAI Responses and Anthropic Messages. What changes is thinking. It is always on and cannot be switched off, and the depth is set with a reasoning effort of low, medium, high, xhigh or max. When you omit it, MiniMax defaults to max.

MiniMax only offers this model through its subscription plans, not on its pay-as-you-go price list, so there is no official per-token price to compare against. It is also a preview: MiniMax may change or retire it.

## Key capabilities

- **Five effort levels** — low / medium / high / xhigh / max. The default is max — set a lower level explicitly for latency-sensitive work.
- **1M-token context** — With text and image input.
- **Tool calling and caching** — Native tool calling and automatic prompt caching.
- **Three protocols** — OpenAI Chat, OpenAI Responses and Anthropic Messages.

## Sources

- [MiniMax — Text generation guide](https://platform.minimax.io/docs/guides/text-generation)

_Content reviewed by Jerry Fan on 2026-09-29._