Using MiniMax M3.1 Flash on MiniMax

Implementation guide · MiniMax M3 · MiniMax

Serverless

MiniMax exposes MiniMax M3.1 Flash through model ID MiniMax-M3.1-Flash. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-19. Next refresh: weekly.

Quick Start

1
Create an account at MiniMax and generate an API key.
2
Use the MiniMax SDK or REST API to call MiniMax-M3.1-Flash — see the documentation for request format.
3
You'll be billed $0.15/1M input, $0.60/1M output tokens. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

See MiniMax documentation for integration details.

Pricing on MiniMax

Type	Price (per 1M)
Input tokens	$0.15
Output tokens	$0.60

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsPrompt Caching

About MiniMax M3.1 Flash

MiniMax M3.1 Flash (API ID MiniMax-M3.1-Flash) is MiniMax's M-series language model for agentic reasoning, tool use, coding, computer use, cybersecurity and long-context tasks. It has a 1,000,000-token context window, accepts text, image and video input, and always thinks before answering, with tunable thinking depth (effort: low, medium, high, xhigh, max; default max). Flat pay-as-you-go pricing is $0.15 / $0.60 / $0.015 per 1M input / output / cached-input tokens. It replaces MiniMax M3.1 Flash Preview. Model weights are promised later and are not on Hugging Face as of 2026-10-19.

Full model details →

Model Specs

Released2026-10-19

Context1M

ArchitectureDecoder Only