MiniMax M3.1 Flash
Save 70%Officialminimax/minimax-m3.1-flash
MiniMax M3.1 Flash — MiniMax's coding and agent model, generally available since October 2026, with 1M context, always-on thinking and five effort levels.
- Context window
- 1M
- Input modalities
- text · image
- Output modalities
- text
- Capabilities
- Vision · Reasoning · Tool calling · Coding · Prompt cache
- Upstream release
- 2026-10-19
- RouteMux name
- minimax/minimax-m3.1-flash
- Official ID
- MiniMax-M3.1-Flash
Try MiniMax M3.1 Flash here
Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.
Sign in first to upload images to this vision model.
Your result will appear here
Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.
What is MiniMax M3.1 Flash
MiniMax M3.1 Flash is the generally available Flash model in MiniMax's M3.1 line, released on October 19, 2026 to replace the September preview. MiniMax positions it on speed and cost for everyday development and agent work — bug fixes, feature builds, agentic coding.
It has a 1M-token context window, text and image input, tool calling and prompt caching, and answers on OpenAI Chat Completions, OpenAI Responses and Anthropic Messages. Thinking is always on and cannot be switched off; the depth is set with a reasoning effort of low, medium, high, xhigh or max. When you omit it, MiniMax defaults to max.
Through RouteMux it is $0.045 per 1M input tokens against MiniMax's $0.15, $0.18 against $0.60 on output, and $0.0045 against $0.015 for cached input, with no context-length tiers.
Requests to the old model names minimax-m3.1-flash-preview, minimax-m2.7 and minimax-m2.7-highspeed are now served by this model and billed at its price — no code changes needed.
MiniMax M3.1 Flash API pricing
Prices verified 2026-10-20
Cache read $0.0045/M · Cache write —/M
Estimate cost
Limited time10% extra Credits on your first top-up — up to 200 bonus Credits
Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.
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
Text and image input, with no context-length price tiers.
Tool calling and caching
Native tool calling and automatic prompt caching.
Three protocols
OpenAI Chat, OpenAI Responses and Anthropic Messages.
Interface and protocols
Use any of these IDs to call this model via the API.
minimax/minimax-m3.1-flashMiniMax-M3.1-FlashReplace the ROUTEMUX_KEY placeholder with your API key. Create one →
from openai import OpenAI
client = OpenAI(
base_url="https://api.routemux.com/v1",
api_key="<ROUTEMUX_KEY>",
)
completion = client.chat.completions.create(
model="minimax/minimax-m3.1-flash",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)Performance (last 30 days)
MiniMax M3.1 Flash FAQ
›What is MiniMax M3.1 Flash?
MiniMax M3.1 Flash — MiniMax's coding and agent model, generally available since October 2026, with 1M context, always-on thinking and five effort levels.
›How large is the context window of MiniMax M3.1 Flash?
MiniMax M3.1 Flash supports a context window of up to 1M tokens.
›How much does the MiniMax M3.1 Flash API cost?
Through RouteMux, MiniMax M3.1 Flash costs $0.045 for input and $0.18 for output (USD per 1M tokens), below the official list price.
›How do I call MiniMax M3.1 Flash via API?
MiniMax M3.1 Flash is OpenAI-compatible: point your base URL at RouteMux and set the model field to minimax/minimax-m3.1-flash — no code changes needed.
›Which input and output modalities does MiniMax M3.1 Flash support?
MiniMax M3.1 Flash accepts text, image as input and produces text as output.
›When was MiniMax M3.1 Flash released?
MiniMax M3.1 Flash was released on October 19, 2026.
›Can I turn thinking off?
No. MiniMax rejects thinking disabled and an effort of "none" for this model with a 400 error. Use effort "low" for the lightest thinking.
›How do I set the effort level on each protocol?
OpenAI Chat Completions: reasoning_effort. OpenAI Responses: reasoning.effort. Anthropic Messages: output_config.effort. Thinking tokens are billed as output tokens.
›Do I need to change code that used the Preview or M2.7?
No. Requests to minimax-m3.1-flash-preview, minimax-m2.7 and minimax-m2.7-highspeed (with or without the minimax/ prefix) are forwarded to M3.1 Flash and billed at its price. Switch the model field to minimax/minimax-m3.1-flash when convenient.
›How is it different from MiniMax M3?
Same context window and protocols. M3.1 Flash always thinks and offers two extra effort levels (xhigh and max); M3 lets you turn thinking off and stops at high. M3 switches to a second price tier above 512K input tokens; M3.1 Flash has a single tier.
Sources
- MiniMax — M3.1 Flash announcement ↗
- MiniMax — Pay-as-you-go pricing ↗
- MiniMax — Text generation guide ↗
Reviewed by Jerry Fan on 2026-10-20