Claude Fable 5.2 now costs less. Improvements to our serving architecture have lowered the cost of using the model, and the new rates are live.See new pricing
Minimax

MiniMax M3.1 Flash Preview

Save 70%Official

minimax/minimax-m3.1-flash-preview

MiniMax M3.1 Flash Preview — MiniMax's September 2026 preview coding model, now forwarded to M3.1 Flash, 1M context, thinking always on with five effort levels.

Context window
1M
Input modalities
TextImage
Output modalities
Text
Capabilities
Vision · Reasoning · Tool calling · Coding · Prompt cache
Upstream release
2026-09-27
RouteMux name
minimax/minimax-m3.1-flash-preview
Official ID
MiniMax-M3.1-Flash-Preview

What is MiniMax M3.1 Flash Preview

MiniMax M3.1 Flash Preview was the first model in MiniMax's M3.1 line, released as a preview on September 27, 2026 and tuned for speed and stability in everyday development work — bug fixes, feature builds, agentic coding. On October 19, 2026 MiniMax released the generally available MiniMax M3.1 Flash and retired the preview name; MiniMax's docs state that requests using the old name are now served by MiniMax-M3.1-Flash.

RouteMux follows suit: requests to minimax-m3.1-flash-preview are forwarded automatically to MiniMax M3.1 Flash and billed at its price, with no code changes needed. The prices on this page are what you are charged now.

MiniMax has not published any behavioral differences between the preview and the GA model, and the two have identical specs in the RouteMux catalog: a 1M-token context window, text and image input, tool calling and prompt caching, and always-on thinking with a reasoning effort of low, medium, high, xhigh or max (default: max). Existing parameters keep working; switch the model field to minimax/minimax-m3.1-flash when convenient.

MiniMax M3.1 Flash Preview API pricing

Prices verified 2026-10-20

InputOfficial $0.15 / M tokens
$0.045/ M tokensSave 70%
OutputOfficial $0.6 / M tokens
$0.18/ M tokensSave 70%

Cache read $0.0045/M · Cache write —/M

Estimate cost

Estimated cost$0.00063

Key capabilities

VisionReasoningTool callingCodingPrompt cache

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.

Sign up and claimNo subscription. Pay for what you use.

Interface and protocols

Use any of these IDs to call this model via the API.

RouteMux nameminimax/minimax-m3.1-flash-preview
Official IDMiniMax-M3.1-Flash-Preview

Replace 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-preview",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)
base_url: https://api.routemux.com/v1

Performance (last 30 days)

MiniMax M3.1 Flash Preview FAQ

›What is MiniMax M3.1 Flash Preview?

MiniMax M3.1 Flash Preview — MiniMax's September 2026 preview coding model, now forwarded to M3.1 Flash, 1M context, thinking always on with five effort levels.

›How large is the context window of MiniMax M3.1 Flash Preview?

MiniMax M3.1 Flash Preview supports a context window of up to 1M tokens.

›How much does the MiniMax M3.1 Flash Preview API cost?

Through RouteMux, MiniMax M3.1 Flash Preview 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 Preview via API?

MiniMax M3.1 Flash Preview is OpenAI-compatible: point your base URL at RouteMux and set the model field to minimax/minimax-m3.1-flash-preview — no code changes needed.

›Which input and output modalities does MiniMax M3.1 Flash Preview support?

MiniMax M3.1 Flash Preview accepts text, image as input and produces text as output.

›When was MiniMax M3.1 Flash Preview released?

MiniMax M3.1 Flash Preview was released on September 27, 2026.

Sources