Home/Models/MiniMax M3
MODEL DOSSIER / ENGLISH

MiniMax M3

minimax-m3

MiniMaxtext2026-06-01

MiniMax M3 is a text model from MiniMax. The snapshot records a release date of 2026-06-01. Context window: 1.04858M tokens. Maximum output: 512K tokens. Input: text, images, video. Output: text. Capabilities recorded: reasoning, tool calls, open weights.

Directory snapshot 2026-10-26 · Chinese dossier: 完整中文页

Context1.04858M
Max output512K
Inputtext, images, video
Outputtext
Official input¥2.01 / 1M
Official output¥8.02 / 1M
Capabilitiesreasoning, tool calls, open weights
Release2026-06-01

Official list price

CNY / 1M TOKENS

Official list price in the directory snapshot: ¥2.01 input and ¥8.02 output per 1M tokens, in CNY. Relay prices below are what individual sites listed; they can be lower or higher, and they are not official prices.

Relay coverage

24 SITES

24 sites in our public directory listed this model ID in the 2026-10-26 snapshot. Listed relay price range: ¥0.0137–¥2.52 per 1M input tokens. A listing means the model appeared on the site's public model list; it is not proof that the site serves the genuine model.

SiteDomainRelay price / 1MVerification
tallius.aiapi.tallius.ai¥0.0137enterprise
aruhub APIaruhub.com¥0.06enterprise
xem中转站ai.xem8k5.top¥0.08715—
OmniaKeyomniakey.com¥0.14enterprise
CheapAIcheapai.info¥0.21–¥0.42enterprise
ClaudeCNclaudecn.top¥0.27—
A6apia6api.com¥0.280095enterprise
LinoRoutelinoroute.com¥0.3–¥0.66personal
orbisorbiorbi.com¥0.3—
Z-APIapi.tmlab.store¥0.3personal
智惠APIapi.api2cn.com¥0.315enterprise
DragonAPInewapi.dragon3api.com¥0.315enterprise
招财猫AIapi.zhaocaimaoai.top¥0.315personal
Token-AItken.lol¥0.315–¥0.525enterprise
天天中转站apitiantian.com¥0.4enterprise
9527code9527.codes¥0.42–¥2.52enterprise
Monikeraimoniker.top¥0.42–¥0.84enterprise
幻灵AIapi.huanling.icu¥0.42—
Super APIsuperapi.buzz¥0.42—
CUN.aicun.ai¥0.438enterprise
猫云APIapi.nekocloud.vip¥0.45personal
Mirgomirgo.top¥0.482599personal
远桥云 APIyuanqiaoyun.com¥0.63enterprise
MX-AImxzzz.xyz¥0.63enterprise

How to verify this model on a relay

THREE STEPS
  1. Send a short request to the relay and read the model field in the response. It must match the ID you sent; a different ID is a mapping, not necessarily a substitution.
  2. Run the same prompt against a known-good endpoint and compare prompt-token counts. A large, repeatable gap points at a different tokenizer or a different backend.
  3. Run the seven checks. Billing, context retention, error shape, parameter compliance, tools, and streaming each produce evidence you can quote.

Same publisher

MiniMax

Questions

FAQ

What is the context window of MiniMax M3?

The snapshot records 1,048,576 tokens.

How much does MiniMax M3 cost?

Official list price: ¥2.01 input / ¥8.02 output per 1M tokens in CNY, per the directory snapshot. 24 relay sites listed it at ¥0.0137–¥2.52 per 1M input tokens.

Is a relay really serving MiniMax M3?

A model ID in a response is not proof. The seven-check detection compares tokenizer ratios, billing, error shape, parameter compliance, tools, and streaming against the advertised family. Run it on a key you can afford to spend, and treat one run as a spot check, not 24/7 monitoring.

Specifications and prices come from the 2026-10-26 public directory snapshot. We do not publish IQ scores or structured-output claims for models where we have no reliable data.