MiniMax M3.1 Flash

MiniMaxKey minimax-m3.1-flashAlso reported as MiniMax-M3.1-Flash, minimax/minimax-m3.1-flash, mm/minimax-m3.1-flash, minimax-cn/minimax-m3.1-flash, minimaxai/minimax-m3.1-flash, cb/minimax-m3.1-flash

Rank
#45
by active users
Active users
39
NewNew: no active users in the previous 30 days, 39 now. vs previous 30 days
Adoption
4.1%
of 961 accounts
Tokens
15.1B
cache included
Est. cost
$334
at public list prices
First seen
Oct 19, 2026
in any submission

Oct 14 – Nov 12, 2026 (UTC)961 accounts100% of tokens from an identified modelData through Nov 12, 2026, 06:11 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 12, 2026

Daily active users for MiniMax M3.1 Flash, Oct 14, 2026 to Nov 12, 2026. Peak 14. Use the left and right arrow keys to read each day.1580
Show daily values
Daily active users and tokens for MiniMax M3.1 Flash
Date (UTC)Active usersTokens
Oct 14, 202600
Oct 15, 202600
Oct 16, 202600
Oct 17, 202600
Oct 18, 202600
Oct 19, 202616M
Oct 20, 20265822.2M
Oct 21, 20267339.9M
Oct 22, 20267363M
Oct 23, 202614250.6M
Oct 24, 202610710.7M
Oct 25, 20269499.3M
Oct 26, 2026131B
Oct 27, 20267133.3M
Oct 28, 202611765.6M
Oct 29, 2026101.2B
Oct 30, 20266621M
Oct 31, 20267519.3M
Nov 1, 20269581.8M
Nov 2, 20265865.7M
Nov 3, 202681.2B
Nov 4, 202661.9B
Nov 5, 20267561.1M
Nov 6, 20264254.3M
Nov 7, 20266505.8M
Nov 8, 20264219M
Nov 9, 20265322M
Nov 10, 202651.2B
Nov 11, 20263341.8M
Nov 12, 202600

Token mix

How the 15.1B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input6.8%
  • Output0.6%
  • Cache read92%
  • Cache write0%
  • Reasoning0.9%

Agents that carry MiniMax M3.1 Flash

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. Pi19% of this model's tokens7active users
  2. OpenCode19% of this model's tokens12active users
  3. Claude Code16% of this model's tokens12active users
  4. Oh My Pi11% of this model's tokens6active users
  5. Hermes Agent8.8% of this model's tokens3active users
  6. MiniMax Code5.7% of this model's tokens2active users
  7. cc-mirror/cindy5.0% of this model's tokens1active users
  8. cc-mirror/asyncopenai4.4% of this model's tokens1active users
  9. Reasonix4.3% of this model's tokens1active users
  10. CodeBuddy3.2% of this model's tokens1active users
  11. Codex CLI2.9% of this model's tokens3active users
  12. Grok Build0.5% of this model's tokens1active users
  13. WorkBuddy0.2% of this model's tokens3active users
  14. cc-mirror/ai-memory<0.1% of this model's tokens1active users
  15. OpenClaw<0.1% of this model's tokens2active users
  16. DeepSeek Harness<0.1% of this model's tokens2active users
  17. Cherry Studio<0.1% of this model's tokens1active users
  18. cc-mirror/python-urllib<0.1% of this model's tokens1active users
  19. cc-mirror/curl<0.1% of this model's tokens1active users
  20. cc-mirror/mozilla<0.1% of this model's tokens1active users

Benchmarks

The best result for MiniMax M3.1 Flash in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.

All benchmarks
  • WebDev ArenaWeb development · LMArena
    1,587
    Rank #29 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)

Not evaluated: Epoch Capabilities Index, GPQA Diamond, Humanity's Last Exam, FrontierMath Tiers 1–3 (v2), SimpleQA Verified, Terminal-Bench 4.1, CursorBench, DeepSWE, FrontierSWE, Agent Arena. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. MiniMax (minimax.io) is the lab's own API and the reference price for the estimates below.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.03
Est. per 1M tokens
92% cache reads
At the community mix
$0.02
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.26
Per 1M tokens at list prices
No cache

Cache reads were 92% of MiniMax M3.1 Flash tokens in the last 30 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • MiniMax (minimax.io) list prices per 1M tokens: input $0.15, output $0.60, cache read $0.01.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.
  • No cache-write price is listed, so cache writes are priced as input.

List prices by provider

  • MiniMax (minimax.io)ReferenceMiniMax-M3.1-Flash
    $0.15 input per 1M tokens$0.60 output per 1M tokens$0.01 cache read per 1M tokensCache write not listed1M tokens of context
  • OpenRouterminimax/minimax-m3.1-flash
    $0.07 input per 1M tokens$0.30 output per 1M tokens$0.007 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewayminimax/minimax-m3.1-flash
    $0.15 input per 1M tokens$0.60 output per 1M tokens$0.01 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Fireworks AIaccounts/fireworks/models/minimax-m3p1-flash
    $0.15 input per 1M tokens$0.60 output per 1M tokens$0.01 cache read per 1M tokensCache write not listed1M tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
1M tokens
Max output
524K tokens
Input
Text, Image, Video
Output
Text
Knowledge cutoff
— not listed
Release date
Oct 19, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used MiniMax M3.1 Flash most in this period, by tokens. Hidden accounts are never listed.

  1. 1如是@MiFaZhan5.2Btokens$251est. cost15active days$251 est. cost · 15 active days
  2. 2sigco3111@sigco31113.3Btokens$5est. cost17active days$5 est. cost · 17 active days
  3. 3Christopher Butler@techsaint979Mtokens$11est. cost14active days$11 est. cost · 14 active days
  4. 4咸鱼一条@MrLinda783.6Mtokens$15est. cost3active days$15 est. cost · 3 active days
  5. 5Baptiste@BaptisteFaisy645.8Mtokens<$1est. cost6active days<$1 est. cost · 6 active days
  6. 6Zenco@notzenco523.2Mtokens$10est. cost5active days$10 est. cost · 5 active days
  7. 7xlfish233@xlfish233518.8Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  8. 8aurura12@aurura12480.8Mtokens$10est. cost6active days$10 est. cost · 6 active days
  9. 9ShirakiriShu@ShirakiriShu378.8Mtokens—est. cost10active daysno price · 10 active days
  10. 10Nehr@AgileInnov8tor291.5Mtokens$5est. cost7active days$5 est. cost · 7 active days

More from MiniMax

Other MiniMax models in the same period, by active users.

  1. MiniMax M3.1 Flash Free5.8% adoption56active users
  2. MiniMax M32.7% adoption26active users
  3. MiniMax M3.1 Flash Preview1.2% adoption12active users
  4. MiniMax M2.70.6% adoption6active users
  5. MiniMax M2.50.3% adoption3active users
  6. MiniMax M2.7 Highspeed0.1% adoption1active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • LMArenaWebDev Arena and Agent Arena leaderboards.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 19, 2026LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), Hugging Face.
  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count