Skip to content
CostPerPrompt

MiniMax M2.5 API Pricing

MiniMax · context window 205K · prices updated 2026-09-15

Input per 1M tokens
$0.27
Output per 1M tokens
$1.08
Cached input per 1M
$0.027
90% cheaper than fresh input

Where MiniMax M2.5 sits on price

At $1.08 per million output tokens, MiniMax M2.5 is a mid tier model — 1.9× cheaper than the median output price of $2.08, which puts it cheaper than 66% and pricier than 34% of the models we track. It sits 2th cheapest of the 9 MiniMax models we track. Output costs 4.0× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
925,926
One full context fill
$0.0553
Cheaper than
66% of tracked models

Cached input is 90% cheaper. On an input-heavy workload you need roughly a 28% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on MiniMax M2.5

These three workloads are the ones teams actually run on a mid-priced model — a $1.08/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. $0.0029 $42.93
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0014 $405
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0003 $8.91

Model your exact traffic in the API cost calculator — it preloads MiniMax M2.5 with caching and batch options.

MiniMax M2.5 price history

MiniMax last cut MiniMax M2.5's output price on Sep 12, 2026 (-10% per output token), from $0.3/$1.20 to $0.27/$1.08 per 1M in/out. That is one of 5 repricings in the 44 days we have tracked it — worth knowing before you hard-code today's rate into a budget.

Date Input /1M Output /1M Output change
Aug 2, 2026 (tracking began) $0.15 $0.9
Aug 6, 2026 $0.22 $0.9 0%
Aug 21, 2026 $0.27 $0.95 +6%
Aug 22, 2026 $0.27 $1.08 +14%
Sep 10, 2026 $0.3 $1.20 +11%
Sep 12, 2026 $0.27 $1.08 -10%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

MiniMax M2.5 vs Qwen3 Next 80B A3B Instruct

The closest-priced alternative from another vendor is Qwen3 Next 80B A3B Instruct (Alibaba (Qwen)) — priced within a rounding error on output, with $0.18 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Qwen3 Next 80B A3B Instruct pricing →

Cheaper alternatives

More MiniMax models

Frequently asked questions

How much does the MiniMax M2.5 API cost?

MiniMax M2.5 costs $0.27 per million input tokens and $1.08 per million output tokens, with cached input at $0.027 per million (90% cheaper). That works out to roughly 925,926 output tokens per dollar.

What does the support chatbot workload cost on MiniMax M2.5?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0029 per request and $42.93 per month on MiniMax M2.5. Conversation history re-sent each turn — the classic prompt-caching win.

What does it cost to fill MiniMax M2.5's 205K context window?

Sending 205K of input in a single request costs $0.0553 at $0.27 per million tokens — before any output. With prompt caching that same fill drops to about $0.0055 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is MiniMax M2.5 worth the price?

MiniMax M2.5 sits in the middle of the market (2 of 9 by price within MiniMax). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.