SHUTS DOWN NOV 18 2026205K CONTEXTTEXT ONLYPROMPT CACHING100 TPS TARGET
MiniMax M2.5 Highspeed API Pricing
Shuts down November 18, 2026. MiniMax dropped MiniMax-M2.5-highspeed from its pricing page around the launch of MiniMax M3.1 Flash on October 19, 2026, and has since published a schedule: closed to new users from October 19 and retired on November 18, 2026, when API requests stop working. Its last published rates were $0.6/M input, $2.4/M output and $0.03/M cached input.
Input - per 1M tokens
$0.60/M
Direct USD vendor row 2x base tier
Output - per 1M tokens
$2.40/M
Direct USD vendor row 2x base tier
Cached input - prompt cache read
$0.03/M
Cache write $0.375/M 95% off
Effective - agentic blend
$0.314/M
92/8 split - 82% cache
§ 01 / TERMINAL
MiniMax M2.5 Highspeed API cost calculator.
Calculator pre-loaded with the last rates MiniMax published for MiniMax M2.5 Highspeed. Tweak workload split and cache hit rate, then share the URL to share the calculation.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
MiniMax M2.5 Highspeed cost on real workloads.
CODING AGENT
Repo repair task
$0.013/task
OFFICE
Analyst memo draft
$0.013/memo
SEARCH
Web research brief
$0.011/brief
CHATBOT
Product support turn
$0.0032/turn
Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type
Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (MiniMaxAI/MiniMax-M2.1, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.
Characters 437
Words 71
Tokens (estimated) 82 tokens
Cost as input · uncached $0.00005 USD
Cost as output · uncached $0.0002 USD
Cost as cached input $0.000002 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| MiniMax M2.5 Highspeed Current | $0.60 cache $0.03 | $2.40 | $0.314 agentic 92/8 | 205K | Fast M2.5 coding and agents |
| MiniMax M2.5 | $0.30 cache $0.03 | $1.20 | $0.168 deprecated · −46% | 205K | Value-first MiniMax agent loops |
| MiniMax M2.1 Highspeed | $0.60 cache $0.03 | $2.40 | $0.314 retired | 205K | Lower-latency M2.1 agents |
| MiniMax M2.7 Highspeed | $0.60 cache $0.06 | $2.40 | $0.337 deprecated · +7% | 205K | Faster MiniMax flagship loops |
| MiniMax M2.7 | $0.30 cache $0.06 | $1.20 | $0.191 deprecated · −39% | 205K | MiniMax flagship agent loops |
| MiniMax M2 | $0.30 cache $0.03 | $1.20 | $0.168 retired | 205K | Original M2 coding agents |
| GPT-6.1 Terra | $1.00 cache $0.05 | $5.00 | $0.645 +2.1× | 1.05M | OpenAI's fast, efficient GPT-6 tier |
| DeepSeek V4 Pro | $1.32 cache $0.044 | $3.96 | $0.569 +81% | 1M | Low-cost reasoning workloads |
MiniMax M2.5 Highspeed API pricing FAQ.
Practical MiniMax M2.5 Highspeed pricing questions, with live MiniMax list rates separated from workload assumptions.
Q · 01 Can I still use MiniMax M2.5 Highspeed? +
Only if you already use it, and only until November 18, 2026. MiniMax's model list now carries a retirement notice for the M2.5 and M2.7 families: unavailable to new users from October 19, 2026, and retired on November 18, 2026, after which API requests to
MiniMax-M2.5-highspeed no longer work. M Plan and Token Plan requests are routed to MiniMax M3.1 Flash from October 19. The rates on this page are the last ones MiniMax published.Q · 02 What is the standard MiniMax M2.5 Highspeed API price? +
MiniMax's official pay-as-you-go pricing page lists
MiniMax-M2.5 Highspeed at $0.6/M input and $2.4/M output. Cache reads are listed at $0.03/M. AI//COST stores those direct USD list prices without currency conversion.Q · 03 Does MiniMax publish prompt caching for this model? +
MiniMax lists prompt-cache reads at
$0.03/M and cache writes at $0.375/M for MiniMax M2.5 Highspeed. The quote board uses the read price because repeated cache hits drive recurring workload cost.Q · 04 What context window does MiniMax M2.5 Highspeed support? +
MiniMax's text-generation docs list
204,800 tokens of context for this M2-family text model. This page rounds that to 205K for display consistency.Q · 05 Is there a Batch API discount? +
MiniMax's current pay-as-you-go table does not publish a separate Batch API discount for
MiniMax M2.5 Highspeed. Treat the public $0.6/M input and $2.4/M output rates as the default unless your account has a negotiated enterprise agreement.Q · 06 When was this price last checked? +
The rates on this page are the last MiniMax published; the Internet Archive still has them on its pricing page on October 11, 2026. On October 23, 2026 the page listed only MiniMax M3.1 Flash and MiniMax M3.
Q · 07 How accurate is the tokenizer estimate? +
The browser widget uses a
minimax-tokenizer-estimate chars-per-token approximation for English planning. Real billing depends on MiniMax server-side tokenization and can differ for Chinese, code, and mixed-language prompts.