RETIRED · OCT 202664K CONTEXTTEXT ONLYCACHE N/A64K CONTEXT
MiniMax M2-her API Pricing
Retired. MiniMax's model list marks M2-her as retired and no longer available, without a date; it had left the pay-as-you-go pricing page by July 2026. MiniMax M2-her is MiniMax's dialogue and role-play M2 variant. MiniMax's pricing page last listed $0.3/M input, $1.2/M output, with no cache-read price published for this row. Checked by hand against platform.minimax.io.
Input - per 1M tokens
$0.30/M
Direct USD vendor row base tier
Output - per 1M tokens
$1.20/M
Direct USD vendor row 4x input
Cached input
Not published
No cache public row not listed
Effective - agentic blend
$0.372/M
92/8 split - no cache
§ 01 / TERMINAL
MiniMax M2-her API cost calculator.
Calculator pre-loaded with the last rates MiniMax published for MiniMax M2-her. Tweak workload split and cache hit rate, then share the URL to share the calculation.
$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
MiniMax M2-her cost on real workloads.
ROLEPLAY
Character conversation
$0.0042/turn
LONG DIALOGUE
Story arc session
$0.021/session
COMMUNITY
NPC reply batch
$0.0072/batch
SUPPORT
Persona support chat
$0.003/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 428
Words 69
Tokens (estimated) 80 tokens
Cost as input · uncached $0.00002 USD
Cost as output · uncached $0.0001 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| MiniMax M2-her Current | $0.30 | $1.20 | $0.372 agentic 92/8 | 64K | Role-play and long dialogue |
| MiniMax M2 | $0.30 cache $0.03 | $1.20 | $0.168 retired | 205K | Original M2 coding agents |
| MiniMax M2.1 | $0.30 cache $0.03 | $1.20 | $0.168 retired | 205K | Stable coding and office agents |
| MiniMax M2.5 | $0.30 cache $0.03 | $1.20 | $0.168 deprecated · −2.2× | 205K | Value-first MiniMax agent loops |
| MiniMax M2.7 | $0.30 cache $0.06 | $1.20 | $0.191 deprecated · −49% | 205K | MiniMax flagship agent loops |
| GPT-6.1 Terra | $1.00 cache $0.05 | $5.00 | $0.645 +73% | 1.05M | OpenAI's fast, efficient GPT-6 tier |
| DeepSeek V4 Pro | $1.32 cache $0.044 | $3.96 | $0.569 +53% | 1M | Low-cost reasoning workloads |
| Gemini 3.8 Flash | $0.75 cache $0.075 | $3.75 | $0.481 +29% · promo | 1M | Global multimodal workloads |
MiniMax M2-her API pricing FAQ.
Practical MiniMax M2-her pricing questions, with live MiniMax list rates separated from workload assumptions.
Q · 01 Can I still use MiniMax M2-her? +
No. MiniMax's model list puts
M2-her under Retired Models — "retired and no longer available" — without a shutdown date, and it had already disappeared from the pay-as-you-go pricing page by July 2026. MiniMax names no replacement for the role-play model; its current text models are MiniMax M3.1 Flash and MiniMax M3. This page keeps the last price MiniMax published.Q · 02 What is the standard MiniMax M2-her API price? +
MiniMax's official pay-as-you-go pricing page lists
MiniMax-M2-her at $0.3/M input and $1.2/M output. No cache-read price is published for this row. AI//COST stores those direct USD list prices without currency conversion.Q · 03 Does MiniMax publish prompt caching for this model? +
MiniMax does not list prompt-cache read or write pricing for
MiniMax M2-her on the pay-as-you-go page. This page therefore uses the base input price for cached-token math and labels cache as not available.Q · 04 What context window does MiniMax M2-her support? +
MiniMax's text-chat docs list
M2-her with a 64 K context window for role-play and multi-turn dialogue. This is smaller than the 204,800-token context listed for the coding-oriented M2 line.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-her. Treat the public $0.3/M input and $1.2/M output rates as the default unless your account has a negotiated enterprise agreement.Q · 06 When was this price last checked? +
This page was verified against MiniMax's official pay-as-you-go pricing page on
May 23, 2026. The same page currently lists the active text rows for M2.7, M2.5, M2.1, M2, and M2-her.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.