minimax
MiniMax M2-her vs MiniMax M3
67.3 overall · $0.525 / 1M
// minimax
MiniMax M2-her
minimax/minimax-m2-her
prompt caching
MiniMax M2-her costs $0.300 per 1M input tokens and $1.20 per 1M output tokens with a 66K-token context window.
A model from minimax, released Jan 23, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.300
- Output / 1M
- $1.20
- Context
- 66K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.300 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $1.20 |
| Blended price 3:1 input:output — #141 cheapest of 343 listed models | $0.525 |
| Cached input read Blank means not priced separately — not free | $0.030 |
| Cache write | — |
| Context window | 65,536 tokens |
| Max output | 2,048 tokens |
| Input modalities | text |
| Tool calling | No |
| Extended reasoning | No |
| Knowledge cutoff | — |
| Listed | Jan 23, 2026 |
What MiniMax M2-her costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $148.56/mo |
| RAG assistant 8K in / 600 out × 100K requests | $204.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $184.80/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $376.50/mo |
| Bulk classification 500 in / 20 out × 5M requests | $735.00/mo |
Compare MiniMax M2-her with
Benchmarked models at a similar price.
openai
MiniMax M2-her vs GPT-5.4 Nano
69.6 overall · $0.463 / 1M
openai
MiniMax M2-her vs GPT-5.6 Luna
73.6 overall · $0.450 / 1M
qwen
MiniMax M2-her vs Qwen3.6 Plus
68.9 overall · $0.731 / 1M
deepseek
MiniMax M2-her vs DeepSeek V4 Flash Vision Exp
76.8 overall · $0.330 / 1M
MiniMax M2-her vs Gemini 3.5 Flash Lite
63.9 overall · $0.850 / 1M
MiniMax M2-her FAQ
How much does MiniMax M2-her cost?
MiniMax M2-her lists at $0.300 per 1M input tokens and $1.20 per 1M output tokens, with cached input reads at $0.030 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $204.00 at list price.
What is the context window of MiniMax M2-her?
MiniMax M2-her accepts up to 65,536 tokens of context and can return up to 2,048 output tokens per response.
Does MiniMax M2-her support tool calling?
MiniMax M2-her does not list tool (function) calling support. It accepts text input.
How does MiniMax M2-her score on benchmarks?
LiveBench has not published a run for MiniMax M2-her yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for MiniMax M2-her?
On OpenRouter the model ID is "minimax/minimax-m2-her". It was listed on Jan 23, 2026.
More from minimax
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.