AI Model Intelligence

MiniMax-M2.5

minimax/m2-5

By MiniMax · family: minimax · released 2026-02-12 · knowledge: 2025-01

$0.300
Input / 1M tokens
$1.20
Output / 1M tokens
205K
Context window
131K
Max output

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Capabilities

✓ Tool calling✓ Reasoning? Structured output✗ Attachments✓ Open weights✓ Temperature control
Modalities: input text · output text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding66
  • Tool calling40/40
  • Structured output0/20
  • Reasoning10/10
  • Context window (100K → 1M)6/20
  • Provider availability10/10
Agents75
  • Tool calling35/35
  • Structured output0/25
  • Reasoning15/15
  • Output token limit15/15
  • Provider availability10/10
JSON / structured output47
  • Structured output / JSON mode0/50
  • Tool calling20/20
  • Temperature control10/10
  • Price-friendly for high-volume17/20
Cost efficiency63
  • Headline price (log-scaled)58/95
  • Has prompt-cache pricing5/5
Long context56
  • Context window (100K → 2M)46/90
  • Has published price for full window10/10
Production-readiness96
  • Number of independent providers40/40
  • Has published per-token price20/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers6/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$2.10
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$4.20
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$1.20
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$3.60
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$4.32
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Pricing detail

Recommended pricing from minimax · MiniMax-M2.5

$0.300
Input
$1.20
Output
$0.030
Cache read
$0.375
Cache write

Cheapest provider: minimax-coding-plan · Unknown input + Unknown output

Available on 40 providers

ProviderProvider model idInput / 1MOutput / 1MContextReleased
MiniMax (minimax.io)
minimax
MiniMax-M2.5$0.300$1.20205K2026-02-12
MiniMax Coding Plan (minimax.io)
minimax-coding-plan
MiniMax-M2.5UnknownUnknown205K2026-02-12
MiniMax Coding Plan (minimaxi.com)
minimax-cn-coding-plan
MiniMax-M2.5UnknownUnknown205K2026-02-12
MiniMax (minimaxi.com)
minimax-cn
MiniMax-M2.5$0.300$1.20205K2026-02-12
OpenRouter
openrouter
minimax/minimax-m2.5$0.300$1.20205K2026-02-12
Vercel AI Gateway
vercel
minimax/minimax-m2.5$0.300$1.20205K2026-02-12
Together AI
togetherai
MiniMaxAI/MiniMax-M2.5$0.300$1.20205K2026-02-12
Deep Infra
deepinfra
MiniMaxAI/MiniMax-M2.5$0.270$0.950205K2026-02-12
Hugging Face
huggingface
MiniMaxAI/MiniMax-M2.5$0.300$1.20205K2026-02-12
NanoGPT
nano-gpt
minimax/minimax-m2.5$0.300$1.20205K2026-02-12
SiliconFlow (China)
siliconflow-cn
Pro/MiniMaxAI/MiniMax-M2.5$0.300$1.22192K2026-02-13
OpenCode Go
opencode-go
minimax-m2.5$0.300$1.20205K2026-02-12
Alibaba (China)
alibaba-cn
MiniMax-M2.5$0.300$1.20205K2026-02-12
ZenMux
zenmux
minimax/minimax-m2.5$0.300$1.20205K2026-02-13
NovitaAI
novita-ai
minimax/minimax-m2.5$0.300$1.20205K2026-02-12
Weights & Biases
wandb
MiniMaxAI/MiniMax-M2.5$0.300$1.20197K2026-02-12
DInference
dinference
minimax-m2.5$0.220$0.880200K2026-02-12
Qiniu
qiniu-ai
minimax/minimax-m2.5UnknownUnknown205K2026-02-12
Kilo Gateway
kilo
minimax/minimax-m2.5$0.250$1.20197K2026-02-12
OpenCode Zen
opencode
minimax-m2.5$0.300$1.20205K2026-02-12
Nebius Token Factory
nebius
MiniMaxAI/MiniMax-M2.5$0.300$1.20197K2025-01-20
Ollama Cloud
ollama-cloud
minimax-m2.5UnknownUnknown205K2026-02-12
Baseten
baseten
MiniMaxAI/MiniMax-M2.5$0.300$1.20204K2026-02-12
FrogBot
frogbot
minimax-m2-5$0.300$1.20192K2025-01-15
Alibaba Coding Plan
alibaba-coding-plan
MiniMax-M2.5UnknownUnknown197K2026-02-12
CloudFerro Sherlock
cloudferro-sherlock
MiniMaxAI/MiniMax-M2.5$0.300$1.20196K2026-03-05
Meganova
meganova
MiniMaxAI/MiniMax-M2.5$0.300$1.20205K2026-02-12
Synthetic
synthetic
hf:MiniMaxAI/MiniMax-M2.5$0.600$3.00191K2026-02-07
Nvidia
nvidia
minimaxai/minimax-m2.5UnknownUnknown205K2026-02-12
DigitalOcean
digitalocean
minimax-m2.5$0.300$1.20205K2026-02-12
Vultr
vultr
MiniMax-M2.5$0.300$1.20194K2025-02-11
Alibaba Coding Plan (China)
alibaba-coding-plan-cn
MiniMax-M2.5UnknownUnknown197K2026-02-12
Friendli
friendli
MiniMaxAI/MiniMax-M2.5$0.300$1.20197K2026-02-12
Cortecs
cortecs
minimax-m2.5$0.320$1.18197K2026-02-12
SiliconFlow
siliconflow
MiniMaxAI/MiniMax-M2.5$0.300$1.20197K2026-02-15
LLM Gateway
llmgateway
minimax-m2.5$0.300$1.20205K2026-02-12
Tencent Coding Plan (China)
tencent-coding-plan
minimax-m2.5UnknownUnknown205K2026-02-12
Neuralwatt
neuralwatt
MiniMaxAI/MiniMax-M2.5$0.350$1.38197K2026-02-12
HPC-AI
hpc-ai
minimax/minimax-m2.5$0.140$0.5601M2026-02-12
Regolo AI
regolo-ai
minimax-m2.5$0.800$3.50190K2026-03-10

Data inconsistencies across providers

  • context_window varies: 1000000, 190000, 191488, 192000, 194000, 196000, 196608, 197000, 200000, 204000, 204800
  • release_date varies (span 419d): 2025-01-15, 2025-01-20, 2025-02-11, 2026-02-07, 2026-02-12, 2026-02-13, 2026-02-15, 2026-03-05, 2026-03-10

Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.

Frequently asked questions

How much does MiniMax-M2.5 cost?

MiniMax-M2.5 costs $0.300 per 1M input tokens and $1.20 per 1M output tokens, sourced from minimax. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of MiniMax-M2.5?

MiniMax-M2.5 has a context window of 205K tokens, with a max output of 131K tokens per reply. This is the total combined size of prompt + completion.

Does MiniMax-M2.5 support tool calling?

Yes. MiniMax-M2.5 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Does MiniMax-M2.5 support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for MiniMax-M2.5 in our data source. Verify with MiniMax's official documentation before relying on it in production.

Can MiniMax-M2.5 accept image input?

No. MiniMax-M2.5 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.

Is MiniMax-M2.5 open-weight?

Yes. MiniMax-M2.5's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.

What are the best alternatives to MiniMax-M2.5?

If MiniMax-M2.5 doesn't fit, consider MiniMax-M2.1, MiniMax-M2.7, MiniMax-M2. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

More MiniMax models

Capability lists this model is in

See also

Last updated:

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.