All AI models · LLM benchmarks · Methodology

MiniMax

MiniMax-M2.5

MiniMax model for chat, coding, office work, and agentic tasks

Model facts

Context window
205K tokens
Maximum output
131K tokens
Cheapest paid input
$0.22 per 1M tokens
Cheapest paid output
$0.88 per 1M tokens
Open weights
yes
Providers
46

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 141.0 GiB, Q8_0 247.5 GiB, F16 447.1 GiB working memory.

Parameters
228.7 billion
Architecture
minimaxm2
Model license
other

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default34.5not measurednot measurednot measured

Observed price history

  • 2026-08-24: $0.22 input / $0.88 output per 1M tokens

API providers