Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
MiniMax
minimax/minimax-m2.5Catalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
MiniMax minimax/minimax-m2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
MiniMax M2.5 earns a request when it needs step-by-step reasoning, tool calls, very long inputs; a short, general request would go to GLM 5.2 instead - $0.01 per million input tokens against $0.30 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs MiniMax M2.5
targets:
- id: minimax-m2-5
kind: llm
name: MiniMax M2.5
metadata:
model: minimax/minimax-m2.5 # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 204800
cost:
usd_per_1k_tokens: 0.000750Input list price per million tokens; MiniMax M2.5 is the 4th cheapest of 9 listed.
Other models by the same vendor in the catalogue.
Photo: RDNE Stock project
Cached input reads $0.03 per 1M · weights on Hugging Face as MiniMaxAI/MiniMax-M2.5
A higher intelligence index, best first, with the price it comes at.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
