Model catalogue

MiniMax
MiniMax M2.5
minimax/minimax-m2.5
Specification
Published by the vendor; the platform bills at the target's declared price.
MiniMax M2.5
reasoning open weights toolsMiniMax 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...
- Input $/1M
- $0.27
- Output $/1M
- $1.08
- Context
- 205K
- Max output
- 128K
- Released
- Feb 12, 2026
- Modalities
- text
Cached input reads $0.03 per 1M · weights on Hugging Face as MiniMaxAI/MiniMax-M2.5
On this deployment
No routing target resolves to this model yet. Declare one and the router picks it up without retraining.
Not routable here yet
Add a target with metadata.model set to this id.
targets.yamlyaml
# 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: 0.000675Price among MiniMax models
Input list price per million tokens; MiniMax M2.5 is the 5th cheapest of 11 listed.
- 1free
- 2free
- 3$0.20
- 4$0.26
- 5$0.27MiniMax M2.5
- 6$0.30
- 7$0.30
- 8$0.30
- 9$0.30
- 10$0.30
- 11$0.55
More from MiniMax
Other models by the same vendor in the catalogue.
- MiniMax M3May 31, 2026$0.30 in
- MiniMax M3 (batch)May 31, 2026$0.30 in
- MiniMax M3 (free)May 31, 2026free in
- MiniMax M2.7Mar 18, 2026$0.30 in
- MiniMax M2.7 (free)Mar 18, 2026free in
- MiniMax M2-herJan 23, 2026$0.30 in
- MiniMax M2.1Dec 23, 2025$0.30 in
- MiniMax M2Oct 23, 2025$0.26 in
- MiniMax M1Jun 17, 2025$0.55 in
- MiniMax-01Jan 15, 2025$0.20 in