MiniMax
MiniMax M2.5
MiniMax M2.5 is a MiniMax model with 1M context, Not verified in / Not verified out per million tokens, last verified September 3, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.
MiniMax M2.5 is the previous open-weight MiniMax MoE with a 1M-token context.
Catalog record checked September 3, 2026Individual provider fields may change
| Specification | MiniMax M2.5 |
|---|---|
| Provider | MiniMax |
| Tier | Balanced |
| Context window | 1M |
| Max output | Not verifiedUnverified |
| Input / 1M tokens | Not verifiedUnverified |
| Output / 1M tokens | Not verifiedUnverified |
| Weights | Open |
| Parameters | open MoE |
| Reasoning levels | low, high, max |
| Modalities | text, image, video |
| API model id | minimax-m2-5 |
| Released | February 20, 2026 |
Pricing tiers: Open (community license); hosted rates vary by provider.
Verified evidence
Published benchmark results
Each result keeps its source and measurement date visible. A missing benchmark is not treated as a zero.
| Benchmark | Score | Measured | Source |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 47 | 2026-08-14 | Artificial Analysis · View source |
Best for
- Open-weight deployments
- Multimodal
Watch out
Source receipts
Catalog figures for this model were checked against the following sources.
- MiniMax — M2.5 (accessed 2026-08-29)
- MiniMax (accessed 2026-08-29)
Common questions
MiniMax M2.5
Answered from the verified figures on this page rather than general guidance.
What is MiniMax M2.5's context window?
MiniMax M2.5 accepts about 1M tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is MiniMax M2.5 best for?
MiniMax M2.5 is a balanced tier from MiniMax. It suits open-weight deployments, multimodal. Verify pricing/weights on your endpoint.
Can I self-host MiniMax M2.5?
MiniMax M2.5 publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.