Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | minimaxMiniMax: MiniMax M2.5Remove × | minimaxMiniMax: MiniMax M2.1Remove × | MiniMaxAIMiniMax-M3Remove × |
|---|---|---|---|
| What’s different | 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-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a… | MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters. |
| Date | Feb 12, 2026Listed | Dec 23, 2025Listed | Jun 1, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.27 in / $0.95 out/ 1M tokensVenice · via OpenRouter · all routes ↗venice | $0.30 in / $1.20 out/ 1M tokensMinimax · via OpenRouter · all routes ↗minimax/fp8 · quantization=fp8 | $0.28 in / $1.10 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ |
| Provider endpoints | 12 endpoints → | 3 endpoints → | 7 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Intelligence ↗4.3.2 | Not reported | Not reported | 29.22 ↗Effort not specifiedIndependent result |
| AA-Briefcase ↗1.1 | Not reported | Not reported | 1,090.37 ↗Effort not specifiedIndependent result |
| GDPval-AA ↗2.1 | Not reported | Not reported | 1,242.47 ↗Effort not specifiedIndependent result |
| AutomationBench-AA ↗AA Index 4.3.2 collection | Not reported | Not reported | 21.25% ↗Effort not specifiedIndependent result |
| Terminal-Bench 4.0 · AA ↗ | Not reported | Not reported | 2.02% ↗Effort not specifiedHarness unreportedIndependent result |
| SciCode ↗AA Index 4.3.2 collection | Not reported | Not reported | 47.11% ↗AA · Under reviewEffort not specifiedIndependent result |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | Not reported | Not reported | 38.97% ↗Effort not specifiedIndependent result |
| GDP.pdf ↗AA Index 4.3.2 collection | Not reported | Not reported | 9.8% ↗Effort not specifiedIndependent result |
| CritPt ↗AA Index 4.3.2 collection | Not reported | Not reported | 3.71% ↗AA · Under reviewEffort not specifiedIndependent result |
| AA-Omniscience ↗AA Index 4.3.2 collection | Not reported | Not reported | 1.35 ↗Effort not specifiedIndependent result |
| AA-LCR ↗1.1 | Not reported | Not reported | 83% ↗Effort not specifiedIndependent result |
Specifications | |||
| Context window | 204.8K | 204.8K | 1M |
| Max output | 32.8K | 131.1K | — |
| Parameters | — | — | — |
| Tool calling | Supported | Supported | Supported |
| Structured output | Supported | Supported | Supported |
| Image input | Not reported | Not reported | Supported |
| Reasoning | Supported | Supported | Supported |
| Prompt caching | Supported | Supported | Not reported |
| Open weights | Supported | Supported | Supported |