MiniMax M2.5
MiniMax M2.5 is MiniMax's language model with a 1.0M context window and up to 131K output tokens, available from 11 providers, starting at $0.27 / 1M input and $1.08 / 1M output. MiniMax's M2.5 generation MoE language model offering strong reasoning and tool-use performance for complex productivity and agent tasks.
| Benchmarks | |
|---|---|
| Intelligence Index | #98 |
| GPQA | #95 |
| HLE | #118 |
| IFBench | #52 |
| Time to First Token | #435 |
| SciCode | #97 |
| LCR | #72 |
| TerminalBench Hard | #71 |
| TAU2 | #27 |
| Output TPS | #129 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Flex | Fast | Batch | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Cache Write 5m $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.3 | $1.20 | N/A | N/A | $0.15 | $0.6 | $0.525 | $2.10 | $0.15 | $0.6 | |
| $0.33 | $1.32 | $0.033 | N/A | — | — | — | — | — | — | |
| $0.3 | $1.20 | N/A | N/A | — | — | — | — | — | — | |
| $0.3 | $1.20 | N/A | N/A | — | — | — | — | — | — | |
| $0.3 | $1.20 | $0.03 | $0.375 | — | — | — | — | — | — | |
| $0.3 | $1.20 | N/A | N/A | — | — | — | — | — | — | |
| $0.3 | $1.20 | $0.03 | N/A | — | — | — | — | — | — | |
| $0.27 | $1.08 | $0.027 | N/A | — | — | — | — | — | — | |
| $0.3 | $1.20 | N/A | N/A | — | — | — | — | — | — | |
| $0.3 | $1.20 | $0.03 | $0.375 | — | — | — | — | — | — | |
| $0.3 | $1.20 | N/A | N/A | — | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host MiniMax M2.5, ranked by cheapest on-demand price. The model needs about 549 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| p4de.24xlarge |  AWS | 8× A100 | 640 GB | $27.45/hr | ||
| Standard_ND96amsr_A100_v4 |  Azure | 8× NVIDIA A100 (80GB) | 640 GB | $32.77/hr | ||
| g7e.48xlarge | AWS | 8× RTX PRO Server 6000 | 768 GB | $33.14/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MiniMax M2.7 | 1.0M | $0.250 | $0.550 | Available | |
| MiniMax M2.5 | 1.0M | $0.270 | $1.08 | Current | |
| MiniMax M2.1 | 1.0M | $0.300 | $1.20 | Available |