MiniMax
MiniMax-M2.1
MiniMax-M2.1 from MiniMax: Earlier MiniMax agent model for practical coding and productivity tasks.
- Context
- 204.8K
- Max output
- 131.07K
- Input / 1M tokens
- $0.30
- Output / 1M tokens
- $1.20
Accepts
- Text input
Produces
- Text output
AI model comparison
Compare pricing, context limits, supported inputs and deployment options to choose a model for your workflow.
MiniMax-M2.1 from MiniMax lists 204.8K context, 131.07K maximum output, $0.30 input per 1M tokens, $1.20 output per 1M tokens. MiniMax-M3 from MiniMax lists 1.05M context, 512K maximum output, $0.30 input per 1M tokens, $1.20 output per 1M tokens. Compare the inputs, outputs and deployment options below to see which fits your workflow.
MiniMax
MiniMax-M2.1 from MiniMax: Earlier MiniMax agent model for practical coding and productivity tasks.
Accepts
Produces
MiniMax
MiniMax-M3 from MiniMax: MiniMax multimodal model for long-context coding, perception, and agent planning.
Accepts
Produces
At a glance
Compare the available figures below, then try both models on the work you need to do.
MiniMax-M3
Context capacity
Higher listed limit
MiniMax-M2.1:204.8K
MiniMax-M3:1.05M
MiniMax-M3
Maximum output
Higher listed limit
MiniMax-M2.1:131.07K
MiniMax-M3:512K
MiniMax-M3
Input price
Lower listed token rate
MiniMax-M2.1:$0.30
MiniMax-M3:$0.30
Same value
Output price
Lower listed token rate
MiniMax-M2.1:$1.20
MiniMax-M3:$1.20
Same value
Specifications
| Specification | MiniMax-M2.1 | MiniMax-M3 |
|---|---|---|
| Provider | MiniMax | MiniMax |
| Listed pricing route | MiniMax | MiniMax |
| Model family | minimax | minimax |
| Accepted inputs | text | text, image, video |
| Produced outputs | text | text |
| Context window | 204.8K | 1.05MHigher |
| Max output | 131.07K | 512KHigher |
| Input price / 1M | $0.30 | $0.30 |
| Output price / 1M | $1.20 | $1.20 |
| Reasoning mode | Documented | Documented |
| Tool calling | Documented | Documented |
| Image input | Not documented | Documented |
| Audio input | Not documented | Not documented |
| Structured output | Not documented | Not documented |
| License | Open weights | Open weights |
Workload guidance
Consider MiniMax-M3 if you need larger context or larger maximum output. Test both on the same representative examples and judge the output against your acceptance criteria. Include tool failures, retries and the time to a completed task.
Explore each model’s features, API requirements and licence terms in the sources below.
MiniMax-M2.1
MiniMax
Profile updated Oct 13, 2026
Model card and weights ↗MiniMax-M3
MiniMax
Profile updated Oct 13, 2026
Model card and weights ↗Search by model or provider to explore another comparison.