MiniMax M2 Models by MiniMax
13 models2024–2026Up to 240K ctxFrom $0.15/1M input
About
MiniMax M2 is a family of 13 AI models by MiniMax, released between 2024 and 2026.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
13 in view
MiniMax M2.7Current
Use when the workload needs 205K context, reasoning, and tool use.
2026-03205K contextreasoningtool use
MiniMax M2.7 HighspeedCurrent
Use when the workload needs 205K context, reasoning, and tool use.
2026-03205K contextreasoningtool use
Together MiniMax M2.5Current
Use when the workload needs 200K context and 228.7B parameters.
2026-02200K context228.7B parameters
MiniMax M2.5 HighspeedCurrent
Use when the workload needs 205K context, reasoning, and tool use.
2026-02205K contextreasoningtool use
MiniMax M2.1Current
Use when the workload needs 200K context and structured outputs.
2025-12200K contextstructured outputs
MiniMax M2Current
Use when the workload needs 197K context and structured outputs.
2025-10197K contextstructured outputs
MiniMax M2.5Current
Use when the workload needs 197K context and structured outputs.
2025-03197K contextstructured outputs
MiniMax-M2-80kCurrent
Use when the workload needs 80K context and 80B parameters.
2025-0180K context80B parameters
MiniMax-M2-240kCurrent
Use when the workload needs 240K context and 240B parameters.
2025-01240K context240B parameters
MiniMax-M2-80k-0905Current
Use when the workload needs 80K context and 80B parameters.
2025-0180K context80B parameters
MiniMax-M2-240k-0905Current
Use when the workload needs 240K context and 240B parameters.
2025-01240K context240B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| MiniMax M2.7 | Use when the workload needs 205K context, reasoning, and tool use. | 2026-03 | 205K contextreasoningtool use | Current |
| MiniMax M2.7 Highspeed | Use when the workload needs 205K context, reasoning, and tool use. | 2026-03 | 205K contextreasoningtool use | Current |
| MiniMax M2-her | Use when the workload needs 64K context. | 2026-03 | 64K context | Current |
| Together MiniMax M2.5 | Use when the workload needs 200K context and 228.7B parameters. | 2026-02 | 200K context228.7B parameters | Current |
| MiniMax M2.5 Highspeed | Use when the workload needs 205K context, reasoning, and tool use. | 2026-02 | 205K contextreasoningtool use | Current |
| MiniMax M2.1 | Use when the workload needs 200K context and structured outputs. | 2025-12 | 200K contextstructured outputs | Current |
| MiniMax M2 | Use when the workload needs 197K context and structured outputs. | 2025-10 | 197K contextstructured outputs | Current |
| MiniMax M2.5 | Use when the workload needs 197K context and structured outputs. | 2025-03 | 197K contextstructured outputs | Current |
| MiniMax-M2-80k | Use when the workload needs 80K context and 80B parameters. | 2025-01 | 80K context80B parameters | Current |
| MiniMax-M2-240k | Use when the workload needs 240K context and 240B parameters. | 2025-01 | 240K context240B parameters | Current |
| MiniMax-M2-80k-0905 | Use when the workload needs 80K context and 80B parameters. | 2025-01 | 80K context80B parameters | Current |
| MiniMax-M2-240k-0905 | Use when the workload needs 240K context and 240B parameters. | 2025-01 | 240K context240B parameters | Current |
| MiniMax-M2.5 | Use when provider availability and model metadata match the workload. | 2024-09 | — | Current |
Release Timeline
7 release groups2026-03
3 current
MiniMax M2-her
Current64K context
MiniMax M2.7
Current205K contextreasoningtool use
MiniMax M2.7 Highspeed
Current205K contextreasoningtool use
2026-02
2 current
MiniMax M2.5 Highspeed
Current205K contextreasoningtool use
Together MiniMax M2.5
Current200K context228.7B parameters
2025-12
1 current
MiniMax M2.1
Current200K contextstructured outputs
2025-10
1 current
MiniMax M2
Current197K contextstructured outputs
2025-03
1 current
MiniMax M2.5
Current197K contextstructured outputs
2025-01
4 current
MiniMax-M2-240k
Current240K context240B parameters
MiniMax-M2-240k-0905
Current240K context240B parameters
MiniMax-M2-80k
Current80K context80B parameters
MiniMax-M2-80k-0905
Current80K context80B parameters
2024-09
1 current
Current
Specifications(13 models)
| Model | Released | Context | Parameters | Reasoning | Fn Calling | Tool Use | Structured Outputs |
|---|---|---|---|---|---|---|---|
| MiniMax M2.7 | 2026-03 | 205K | 10B active | Yes | Yes | Yes | Yes |
| MiniMax M2.7 Highspeed | 2026-03 | 205K | 10B active | Yes | Yes | Yes | Yes |
| MiniMax M2-her | 2026-03 | 64K | — | No | No | No | No |
| Together MiniMax M2.5 | 2026-02 | 200k | 228.7B | No | No | No | No |
| MiniMax M2.5 Highspeed | 2026-02 | 205K | — | Yes | Yes | Yes | Yes |
| MiniMax M2.1 | 2025-12 | 200k | — | No | No | No | Yes |
| MiniMax M2 | 2025-10 | 197K | — | No | No | No | Yes |
| MiniMax M2.5 | 2025-03 | 197K | — | No | No | No | Yes |
| MiniMax-M2-80k | 2025-01 | 80K | 80B | No | No | No | No |
| MiniMax-M2-240k | 2025-01 | 240K | 240B | No | No | No | No |
| MiniMax-M2-80k-0905 | 2025-01 | 80K | 80B | No | No | No | No |
| MiniMax-M2-240k-0905 | 2025-01 | 240K | 240B | No | No | No | No |
| MiniMax-M2.5 | 2024-09 | — | — | No | No | No | No |
Available From(7 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| MiniMax M2.5 | OpenRouter | $0.15 | $1.15 | Serverless |
| MiniMax M2 | OpenRouter | $0.255 | $1 | Serverless |
| MiniMax M2.1 | OpenRouter | $0.29 | $0.95 | Serverless |
| MiniMax-M2-240k | Fireworks AI | $0.3 | $1.2 | Serverless |
| MiniMax-M2-80k-0905 | Fireworks AI | $0.3 | $1.2 | Serverless |
| MiniMax-M2-240k-0905 | Fireworks AI | $0.3 | $1.2 | Serverless |
| MiniMax-M2.5 | Fireworks AI | $0.3 | $1.2 | Serverless |
| MiniMax M2.5 | Together AI | $0.3 | $1.2 | Serverless |
| MiniMax M2.1 | AWS Bedrock | $0.3 | $1.2 | Serverless |
| MiniMax M2.7 | OpenRouter | $0.3 | $1.2 | Serverless |
| MiniMax M2.7 | Fireworks AI | $0.3 | $1.2 | Serverless |
| MiniMax M2 | AWS Bedrock | $0.4 | $1.6 | Serverless |
| MiniMax M2.5 Highspeed | Novita AI | $0.6 | $2.4 | Serverless |
| MiniMax-M2-80k | Fireworks AI | $0.9 | $0.9 | Serverless |
| MiniMax M2 | Fireworks AI | $0.9 | $0.9 | Serverless |
Frequently Asked Questions
- What is MiniMax M2 used for?
- MiniMax M2 is used for reasoning, agent workflows and tool use, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does MiniMax M2 compare to MiniMax Speech?
- MiniMax M2 by MiniMax is strongest where you need reasoning, while MiniMax Speech by MiniMax is the closest related family to check for adjacent model selection. MiniMax M2 has 13 listed variants and reaches up to 240K context, so compare the specs and pricing tables before choosing a production model.
- Which MiniMax M2 model should I use?
- For the lowest listed input price, start with MiniMax M2.5 through OpenRouter at $0.15/1M input tokens. For the most capable/latest local choice, evaluate MiniMax M2.7 with 205K context and reasoning, tool use, function calling, and structured outputs.
Related Model Families
Models(13)
MiniMax M2.7
2026-03205K10B active2 providers
Reasoning
MiniMax M2.7 Highspeed
2026-03205K10B active1 provider
Reasoning
MiniMax M2-her
2026-0364K
Together MiniMax M2.5
2026-02200k228.7B
MiniMax M2.5 Highspeed
2026-02205K2 providers
Reasoning
MiniMax M2.1
2025-12200k2 providers
MiniMax M2
2025-10197K3 providers
MiniMax M2.5
2025-03197K3 providers
MiniMax-M2-80k
2025-0180K80B1 provider
MiniMax-M2-240k
2025-01240K240B1 provider
MiniMax-M2-80k-0905
2025-0180K80B1 provider
MiniMax-M2-240k-0905
2025-01240K240B1 provider
MiniMax-M2.5
2024-091 provider