MiniMax
MiniMax-M2.5-highspeed
Tool callingReasoning
High-speed MiniMax model for low-latency coding and agent workflows
- Context
- 205K
- Released
- 8mo ago
- Parameters
- —
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- MiniMax
- Model family
- MiniMax
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- February 13, 2026
- Model ID
minimax/MiniMax-M2.5-highspeed- Openness
- Open weights
- License
- —
- Parameters
- —
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Max output tokens
- 131K
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- minimax/MiniMax-M2.5-highspeed
- Source family
- minimax
- Last updated
- 2026-02-13
- Model context
- 205K
- Model output limit
- 131K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Complete source record (JSON)
{
"id": "minimax/MiniMax-M2.5-highspeed",
"name": "MiniMax-M2.5-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"family": "minimax",
"last_updated": "2026-02-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"release_date": "2026-02-13",
"open_weights": true,
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.5"
}
]
}Infrastructure
Provider availability
Provider endpoint data will appear after this model's first OpenRouter endpoint sync.
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.