MiniMax-01
MiniMaxhuggingface.co/MiniMaxAI/MiniMax-Text-01
MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...
Updated 34 min ago · first seen 11 Sept 2026
model_01M294WWKYTBHEWJB8GCXGMPFV
- Parameters
- 456.1B
- T2 · 3 h ago
- Context
- 1M tokens
- T2 · 3 h ago
- Released
- 12 Jan 2025
- T2 · 34 min ago
- Knowledge cutoff
- Mar 2024
- T2 · 3 h ago
Specification
- Release date
- 12 Jan 2025
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 34 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Architecture
- MiniMaxText01ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 456.1B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Context window
- 1M tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 900.2K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Knowledge cutoff
- Mar 2024
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Input modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- File size
- 914.7 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- MiniMaxAI/MiniMax-Text-01
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads
- 3,446
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 34 min agomedium
- Likes
- 657
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 34 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2025-07-03T05:13:03+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads all time
- 87,750
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 34 min agomedium
- Model type
- minimax_text_01
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openrouter id
- minimax/minimax-01
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Supported parameters
- max_tokens, temperature, top_p
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Tags
- safetensors, minimax_text_01, text-generation, custom_code
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- BF16, F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
28
Source tiers
T228
Freshest observation
34 min ago
Conflicts
None
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- text
Capabilities
Tool calling
No
OpenRouter public model & pricing listing · T2
Structured output
No
OpenRouter public model & pricing listing · T2
Reasoning
Unavailable
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 1M tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 900.2K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Knowledge cutoff
- Mar 2024
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| MiniMax APIminimax/minimax-01 | $0.20 | $1.1 | — | — | 1M | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- MiniMax API
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 262.8 GB | Yes |
| Apple M3 Ultra | 4bit | — | 262.8 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 262.8 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 262.8 GB | No |
| AMD Instinct MI300X | 4bit | 192 GB | 262.8 GB | No |
| Apple M2 Ultra | 4bit | — | 262.8 GB | No |
| NVIDIA B200 | 4bit | 180 GB | 262.8 GB | No |
| NVIDIA H200 | 4bit | 141 GB | 262.8 GB | No |
| NVIDIA H200 NVL | 4bit | 141 GB | 262.8 GB | No |
| Apple M1 Ultra | 4bit | — | 262.8 GB | No |
| Apple M3 Max | 4bit | — | 262.8 GB | No |
| Apple M4 Max | 4bit | — | 262.8 GB | No |
| Mac Studio (Apple M5 Max) | 4bit | — | 262.8 GB | No |
| MacBook Pro (Apple M5 Max) | 4bit | — | 262.8 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 262.8 GB | No |
| Apple M2 Max | 4bit | — | 262.8 GB | No |
| NVIDIA H100 NVL | 4bit | 94 GB | 262.8 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 262.8 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 262.8 GB | No |
| Apple M1 Max | 4bit | — | 262.8 GB | No |
| Apple M4 Pro | 4bit | — | 262.8 GB | No |
| Mac mini (Apple M5 Pro) | 4bit | — | 262.8 GB | No |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 262.8 GB | No |
| Apple M3 Pro | 4bit | — | 262.8 GB | No |
| Apple M1 Pro | 4bit | — | 262.8 GB | No |
| Apple M2 Pro | 4bit | — | 262.8 GB | No |
| Apple M4 | 4bit | — | 262.8 GB | No |
| iMac (Apple M4) | 4bit | — | 262.8 GB | No |
| Mac mini (Apple M6) | 4bit | — | 262.8 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 262.8 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 262.8 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 262.8 GB | No |
| Apple M2 | 4bit | — | 262.8 GB | No |
| Apple M3 | 4bit | — | 262.8 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 262.8 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 262.8 GB | No |
| Apple M1 | 4bit | — | 262.8 GB | No |
No lineage recorded
Papers 1
- arXiv:2501.08313Active35
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Pipeline tag
Pipeline tagpipeline_tag1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text-generation | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
MiniMax-01: release date changed from 2025-01-12 to 2025-01-15
Release date12 Jan 2025→15 Jan 2025openrouterMiniMax-01: release date changed from 2025-01-15 to 2025-01-12
Release date15 Jan 2025→12 Jan 2025huggingfaceMiniMax API lists MiniMax-01 at $0.2 in / $1.1 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/MiniMaxAI/MiniMax-Text-01 | model_page | T2· Quality secondary | 34 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=MiniMaxAI&p=0&sort=downloads | listing | T2· Quality secondary | 58 min ago | 3 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/MiniMaxAI/MiniMax-Text-01/raw/main/README.md | model_card | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.