MiniMax-Text-01
MiniMax-Text-01 is a powerful language model with 456 billion total parameters, of which 45.9 billion are activated per token. To better unlock the long context capabilities of the model, MiniMax-Text-01 adopts a hybrid architecture that combines Lightning Attention, Softmax Attention and Mixture-of-Experts (MoE). Leveraging advanced parallel strategies and innovative compute-communication overlap methods—such as Lin...
Params
456.1 B
Context
10,240,000
Downloads 30d
3 K
Likes
657
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)3 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 914.7 GB | 1,075.1 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 10000K ctx | 914.7 GB | 86,523.5 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/minimax-text-01
{
"hf_id": "MiniMaxAI/MiniMax-Text-01",
"params_b": 456.09,
"context_length": 10240000,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 2675,
"vram_estimates": [
{ "quant": "bf16", "gb": 1075.1 }
],
"updated_at": "2026-10-19T06:01:22Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.20
input / 1M
$1.10
output / 1M
—
cached input / 1M
$1.30
1M in + 1M out
- Context window
- 1,000,192 tokens
- Max output
- 900,172 tokens
- Providers
- 1
- Cheapest provider
- Minimax · $0.20 / $1.10
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✗ Tool calling
✗ Reasoning
✗ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- MiniMaxText01ForCausalLM
- Parameters
- 456.1 B
- Tensor type
- BF16
- Context length
- 10,240,000
- Vocabulary
- 200,064
- Layers / heads
- 80 / 64
- First seen on the Hub
- 2025-01-12
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model