DeepSeek-V3 vs MiniMax-Text-01

Specs, VRAM requirements and download trends — updated 25 October 2026.

deepseek-ai · A · Open weights
Params
684.5 B
Context
163,840
30d
1.4 M
MiniMaxAI · B · Open weights
Params
456.1 B
Context
10,240,000
30d
3 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification DeepSeek-V3 MiniMax-Text-01
Deployment Open weights · also via API Open weights · also via API
Parameters 684.5 B 456.1 B
Architecture DeepseekV3ForCausalLM MiniMaxText01ForCausalLM
Context length 163,840 10,240,000
Licence — —
Commercial use Unknown Unknown
Languages — —
Downloads 30d 1,420,996 2,675
Downloads all time 22.6 M 92 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-12-25 2025-01-12
API input price / 1M tokens $0.26 $0.20
API output price / 1M tokens $1.03 $1.10
Est. cost per 1M input + 1M output tokens $1.29 $1.30
Cached input / 1M tokens — —
AA Intelligence Index — —
AA Coding Index — —
AA Agentic Index — —
Max output tokens 16,000 900,172
API providers 2 1
Tool calling Yes No
Reasoning mode No No

API cost

Estimated cost of 1M input + 1M output tokens via OpenRouter

DeepSeek-V3 $1.29
MiniMax-Text-01 $1.30

DeepSeek-V3 is 1.0× cheaper at list price.

Download trend

Daily snapshots, last 90 days (28 Jul – 25 Oct)

1.5 M3 K
DeepSeek-V3 MiniMax-Text-01

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

DeepSeek-V3 · fp16 @ 160K ctx 2,811.5 GB / 24 GB
❌ Won’t fit
MiniMax-Text-01 · fp16 @ 10000K ctx 86,523.5 GB / 24 GB
❌ Won’t fit

Adjacent comparisons