MiniMax M3.1-Flash (Public Preview)
DigitalOcean
MiniMax M3.1-Flash (Public Preview) by DigitalOcean costs $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 1M-token context window.
Pricing
Input (per 1M tokens)
$0.15
Output (per 1M tokens)
$0.60
Cached input (per 1M)
$0.02
Specifications
- Provider
- DigitalOcean
- Context window
- 1M tokens
- Parameters
- —
- Released
- Oct 2026
- Open weights
- No
- Frontier model
- No
Compare MiniMax M3.1-Flash (Public Preview) with…
MiniMax M3.1-Flash (Public Preview) vs GPT OSS 120B$0.60/1MMiniMax M3.1-Flash (Public Preview) vs GPT-4o-mini$0.60/1MMiniMax M3.1-Flash (Public Preview) vs Command R (08-2024)$0.60/1MMiniMax M3.1-Flash (Public Preview) vs Gemma 4 26B A4B IT$0.60/1MMiniMax M3.1-Flash (Public Preview) vs Solar Pro 4$0.60/1MMiniMax M3.1-Flash (Public Preview) vs Mistral Small (latest)$0.60/1M
FAQ
How much does MiniMax M3.1-Flash (Public Preview) cost?
MiniMax M3.1-Flash (Public Preview) is priced at $0.15 per 1M input tokens and $0.60 per 1M output tokens. Output tokens cost more than input.
What is MiniMax M3.1-Flash (Public Preview)'s context window?
MiniMax M3.1-Flash (Public Preview) supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.
Is MiniMax M3.1-Flash (Public Preview) open weight?
No — MiniMax M3.1-Flash (Public Preview) is a closed/proprietary model accessed via API.
Data as of 2026-10-24. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.