Deep Infra
MiniMax-M3
MiniMaxAI/MiniMax-M3
Prices and limits
- Input price per 1M tokens
- $0.28
- Output price per 1M tokens
- $1.10
- Cached input per 1M tokens
- $0.056
- Blended price per 1M (our estimate)
- $0.485
- Context window
- 524,288
- Max output tokens
- 512,000
- Accepts
- TextImageVideo
- Produces
- Text
- Released
- Jun 1, 2026
- Last updated
- Jun 1, 2026
- Knowledge cutoff
- —
- Open weights
- Yes
Wrong price, or a provider that wants its listing corrected or removed? Email ceo@uniholix.com. We reply within 5 business days.
Cheapest comparable models
Other priced models that accept at least the same inputs, produce the same outputs and have at least half this context window, sorted by blended price.
- GLM-5.3-FlashPareto Inference$0.03 / $0.101M
- Qwen3.5 4BEmpirioLabs AI$0.04 / $0.07262.1K
- Qwen3.7 FlashAlibaba (China)$0.03 / $0.1191M
- Qwen3.5 9BCrofAI$0.04 / $0.15262.1K
- Space Bunny AlphaNanoGPT$0.05 / $0.151M
- Gemma 4 26B A4B ITKilo Gateway$0.042 / $0.22262.1K
- Ling 3.0 Flash VLNanoGPT$0.06 / $0.18262.1K
- Gemini-2.0-Flash-LitePoe$0.052 / $0.21990K
Same model at other providers
Matched by the catalogue’s model ID. Cheapest blended price first.
- MiniMax-M3Kenari$0.00 / $0.001M
- MiniMax-M3Vultr$0.20 / $0.90524.3K
- MiniMax M3EmpirioLabs AI$0.225 / $0.901M
- MiniMax M3CoreWeave$0.23 / $0.96262.1K
- MiniMax-M3Vancine$0.24 / $0.961M
- MiniMax M3Lilac$0.28 / $1.101M
- MiniMax-M3AIHubMix$0.288 / $1.151M
- MiniMax-M3IteraCompute$0.29 / $1.201M
- MiniMax LatestFireworks AI$0.30 / $1.20512K
- MiniMax M3Merge Gateway$0.30 / $1.201M
- MiniMax M3NanoGPT$0.30 / $1.20512K
- MiniMax M3Vercel AI Gateway$0.30 / $1.20512K
Price changes
Models whose price changed in the catalogue, newest first. We compare prices every day.
No price changes recorded yet. When a model’s price changes, it appears here.