OpenRouter
Catalog quote- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
minimaxListed May 31, 2026
MiniMax: MiniMax M3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Context window1M
Max output512K
Provider endpoints15
Benchmark results0
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Access & cost
15 quotesPrices across providers
Your token mix
USD · listed token rates- Input
- $0.224
- Output
- $0.88
- Cached input
- $0.0448
- Input
- $0.23
- Output
- $0.96
- Cached input
- $0.05
- Input
- $0.24
- Output
- $0.96
- Cached input
- $0.048
Source discount 20%; rates as published
- Input
- $0.28
- Output
- $1.10
- Cached input
- $0.056
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
Source discount 50%; rates as published
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
- Input
- $0.30
- Output
- $1.20
- Cached input
- $0.06
Max prompt 524288 tokens
- Input
- $0.30
- Output
- $1.30
- Cached input
- $0.05
- Input
- $0.60
- Output
- $2.40
- Input
- $0.60
- Output
- $2.40
- Cached input
- $0.06
Model specifications
- Developer
- minimax
- Modality
- Language
- Context
- 1,048,576 tokens
- Maximum output
- 512,000 tokens
- Weights
- Open weights
- Provider listed
- May 31, 2026
- First discovered
- Oct 16, 2026
More from minimax
View all ↗minimaxListed 1 day ago
MiniMax: MiniMax M3.1 Flash (free)
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It…
1M contextImage inputVideo inputNo reported score
No reported score
minimaxListed 4 days ago
H3 Max Reference Director
Direct a continuous world in real time with image references and text prompts.
No reported score
No reported score
minimaxListed Sep 3
H3 Max Director
Direct continuous, realtime video streams with live prompts while preserving characters, settings, and story continuity.
No reported score
No reported score
Price not listed
minimaxListed Aug 10
MiniMax H3 Reference to Video LoRA Trainer
Train a MiniMax H3 LoRA with reference conditioning, so different modalities animate into video with audio; captions optional.
No reported score
No reported score
Price not listed