Modular
MiniMax-M3.1-Flash
Canonical ID:
modular/MiniMaxAI/MiniMax-M3.1-Flash
Frontier multimodal coding model with 1M context window and tunable thinking depth
Overview
Pricing and Limits
Token pricing
- Input
- $0.15/1M
- Output
- $0.6/1M
- Cached input
- N/A
Context and output
- Context window
- 1,048,576
- Max output tokens
- 512,000
- Qualified ID
- modular/MiniMaxAI/MiniMax-M3.1-Flash
Model Summary
MiniMax-M3.1-Flash is a model listing in the Modular provider catalog. It is categorized under the minimax family.
The model supports text, image, video modalities across input/output paths. Reported context capacity is 1,048,576. Pricing is listed at $0.15/1M input and $0.6/1M output.
More From Modular
Related models from the same provider catalog.
DeepSeek V4.1 Flash
modular/deepseek/deepseek-v4.1-flash
Gemma 4 31B IT
modular/google/gemma-4-31b-it
MiniMax-M3
modular/minimax/minimax-m3
Same Family: minimax
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
Coding MiniMax M2.7
aihubmix/coding-minimax-m2.7
|
|
204,800 | $0.2/1M | $0.2/1M |
Reasoning
Tools
|
|
Coding MiniMax M2.7 (Free)
aihubmix/coding-minimax-m2.7-free
|
|
204,800 | $0/1M | $0/1M |
Reasoning
Tools
|
|
Coding MiniMax M2.7 Highspeed
aihubmix/coding-minimax-m2.7-highspeed
|
|
204,800 | $0.2/1M | $0.2/1M |
Reasoning
Tools
|
|
MiniMax 01
nano-gpt/minimax/minimax-01
|
|
1,000,192 | $0.1394/1M | $1.122/1M |
|
|
MiniMaxAI/MiniMax-M2.5
siliconflow/MiniMaxAI/MiniMax-M2.5
|
|
197,000 | $0.3/1M | $1.2/1M |
Tools
|
|
MiniMax H3
vercel/minimax/minimax-h3
|
|
0 | N/A | N/A |
|
|
MiniMax H3 Max
vercel/minimax/minimax-h3-max
|
|
0 | N/A | N/A |
|
|
MiniMax Latest
fireworks-ai/accounts/fireworks/routers/minimax-latest
|
|
512,000 | $0.3/1M | $1.2/1M |
Reasoning
Tools
|
|
MiniMax Latest
nano-gpt/minimax/minimax-latest
|
|
512,000 | $0.23/1M | $0.96/1M |
Reasoning
Tools
|
|
MiniMax M1
qiniu-ai/MiniMax-M1
|
|
1,000,000 | $0.57971/1M | $2.318841/1M |
Reasoning
Tools
|