Model Library
MiniMaxReleased June 1, 2026MiniMax-M3
MiniMax · Released June 1, 2026
Intelligence score
44
At a glance
- Intelligence
- 44
- Speed
- 99.0tokens/sec
- Latency
- 1.81stime to first token
- Input price
- $0.30per 1M tokens
- Output price
- $1.20per 1M tokens
- Context window
- 3tokens
- Parameters
- 428billions
Summary
Comparison summary
MiniMax-M3 scores 44 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25). MiniMax-M3 generates output at 99.0 tokens per second (based on MiniMax's API), which is above average compared to other open weight models of similar size (median: 61.7 t/s). MiniMax-M3 costs $0.30 per 1M input tokens (very competitive, median: $0.59) and $1.20 per 1M output tokens (better than average, median: $2.20), based on MiniMax's API.
Specifications
Technical specifications
| Model name | MiniMax-M3 |
|---|---|
| Provider | MiniMax |
| Release date | June 1, 2026 |
| Intelligence score | 44 |
| Speed | 99.0 tokens/sec |
| Latency (TTFT) | 1.81s |
| Input price | $0.30 / 1M tokens |
| Output price | $1.20 / 1M tokens |
| Context window | 3 tokens |
| Parameters | 428B |
| Reasoning | Yes |
| Input modalities | text, image, video |
| Output modalities | — |
| Open weights | Yes |
| License | MINIMAX COMMUNITY LICENSE |
| API availability | — |
| Source | Model Intelligence legacy profile: minimax-m3 |
Pricing
Token prices
Price per 1M tokens
MiniMax-M3, as listed in the catalog record
- Input$0.30
- Output$1.20
| Token type | Price per 1M |
|---|---|
| Input | $0.30 |
| Output | $1.20 |
Model Intelligence legacy profile: minimax-m3
FAQ · 21
Frequently asked questions
MiniMax-M3 was released on June 1, 2026.
MiniMax-M3 was created by MiniMax.
MiniMax-M3 scores 44 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25).
MiniMax-M3 generates output at 99.0 tokens per second (based on MiniMax's API), which is above average compared to other open weight models of similar size (median: 61.7 t/s).
MiniMax-M3 has a time to first token (TTFT) of 1.81s (based on MiniMax's API), which is better than average compared to other open weight models of similar size (median: 2.01s).
MiniMax-M3 costs $0.30 per 1M input tokens (very competitive, median: $0.59) and $1.20 per 1M output tokens (better than average, median: $2.20), based on MiniMax's API.
MiniMax-M3 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens (based on MiniMax's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.22 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, MiniMax-M3 generated 89M output tokens, which is better than average compared to other open weight models of similar size (median: 92M).
Yes, MiniMax-M3 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
MiniMax-M3 supports text, image, and video input.
MiniMax-M3 supports text output.
Yes, MiniMax-M3 supports image input and can analyze, describe, and answer questions about images.
Yes, MiniMax-M3 is multimodal. It can process text, image, and video input and generate text output.
MiniMax-M3 has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Yes, MiniMax-M3 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
MiniMax-M3 has 428 billion parameters (23 billion active).
MiniMax-M3 is a Mixture of Experts (MoE) model with 428 billion total parameters, but only 23 billion active parameters are used during inference.
MiniMax-M3 is released under the MINIMAX COMMUNITY LICENSE license. Commercial use requires a separate license agreement.
MiniMax-M3 achieves a score of 44 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, MiniMax-M3 is available via API through 7 providers.
MiniMax-M3 is available through 7 API providers.