MiniMax: MiniMax M3
Released May 31, 2026Try it on:
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,...
Best overall rank
-
Across all subsets · overall
Total arena votes
0
Across 0 (subset, category) entries
Providers on OR
0
None yet
First seen
-
Awaiting first snapshot
Trend
No snapshot history yet - trends appear after the first daily refresh.
Pricing
Per token
- Input (per 1M)
- $0.300
- Output (per 1M)
- $1.20
- Cache Read (per 1M)
- $0.060
Capabilities
Modality
text+image+video->textContext
1M tokens
Tokenizer
Other
Max output
512K tokens
Moderation
Unmoderated
Hugging Face
Supported parameters
frequency_penalty
include_reasoning
max_tokens
reasoning
response_format
temperature
tool_choice
tools
top_k
top_p
Providers
No provider endpoint data yet.
Per-category ranks
No leaderboard entries for this model.