Model catalogue

MiniMax
MiniMax M3 (batch)
minimax/minimax-m3:batch
Specification
Published by the vendor; the platform bills at the target's declared price.
MiniMax M3 (batch)
reasoning open weights toolsMiniMax minimax/minimax-m3:batch
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,...
- Input $/1M
- $0.30
- Output $/1M
- $1.20
- Context
- 524K
- Max output
- 472K
- Released
- May 31, 2026
- Modalities
- textimagevideo
Intelligence index30
Coding index59
Agentic index31
Cached input reads $0.06 per 1M · weights on Hugging Face as MiniMaxAI/Minimax-M3
On this deployment
No routing target resolves to this model yet. Declare one and the router picks it up without retraining.
Not routable here yet
Add a target with metadata.model set to this id.
targets.yamlyaml
# targets.yaml - declare a target that runs MiniMax M3 (batch)
targets:
- id: minimax-m3-batch
kind: llm
name: MiniMax M3 (batch)
metadata:
model: minimax/minimax-m3:batch # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 524288
cost:
usd_per_1k_tokens: 0.000750Price among MiniMax models
Input list price per million tokens; MiniMax M3 (batch) is the 4th cheapest of 9 listed.
- 1$0.20
- 2$0.26
- 3$0.27
- 4$0.30MiniMax M3 (batch)
- 5$0.30
- 6$0.30
- 7$0.30
- 8$0.30
- 9$0.55
More from MiniMax
Other models by the same vendor in the catalogue.