MiniMax M3
Multimodal foundation model accepting text, image, and video input with a 1M-token context window, suited to long-horizon agentic work and coding.
Pricing
Input$0.30 / 1M checked Jul 19, 2026
Output$1.20 / 1M checked Jul 19, 2026
Cost bandUltra-budget
Free tierNo free API tier documented.
Limits
Context window1M checked Jul 19, 2026
DeploymentMiniMax API
OpenAI-compatible APIYes
ModalitiesText, Image input, Video input
Where it fits
Best forVideo-aware pipelines and long-context agents on a budget.
Business fitOne of the few budget models with native video input.
Capabilities
Function callingStructured outputs
Change history
- May 31, 2026New modelMiniMax M3 added to the index $0.30 in / $1.20 out per 1M, 1M context, video input. OpenRouter listing
Data
Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/minimax/minimax-m3
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.