MiniMax H3
unknownMiniMax general-purpose video model with multimodal references and synchronized stereo audio. Open H3-Base checkpoints; Context-IR and 2K regeneration are not included in the initial weights release.
- Context
- Unknown
- Output
- Unknown
- Offers
- 0
View modelMiniMax image-01
unknownMiniMax text-to-image generation model. The API also takes one character (portrait) reference to keep a person consistent, but it cannot edit an input image
- Context
- Unknown
- Output
- Unknown
- Offers
- 0
View modelMiniMax M1 80K
unknownOpen hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget
- Context
- 1,000,000
- Output
- 80,000
- Offers
- 0
View modelMiniMax-M2
unknownEfficient open MiniMax model built for coding agents and tool-heavy workflows
- Context
- 204,800
- Output
- 131,072
- Offers
- 16
View modelMiniMax-M2.1
unknownEarlier MiniMax agent model for practical coding and productivity tasks
- Context
- 204,800
- Output
- 131,072
- Offers
- 21
View modelMiniMax-M2.5
unknownPrior MiniMax coding model for agent workflows, office edits, and automation
- Context
- 204,800
- Output
- 131,072
- Offers
- 42
View modelMiniMax-M2.5-highspeed
unknownHigh-speed MiniMax model for low-latency coding and agent workflows
- Context
- 204,800
- Output
- 131,072
- Offers
- 10
View modelMiniMax-M2.7
unknownOpen MiniMax flagship for coding agents, office automation, and complex environments
- Context
- 204,800
- Output
- 131,072
- Offers
- 33
View modelMiniMax-M2.7-highspeed
unknownLow-latency M2.7 variant for interactive coding plans and agent loops
- Context
- 204,800
- Output
- 131,072
- Offers
- 14
View modelMiniMax-M2 Her
unknownMiniMax M2 variant tuned for conversational and character-driven agent interactions
- Context
- 200,000
- Output
- 131,000
- Offers
- 0
View modelMiniMax-M3
unknownMiniMax multimodal model for long-context coding, perception, and agent planning
- Context
- 1,048,576
- Output
- 512,000
- Offers
- 28
View modelMiniMax-M3.1-Flash
unknownFrontier multimodal coding model with 1M context window and tunable thinking depth
- Context
- 1,000,000
- Output
- 512,000
- Offers
- 0
View modelMiniMax-M3.1-Flash-Preview
unknownFrontier multimodal coding model with 1M context window and tunable thinking depth
- Context
- 1,000,000
- Output
- 512,000
- Offers
- 0
View modelMiniMax Text 01 (MiniMax)
unknownMiniMax model for chat, coding, office work, and agentic tasks
- Context
- 1,000,000
- Output
- 131,072
- Offers
- 0
View model