MoleAPI logo
MoleAPI
AI model gateway
Models/MiniMax

MiniMax

MiniMax models, pricing, and protocols

15 currently available models with pricing synced from the MoleAPI console.

15 models

Compare
M
MiniMax-M3-90%Official profile verified

MiniMax M3 is MiniMax's next-generation model for million-token context, agents, and office automation, using sparse attention to reduce long-context compute.

View model
defaultx1
base
Input$0.3 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.06 / 1M tokens
discountx0.8
base
Input$0.24 / 1M tokens
Output$0.96 / 1M tokens
Cache read$0.048 / 1M tokens
relayx0.3
base
Input$0.09 / 1M tokens
Output$0.36 / 1M tokens
Cache read$0.018 / 1M tokens
tempx0.1
base
Input$0.03 / 1M tokens
Output$0.12 / 1M tokens
Cache read$0.006 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationPrompt cacheCompare
M
MiniMax-M2.7-90%Official profile verified

MiniMax M2.7 is a mature M2-series model for reasoning, coding, and agents, with a high-speed serving variant.

View model
defaultx1
base
Input$0.306 / 1M tokens
Output$1.224 / 1M tokens
Cache read$0.06 / 1M tokens
discountx0.8
base
Input$0.2448 / 1M tokens
Output$0.9792 / 1M tokens
Cache read$0.048 / 1M tokens
relayx0.3
base
Input$0.0918 / 1M tokens
Output$0.3672 / 1M tokens
Cache read$0.018 / 1M tokens
tempx0.1
base
Input$0.0306 / 1M tokens
Output$0.1224 / 1M tokens
Cache read$0.006 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationPrompt cacheCompare
M
MiniMax-M2.7-highspeed-90%Official profile verified

MiniMax M2.7 is a mature M2-series model for reasoning, coding, and agents, with a high-speed serving variant.

View model
defaultx1
base
Input$0.306 / 1M tokens
Output$1.224 / 1M tokens
Cache read$0.06 / 1M tokens
discountx0.8
base
Input$0.2448 / 1M tokens
Output$0.9792 / 1M tokens
Cache read$0.048 / 1M tokens
relayx0.3
base
Input$0.0918 / 1M tokens
Output$0.3672 / 1M tokens
Cache read$0.018 / 1M tokens
tempx0.1
base
Input$0.0306 / 1M tokens
Output$0.1224 / 1M tokens
Cache read$0.006 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationPrompt cacheCompare
M
MiniMax-M2.5-70%

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.304 / 1M tokens
Output$1.216 / 1M tokens
Cache read$0.0304 / 1M tokens
discountx0.8
base
Input$0.2432 / 1M tokens
Output$0.9728 / 1M tokens
Cache read$0.0243 / 1M tokens
relayx0.3
base
Input$0.0912 / 1M tokens
Output$0.3648 / 1M tokens
Cache read$0.0091 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationPrompt cacheCompare
M
MiniMax-M2.5-highspeed-70%

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.608 / 1M tokens
Output$2.432 / 1M tokens
Cache read$0.06 / 1M tokens
discountx0.8
base
Input$0.4864 / 1M tokens
Output$1.9456 / 1M tokens
Cache read$0.048 / 1M tokens
relayx0.3
base
Input$0.1824 / 1M tokens
Output$0.7296 / 1M tokens
Cache read$0.018 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationPrompt cacheCompare
M
MiniMax-M2.1-70%

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.304 / 1M tokens
Output$1.216 / 1M tokens
Cache read$0.06 / 1M tokens
discountx0.8
base
Input$0.2432 / 1M tokens
Output$0.9728 / 1M tokens
Cache read$0.048 / 1M tokens
relayx0.3
base
Input$0.0912 / 1M tokens
Output$0.3648 / 1M tokens
Cache read$0.018 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationPrompt cacheCompare
M
MiniMax-M2-70%

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.304 / 1M tokens
Output$1.216 / 1M tokens
Cache read$0.06 / 1M tokens
discountx0.8
base
Input$0.2432 / 1M tokens
Output$0.9728 / 1M tokens
Cache read$0.048 / 1M tokens
relayx0.3
base
Input$0.0912 / 1M tokens
Output$0.3648 / 1M tokens
Cache read$0.018 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationPrompt cacheCompare
M
minimax-m2.7-70%Official profile verified

MiniMax M2.7 is a mature M2-series model for reasoning, coding, and agents, with a high-speed serving variant.

View model
discountx0.8
base
Input$0.2448 / 1M tokens
Output$0.9792 / 1M tokens
Cache read$0.048 / 1M tokens
relayx0.3
base
Input$0.0918 / 1M tokens
Output$0.3672 / 1M tokens
Cache read$0.018 / 1M tokens
openaiopenai-responseanthropicOpenAI compatibleResponses APIAnthropic compatiblePrompt cacheCompare
M
minimax-m3Official profile verified

MiniMax M3 is MiniMax's next-generation model for million-token context, agents, and office automation, using sparse attention to reduce long-context compute.

View model
defaultx1
base
Input$0.3 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.06 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M
minimax-m2.5

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.3 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.03 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M
minimax-m2.5-lightning

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.6 / 1M tokens
Output$2.4 / 1M tokens
Cache read$0.06 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M
MiniMax-M2.5-lightning

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.3 / 1M tokens
Output$2.4 / 1M tokens
Cache read$0.06 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M
minimax-m2.1

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.3 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.06 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M
MiniMax-M2.1-lightning

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.3 / 1M tokens
Output$2.4 / 1M tokens
Cache read$0.06 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M
minimax-m2-her

MiniMax model by MiniMax for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$0.3 / 1M tokens
Output$1.2 / 1M tokens
openaiOpenAI compatibleCompare