Skip to main content

MiniMax

MiniMax is an AI company that builds the M2/M2.5 model family. The current coding-focused release is MiniMax M2.5, designed for real-world complex tasks including multi-language coding, web/app development, and agent workflows.

Setup options

Provider settings

SettingValue
Provider IDminimax
Base URLhttps://api.minimax.io/anthropic
APIAnthropic Messages compatible
Auth env varMINIMAX_API_KEY

Available models

Model IDContextNotes
MiniMax-M2.5200KReasoning; recommended
MiniMax-M2.5-highspeed200KReasoning; faster, lower latency
MiniMax-M2.5-Lightning200KLegacy name — prefer highspeed for new setup
Use model IDs as minimax/<model-id> — for example, minimax/MiniMax-M2.5.
Model IDs are case-sensitive. minimax/MiniMax-M2.5 is correct; minimax/minimax-m2.5 will not resolve.

Verification

openclaw models status --probe-provider minimax
openclaw models list --provider minimax

Troubleshooting

The MiniMax provider is not configured. Fix by either:
  • Running openclaw configure and selecting MiniMax M2.5, or
  • Adding the models.providers.minimax block manually, or
  • Setting MINIMAX_API_KEY so the provider can be auto-injected.
Then restart the gateway and recheck with openclaw models list.
Verify MINIMAX_API_KEY is set correctly in ~/.openclaw/.env. For OAuth users, re-run the login command if the token refresh has failed.
Check your Coding Plan usage via the MiniMax platform dashboard. The CN endpoint (api.minimaxi.com) has separate rate limits from the global endpoint.