feat: upgrade MiniMax default model to M3

[octo-patch]

Summary

Upgrade MiniMax model configuration to include the latest M3 model as default.

Changes

• Add MiniMax-M3 to the model selection list and set it as the new default
• Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed as available alternatives
• Remove deprecated MiniMax-M2.5 and MiniMax-M2.5-highspeed from the list
• Update docs and GUI model selection to reflect M3 as flagship

Why

MiniMax-M3 is the new flagship model with a 512K context window, 128K max output, and image input support across the OpenAI-compatible API.

Models

Model	Description
MiniMax-M3 (default)	Latest flagship with 512K context, 128K max output, image input.
MiniMax-M2.7	Previous flagship with enhanced reasoning and coding. 204K context.
MiniMax-M2.7-highspeed	High-speed M2.7 for low-latency scenarios. 204K context.

Testing

• Prettier formatting checked
• All MiniMax model IDs verified against the MiniMax platform

---

Summary by cubic

Set MiniMax M3 as the default model and update docs/GUI to make it the flagship. Removes M2.5 variants; M3 offers a 512K context, 128K max output, and image input.

• New Features

  • Default minimax model set to MiniMax-M3.
  • GUI and provider updates: add M3; keep M2.7 and M2.7-highspeed; remove M2.5 variants (packages/llm-info, GUI configs).
  • Docs updated with M3 examples and model table.

• Migration

  • No action needed if you use the default minimax model.
  • Replace any MiniMax-M2.5* references with MiniMax-M3, MiniMax-M2.7, or MiniMax-M2.7-highspeed.

^{Written for commit c1a26ec. Summary will update on new commits.}

[cubic-dev-ai]

No issues found across 5 files

_{Re-trigger cubic}