A technical post details issues encountered when migrating from MiniMax M2.7 to M3.1 Flash via the AIHubMix platform. Specifically, disabling the "thinking" feature in chat completions resulted in an HTTP 400 error with code 2013, indicating that the M3.1 Flash model requires adaptive thinking. The post also notes that other methods of disabling thinking still resulted in the model processing information, albeit with varying token usage and execution times. Additionally, a separate issue was identified where image uploads via URL failed, while base64 encoded images or URLs from other hosts succeeded, both instances returning a 2013 error code. AI
IMPACT Highlights potential integration challenges and model behavior changes for developers using MiniMax models via third-party platforms.
RANK_REASON Technical documentation of issues encountered with a specific model version and platform.
- 9router-go
- AIHubMix
- Chat Completions
- kodus-ai
- M2.x
- Messages API
- MiniMax
- MiniMax M2.7
- MiniMax M3.1 Flash
- Token Plan
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →