MiniMax M2 AI
Description: gorroAI gives you API access to Qwen3 235B, a frontier-scale mixture-of-experts model running on dedicated Apple Silicon hardware in San Juan, PR. 235B parameters, 22B active per token Thinking mode enabled — extended reasoning for complex tasks OpenAI-compatible /v1/chat/completions Running on Apple M5 Max, not in the cloud Flat monthly pricing. No per-token meters. No surprise…
4 subscribers
0.1/10 popularity
458 ms avg latency
5% success rate
1 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
MiniMax M2 AI endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Chat Completions /v1/chat/completions |
Send a chat message and get a response from MiniMax M2.5. OpenAI-compatible format. |
MiniMax M2 AI pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 1 / minute |
|
| PRO | $9.99 / month | — |
|
| ULTRA | $29.99 / month | — |
|
