MiniMax M2.5 API via TokenMix

Use MiniMax M2.5 from MiniMax as a chat model through the TokenMix AI API relay and multi-model gateway.

SOTA in coding and agentic tasks, designed for Agent Universe with 100 TPS throughput at 1/10 cost of competitors

API access

  • Base URL: https://api.tokenmix.ai/v1
  • Model ID: minimax-m2.5
  • OpenAI SDK compatible. Change the base URL and use your TokenMix API key.

Pricing

Input $0.324265/M tokens, output $1.297059/M tokens

Capabilities

Function calling, JSON mode, Streaming, Reasoning

Model specs

  • Context: 200K tokens
  • Max output: 128K tokens

Availability

3/3 available API endpoints are healthy right now.

Recent performance

TTFT 2525ms, latency 7223ms, throughput 57.0 tok/s.

Start using this model

Create an API key, top up from $1 when needed, and call this model through the TokenMix OpenAI-compatible endpoint.

Create API key · View pricing · Quickstart