Notice
Wan3.0 Officially Launched: Wan3.0 is a native large-scale model for generating 30-second videos, seamlessly orchestrating all audiovisual elements and supporting multi-modal references, delivering viOriginal Manufacturer Authorized · Genuine and TraceableEnterprise‑grade large‑model intelligent gateway platform—provides enterprises with compliant, controllable, stable, and efficient AI model API aggregation and governance services; one‑stop access to⚡️This site has been integrated with the official versions of GLM 5.3 and DeepSeek V4❗️

Vision / MiniMax

minimax-m2.5

Text and codeMultimodalityDeep Thinking

Overview

The state-of-the-art in the agent world, designed specifically for Agent 2.0, extends coding capabilities to the real world—encompassing workspaces, entertainment, and personal assistance. Key model highlights: a globally SOTA open-source coding and agent model; superior scores on SWE-bench Pro and SWE-bench Verified compared to Opus 4.6; world‑leading performance in Excel tasks, search and research, and document summarization; the ideal core model for future workspaces; lightning‑fast: optimized for thinking efficiency, delivering over 100 TPS and running up to three times faster than Opus; and exceptional cost‑effectiveness, enabling always‑on agents.

  • Model type: Vision
  • Input: Text
  • Output: Text
  • Endpoints: chat / chat_completion
Tiered billing details
TierInputOutputCache hitCache write
Fallback tier$0.0003/1K$0.0012/1K$0.0000/1K$0.0004/1K

Billed bylen (input context token count). Coefficient is the $ / 1M tokens price. Default group price (other groups converted by discount).

Capabilities

  • programming: Thinking and Building Like an Architect
  • Search and function calling

Code example

Call with minimax-m2.5 :

curl https://www.starunion.net/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.5",
    "messages": [{
      "role": "user",
      "content": [
        { "type": "text", "text": "Describe this image" },
        { "type": "image_url", "image_url": { "url": "https://example.com/photo.jpg" } }
      ]
    }]
  }'