MiniMax (M2 / Text-01 / Hailuo AI)
LLMby MiniMax
MiniMax is a pioneer in Asian LLMs offering multimodal capabilities across text, audio, video, image, and music. Known for natural voice synthesis and the consumer product Hailuo AI.
Registration & API Key Steps
Step 2
Register with email and complete verification.
Step 3
Claim the free developer starter pack upon registration.
Step 4
Navigate to API Key management and generate a key.
Step 5
For additional test credits, email api@minimaxi.com (up to $100).
Pricing
| Tier | Price | Features |
|---|---|---|
| MiniMax-01 | $0.20 / $1.10 per 1M tokens | Input / Output. Base model. |
| MiniMax M2 | $0.26 / $1.00 per 1M tokens | Input / Output. Latest model. |
| MiniMax M2.1 | $0.27 / $0.95 per 1M tokens | Input / Output. Updated version. |
| Cache Hits | $0.03 / 1M tokens | 10% of input price for cached content. |
Application Tips
Tip 1
MiniMax excels at voice synthesis — one of the most natural-sounding TTS APIs.
Tip 2
Email api@minimaxi.com for up to $100 in free developer credits.
Tip 3
Enterprise/individual developers get 100M free tokens for Abab6.5s after completing registration.
Tip 4
Hailuo AI (hailuoai.com) is the consumer-facing product for testing capabilities.
Tip 5
Supports both international (intl.minimaxi.com) and Chinese (minimaxi.com) platforms.
Tip 6
Video generation (Hailuo Video) is one of the top AI video generators.
China Access Solutions
Access Solution
Directly accessible via minimaxi.com (Chinese platform). International platform at intl.minimaxi.com may require VPN from China.
Code Example
from openai import OpenAI
client = OpenAI(
api_key="your-minimax-api-key",
base_url="https://api.minimax.chat/v1"
)
response = client.chat.completions.create(
model="MiniMax-Text-01",
messages=[
{"role": "user", "content": "Write a creative short story about AI"}
],
max_tokens=1024
)
print(response.choices[0].message.content)
# --- cURL example ---
# curl https://api.minimax.chat/v1/text/chatcompletion_v2 \
# -H "Authorization: Bearer your-api-key" \
# -H "Content-Type: application/json" \
# -d '{"model":"MiniMax-Text-01","messages":[{"role":"user","content":"Hello!"}]}'Rate Limits
| Tier | Limits |
|---|---|
| Default | Default: varies by model and plan. Free tier has limited RPM. Contact support for enterprise limits. |
Recommended Use Cases
Related API Guides
OpenAI GPT-4o / GPT-4.1 / o3
OpenAI
OpenAI's flagship LLM family including GPT-4o for multimodal tasks, GPT-4.1 for long-context coding, and o3 for advanced reasoning. Industry-leading models with the largest developer ecosystem.
Anthropic Claude (Sonnet 4.5 / Opus 4.5)
Anthropic
Anthropic's Claude model family excels in nuanced reasoning, safety, and long-context tasks. Claude Sonnet 4.5 offers the best balance of cost and performance, while Opus 4.5 delivers frontier intelligence.
Google Gemini (2.5 Pro / 2.5 Flash)
Google's Gemini models offer a generous free tier, 1M token context window, and strong multimodal capabilities. Gemini 2.5 Pro leads in reasoning, while Flash models provide cost-effective alternatives.
Meta Llama 4 (Scout / Maverick)
Meta
Meta's open-source Llama 4 models are free to use and available through multiple cloud providers. Llama 4 Scout and Maverick offer competitive performance at extremely low cost through partner APIs.