6G
6G-AI
0

01.AI Yi (Yi-Large / Yi-Medium)

LLM

by 01.AI

01.AI's Yi series models offer strong multilingual performance and competitive pricing. Yi-Large is the flagship model. OpenAI-compatible API makes migration easy. Open-source models available.

Official APIDocumentation
API Endpoint

https://platform.lingyiwanwu.com/

Documentation

Official Docs

Pricing

View Pricing

Registration & API Key Steps

1

Step 1

Visit 01.AI Platform and register.

Open link
2

Step 2

Sign up with email or phone number (Chinese phone supported).

3

Step 3

Complete account verification.

4

Step 4

New users automatically receive ¥60 in trial credits.

5

Step 5

Navigate to API Key management to create your key.

6

Step 6

API is OpenAI-compatible — use the OpenAI SDK with a custom base URL.

Pricing

TierPriceFeatures
Yi-Large¥20 / ¥20 per 1M tokensInput / Output (~$2.75). Most capable model.
Yi-Medium¥2.5 / ¥2.5 per 1M tokensInput / Output (~$0.34). Balanced performance.
Yi-Spark¥1 / ¥1 per 1M tokensInput / Output (~$0.14). Budget-friendly.
Yi-Large-Turbo¥12 / ¥12 per 1M tokensInput / Output (~$1.65). Fast version of Yi-Large.

Application Tips

Tip 1

¥60 free credits is one of the most generous new user offers among Chinese LLM providers.

Tip 2

API is OpenAI-compatible — migration from OpenAI is seamless.

Tip 3

Yi-Spark at ¥1/1M tokens is extremely affordable for lightweight tasks.

Tip 4

Yi open-source models (Yi-34B, Yi-9B) can be self-hosted on Hugging Face.

Tip 5

Yi-Large supports 300K Chinese characters input — good for long document analysis.

Tip 6

Access is limited — new user quotas may be restricted during high-demand periods.

China Access Solutions

Access Solution

Directly accessible in China. 01.AI is a Beijing-based company. Supports Chinese phone and domestic payment methods.

Code Example

JavaScript / TypeScript
from openai import OpenAI

client = OpenAI(
    api_key="your-yi-api-key",
    base_url="https://api.lingyiwanwu.com/v1"
)

response = client.chat.completions.create(
    model="yi-large",
    messages=[
        {"role": "user", "content": "分析中国AI产业的发展趋势"}
    ]
)

print(response.choices[0].message.content)

# --- cURL example ---
# curl https://api.lingyiwanwu.com/v1/chat/completions \
#   -H "Authorization: Bearer your-api-key" \
#   -H "Content-Type: application/json" \
#   -d '{"model":"yi-large","messages":[{"role":"user","content":"你好"}]}'

Rate Limits

TierLimits
DefaultDefault: varies by model. Yi-Large: limited RPM for free tier. Paid tier offers higher limits. Contact support for enterprise.

Recommended Use Cases

Multilingual content generationLong document analysisChinese language tasksCode generationResearch
Last Updated: 2026-02-10

Related API Guides

O

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.

A

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.

G

Google Gemini (2.5 Pro / 2.5 Flash)

Google

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.

M

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.