FAQ Overview

Complete index of APIYI frequently asked questions: getting started, model calls, tokens and logs, billing, enterprise services, and account login — browsable by topic or by symptom.

Every APIYI FAQ article is indexed here. New to APIYI? Start with Getting Started and Top Questions. Already integrated and hitting a specific error? Jump to Troubleshooting by Symptom. Want to read through everything? See Browse by Topic below.

🚀 Getting Started in 3 Steps

Step 1: Register

Gmail, Outlook, Foxmail and university email addresses are supported, or sign in with GitHub

Step 2: Create a KEY

Grab the default token from the console, or create a dedicated KEY and pick its group

Step 3: Set the Base URL

Use /v1 for OpenAI format, the root domain for Claude, /v1beta for Gemini

🔥 Top Questions

How to create a KEY?

Getting the default token and creating a new KEY, step by step

How to configure the Base URL?

Which of /v1, root domain, or /v1beta applies to which models

How to choose the right AI model?

Picking a model by use case, cost, and speed

Why is my API Key invalid?

Nine times out of ten the Base URL and KEY do not match — check this first

Why can't I run requests with a balance?

The pre-deduction mechanism and oversized max_tokens values

What does the model multiplier mean?

The multiplier is an RMB unit — apply the fixed rate to get the USD equivalent

What recharge promotions are available?

First-time bonuses, tiered bonuses, and enterprise policies

Why do the web app and the API differ?

Why the same model feels smarter on the official site than through the API

---

🔧 Troubleshooting by Symptom

Find the row that matches what you are actually seeing. A single symptom often spans several topics, so this table re-threads the troubleshooting articles by observable behavior.

What you’re seeing	Likely cause	Where to look
API Key invalid / 401	Base URL and KEY do not match, or the KEY is mistyped	Invalid API Key · Base URL config
Balance remaining but requests fail	Pre-deduction mechanism, or max_tokens set too high	Balance insufficient · Pre-deduction
Request times out or drops mid-stream	Client timeout too short; reasoning models are slow	Avoiding API timeouts
429 concurrency errors	Concurrency quota reached	API concurrency limits
Output truncated mid-sentence	max_tokens unset or too small	What is max_tokens
A specific model won’t run	Account permission locked, or token model whitelist	Why can’t I use some models · Token model whitelist
Image generation fails / returns empty	Google content safety triggered	Nano Banana failures
Output differs greatly from the reference image	Reference images must be uploaded as base64	Image differs from reference
White-background image shows black spots	Known behavior on the AI Studio route	White background artifacts
Want to poll image results by task ID	Image generation is synchronous only	Is there an async image API
Model claims to be another vendor / can’t state its version	Model self-knowledge is unreliable	Claude claims to be Qwen · Models don’t know their version
Web app smart, API dumb	The web app ships system prompts and tooling; the API is the bare model	Web app vs API
Unfamiliar calls on your KEY	The KEY may be leaked — trace it and disable it	Investigate unexpected KEY usage · Manage keys securely
Billing doesn’t add up	Per-usage and per-call billing read differently	Reading billing in logs · Model multiplier
Image or video downloads are slow	Overseas CDN routing on specific servers	CDN downloads are slow
Do I need a proxy?	Direct connection works; no proxy required	Do I need a proxy
GitHub login says ‘Account already bound’	That GitHub account is bound to another email	GitHub binding error
Forgot your password	Reset by email or ask support for help	Forgot password

---

📚 Browse by Topic

🧭 Site Features (3)

Question	In one line
Tokens & Groups	How to create a KEY and pick a group
What is a Group? User Group vs Token Group Explained	The group selected on the token is what actually applies
Why Doesn’t APIYI Offer One-Click Integration?	Integration differs per model; use the AI assistant instead

⚙️ Models & API (15)

Question	In one line
Do Google Models Run on AI Studio or Vertex?	Default groups use the official AI Studio route
Why Does a White-Background Image Show Black Spots, Dirty Patches, or Blurry Color Blocks?	Prompt for a light background instead of pure white
How to Choose the Right AI Model?	Select by use case, cost, and speed
Why can’t I use some models?	Some models need permission unlocked first
Why do official web apps and the API give different results?	The web app adds system prompts; the API is the bare model
Why Don’t AI Models Know Their Own Version?	Model self-knowledge is unreliable
Why Does Claude Claim to Be Qwen or DeepSeek?	Identity hallucination, not a swapped model
What does the -c suffix in model names mean?	Marks a different route with different billing
How to Configure Base URL? Differences Between /v1, Root Domain, and /v1beta	One form each for OpenAI, Claude, and Gemini
How do I avoid API timeouts?	Raise the client timeout; reasoning models are slow
What Are the API Concurrency Limits?	Limits vary by model type and can be raised
What is max_tokens? What Happens If Not Set?	Caps output length; there is a default if unset
Common Reasons for Nano Banana Image Generation Failures	Usually Google content safety being triggered
Why Does the Generated Image Differ Greatly from the Reference?	Reference images must be base64 encoded
Is There an Async Image API? Can I Query Results by Task ID?	Synchronous only; no task ID lookup

🔑 Tokens & Logs (9)

Question	In one line
How to create a KEY?	Get the default token or create a new one in the console
Do I Need to Set Available Models for Tokens?	Optional, but recommended when isolating projects
How Do I Manage API Keys Securely?	IP whitelists, model whitelists, and daily habits
What’s the Difference Between Token Billing Modes?	Five billing modes and when each fits
How to view my call records?	Call and billing detail in the console log page
How do I read the billing amounts in the logs?	Per-usage vs per-call, and computing cost from usage
How long are call logs kept, and when are they cleared?	Current month plus two prior; cleared on the 5th
Can I View Detailed Logs in the Backend for Troubleshooting?	Admins can enable verbose logging temporarily
How do I investigate unexpected API Key usage?	Trace real IPs in the logs and disable the KEY

🏢 Enterprise Services (7)

Question	In one line
What Is the Enterprise Group? When Should You Use It?	Model-specific group with steadier supply, higher multiplier
Is APIYI’s Enterprise Service Trustworthy? Are the Models Authentic?	Transparent official relay — no rerouting or model swapping
What’s the difference between enterprise and individual users?	Same account type; differences are in support and pricing
How do enterprise customers recharge?	Bank transfer preferred; VAT invoices available
How can university customers reimburse worry-free?	Invoices, purchase lists, and stamped documents provided
Does APIYI offer SLA guarantees?	Yes, including billing-anomaly compensation and credit refills
Does an Agent Mini-Program Need Algorithm Filing?	Usually yes; this covers the general process

💰 Billing & Security (14)

Question	In one line
Prices Match the Official Rates — Why Buy from APIYI?	Same price plus recharge bonuses, stackable with group discounts
How can APIYI price below the official rates?	Bulk purchasing and vendor distribution, not degraded models
What Does the Model ‘Multiplier’ Mean?	An RMB unit; apply the fixed rate for the USD equivalent
How Much Computing Power Does 100 RMB Get?	Your own system decides the conversion ratio
Does APIYI Support Cache Billing?	All major routes support it; hit rates vary by vendor
What is the pre-deduction mechanism for API calls?	Estimated upfront, settled against actual usage
Why can’t I run requests with remaining balance?	Pre-deduction check, or max_tokens set too high
How to Set Up Balance Alerts?	Email, group bots, or the balance alert API
What Payment Methods Does APIYI Support?	WeChat, Alipay, USDT, Stripe, PayPal and more
What recharge promotions are available?	First-time and tiered bonuses, plus invoicing
How do I apply for an agent partnership? Can I earn rebates by inviting friends?	Referral rebates are on by default; no application needed
What Is APIYI’s Refund Policy?	Conditions, process, fees, and invoice notes
How is content safety and compliance ensured?	Moderation mechanisms and violation handling
How does APIYI ensure data security?	Encrypted transport, minimal storage, access control

🌐 Network & Connection (3)

Question	In one line
Do I Need a Proxy to Use the API?	Direct connection works; no proxy or VPN needed
Where are APIYI’s Servers? Which Server Should I Choose?	Node locations, latency testing, and purchase advice
CDN Image/Video Downloads Are Slow — What to Do?	Diagnosing overseas CDN routing on specific servers

👤 Account & Login (6)

Question	In one line
Which email providers does APIYI support for registration?	Gmail, Outlook, Foxmail and university addresses
How do I sign in with a Passkey?	Bind once, then use fingerprint or face unlock
GitHub Login Shows ‘Account Already Bound’?	That GitHub account is bound to another email
What If I Forgot My Password?	Reset by email or ask support for help
Why is my API Key invalid?	A mismatched Base URL and KEY is the usual cause
How Do I Delete My Account?	One-click deletion; data cannot be recovered

---

💬 Still Stuck?

Use Cases

Integration guides for Cherry Studio, Claude Code, Cursor and more

Model Pricing

Live pricing table and detail pages for every model

Live Updates

Daily updates on model status, supply changes, and incidents

Announcements

New model launches, price changes, and feature updates

Still no luck? Reach us directly:

• 📧 Email: [e-mail]
• 🌐 Console: api.apiyi.com
• 💰 Pricing: Pricing page

If your question isn’t covered, send it to support — we review suggestions and add them to the FAQ. New users get free trial credits, so you can validate your integration before topping up.