GPT-5.5 Pro · Claude Opus · DeepSeek · Gemini — plus 50+ more

One API · Connect to world-leading models

Better routing · transparent pricing · no subscriptions

Change two lines — base URL and API key — to connect. A small infra fee is added when you purchase credits (default 5%); usage deducts against provider list pricing.

Python · OpenAI SDK1-line migration
# Before (OpenAI official)
client = OpenAI(base_url="https://api.openai.com/v1")
# After — ModelAPI, same SDK, every top model
client = OpenAI(base_url="https://api.aimodelapi.ai/v1")
✓ OpenAI-compatible✓ One key for all models✓ Auto global routing
400+
AI Models
60+
Providers
120M+
Weekly Tokens
5%
Only fee charged
Ultimate Coding Agent

Claude Code on full Opus 4.7at $2.20/M output cost

Claude Code stays on native Opus 4.7 for planning and reasoning. ModelAPI nexus/cheapest-west handles high-volume subtasks cheaply. Blended output cost: $2.20/M — just 9% of the all-Opus price.

Cost per 1M output tokens
All-Opus
Claude Opus 4.7 × 100%
$25.00
baseline
Hybrid Agent
Opus 5% + nexus/cheapest-west 95%
$2.20
−91%
Savings91%
Output quality: near full-Opus

Sound familiar?

3 blockers that stop most developers

Account bans, unstable connections, payment walls — we eliminate all three.

🚫

Account rejected or banned

Overseas phone + credit card required. Accounts banned without warning; balance lost.

✓ Our solution

Sign up with any email. No foreign card, no ban risk. Your credits never expire.

📶

Unstable network & timeouts

Direct overseas connections drop constantly. VPNs add latency and compliance risk.

✓ Our solution

US primary launches first; APAC and EU regional BASE_URLs enable as PoPs ship.

💸

Payment walls & no invoices

Foreign card only. No RMB payment, no VAT invoice, no corporate billing.

✓ Our solution

WeChat Pay, Alipay, bank transfer in RMB. VAT invoices available. Corporate billing supported.

Problems we solve

Ten keys, inflated bills, flaky routing — condensed into one control plane.

Sound familiar?

10 provider accounts · 10 API keys · 10 dashboards

OpenAI, Anthropic, Google, DeepSeek — each with its own account, billing, key rotation, and quota tracking.

ModelAPI
One key. 50+ models. Unified billing. Central control.
Sound familiar?

API feels 10× more expensive · hidden token inflation

Per-token API billing adds up. Some gateways add markup, inflate counts, or swap models.

ModelAPI
0% per-token markup. Official prices. What you call is what you get.
Sound familiar?

Cheap models underperform · flagship costs · manual switching hurts flow

Trading cost vs quality manually breaks unattended workflows.

ModelAPI
nexus/* routes by task; standard IDs always hit the named model.
Sound familiar?

Complex docs · hard to debug · slow support

Non-developers get stuck; ticket cycles are long.

ModelAPI
Docs tested with non-experts; AI support available 7×24.

Frontier paths and savings in one envelope

Same credential surface for experimentation and scaled traffic.

01

Frontier models

GPT-5.5 Pro, Claude Opus 4.7, Gemini 3.1 Pro, Grok 4.3 — same integration surface.

GPT-5.5Claude Opus 4.7Gemini 3.1 ProGrok 4.3o3
02

High-value models

DeepSeek V4 Flash, Qwen, Kimi, GLM — built for volume and everyday workloads.

DeepSeek V4 FlashQwen3.6 PlusKimi K2.6GLM-5 FlashGemini 3.1 Flash-Lite

Watch a request end-to-end

Representative routing: code pane, streamed body, latency and credits.

request.ts
Anthropic
Loading...
response.json
Awaiting response…

Ecosystem

Works where you already build

Point Cursor, Windsurf, VS Code, Claude Code, or Codex CLI at ModelAPI.

All guides

Universal config — works in every tool

Base URL
https://api.aimodelapi.ai/v1
API Key
sk-ama-YOUR_KEY

Resilience

Backup hosts when routes change

Reuse the exact same key — swap hostname only.

GLGlobal (Auto-routing)PRIMARY
api.aimodelapi.ai/v1
Primary · auto-optimal
USVirginiaSoon
us.api.aimodelapi.ai/v1
US East
SGSingaporeSoon
sg.api.aimodelapi.ai/v1
Asia Pacific PoP
JPTokyoSoon
jp.api.aimodelapi.ai/v1
Japan PoP
THBangkokSoon
th.api.aimodelapi.ai/v1
Southeast Asia
EUFrankfurtSoon
eu.api.aimodelapi.ai/v1
Europe PoP
BKAlt Primary DomainSoon
api2.aimodelapi.ai/v1
Backup if .ai is blocked
Switching endpoints takes one config change
Replace api.aimodelapi.ai with any backup host in your BASE_URL. Same API key. Same code.
Live Status

Capabilities

What sits behind one endpoint

One envelope for frontier models and value tiers — not another dashboard maze.

Universal Model Access

GPT-5.5, Claude Opus 4.7, Gemini 3.1, DeepSeek V4, Grok 4.3 and 50+ more — all through one API key, no restrictions.

Drop-in OpenAI SDK

Change 2 lines of code. Keep your existing SDK, prompts, and tools — zero refactoring.

Global Edge Network

US · Singapore · Tokyo · Frankfurt. Regional PoPs roll out after US primary launch.

Lowest Total Cost

Official API prices, zero markup. 5% infrastructure fee at top-up only — below industry average. Bring Your Own Key (BYOK) at $0.50/M for expensive models.

Enterprise Security

Key isolation · RBAC · Audit logs · Spend caps · SOC 2 compliant infrastructure.

Smart Failover

Automatic provider fallback. Route by cost, latency, or capability. Model group aliases included.

Start in under 60 seconds

Three steps to your first call

01
🔐

Create account

Sign up with Google or email. No credit card needed.

Sign up free
02
💳

Add credits

Top up from $5. Supports WeChat, Alipay, Stripe, Apple Pay, crypto.

View payment options
03

Get your API key

Create a key, swap the base URL. Your existing OpenAI code works as-is.

Read quickstart
Change 2 lines — everything else staysPython
# Before (OpenAI direct)
base_url = "https://api.openai.com/v1"
api_key = "sk-openai-..."
# After (ModelAPI — same SDK, any model)
base_url = "https://api.aimodelapi.ai/v1"
api_key = "sk-ama-YOUR_KEY"
client = OpenAI(base_url=base_url, api_key=api_key)
resp = client.chat.completions.create(
model="claude-opus-4-7", # or gpt-5.5, deepseek-v4-pro...
messages=[{"role": "user", "content": "Hello"}]
)

Pricing

Usage-based tiers without guesswork

Upstream model passes through with a spelled-out infra surcharge — zero surprise fees.

Free

$0/month

For exploration and testing

  • 20 req/min · 200 req/day
  • 10+ free models
  • Community support
  • Basic analytics
Start Free
MOST POPULAR

Pay-as-you-go

5% infra fee

Official API prices · zero markup · min $5 top-up

  • 500 req/min · 50K req/day
  • All 50+ models
  • 0% per-token markup
  • 5% infra fee (below industry avg)
  • Bring Your Own Key · $0.50/M
  • Navigator 1 AI support · 7×24
  • WeChat · Alipay · Stripe · Apple Pay
Get Started

Enterprise

Custom

For production workloads

  • Unlimited rate limits
  • Reduced service fee (negotiated)
  • Dedicated infrastructure
  • SLA guarantee
  • 24/7 dedicated support
  • VAT invoice available
Contact Sales

Accepted payment methods worldwide

WeChat Pay
CNY
Alipay
CNY
Visa
Card
Mastercard
Card
Apple Pay
Wallet
Google Pay
Wallet
PayPal
Global
Amex
Card
256-bit TLS encryptionPCI DSS compliant via StripeCredits never expireMulti-currency support

Loved by developers

Real users, real results

"Used to juggle 7–8 API accounts. Now one ModelAPI key covers everything, billing is crystal clear, and switching between Claude Opus and DeepSeek takes zero effort."

CY
Chen Yuxiang
AI indie developer

"The Singapore PoP is legitimately fast. I was skeptical about a gateway adding latency, but median response time is actually lower than hitting the OpenAI API directly from SEA. Solid routing."

JK
Jason K.
Full-stack engineer, Singapore

"China access was always our headache. ModelAPI domestic endpoints solved it, and WeChat Pay means no more fighting with foreign credit cards. Deployed to production in one afternoon."

LX
Lin Xiaowen
Startup CTO

"The PPP pricing for India is real — I'm paying ~40% less than teammates in the US for the same models. Switching my existing codebase took literally 2 lines of code."

PM
Priya M.
ML Engineer, Bangalore

"Looked at a lot of gateways — ModelAPI is one of the few with truly 0% per-token markup and a transparent fee structure. The nexus/cheapest route cut our batch inference cost substantially."

WB
Wang Boyuan
Algorithm engineer

"Building multi-tenant where users have different model preferences. The Compare page saved hours of manual benchmarking. BYOK at $0.50/M flat is the most cost-effective routing I've found."

AT
Alex T.
SaaS founder, London

Recent Updates

What we've shipped lately

Full changelog
New Model

DeepSeek V4 Flash added — 344% weekly surge

Now routing via nexus/cheapest. $0.16/M input, 1M context window.

Feature

Human-in-the-loop tool calls now supported

Pause agentic workflows mid-execution and inject human decisions via the API.

Performance

nexus/cheapest-west routing now 40% faster with edge caching

Prompt-level cache hits on repeated context now reduce latency by ~40% at no extra cost.

Access every top AI. Right now.

Sign up in 30 seconds. No credit card required. 50+ models, one key.