Enterprise-grade AI throughput
The world’s most advanced language, image, and video models on one high-concurrency OpenAI-compatible API.
Licensed upstream routing — not a scraped consumer-account pool. Peak capacity, measured latency, and contract SLA are listed separately. US and Singapore are live. We do not serve PRC-registered entities.
Paid accounts default to 500 RPM; 1000+ RPM is available on request. No enterprise contract required to use the same infrastructure — start at $5 PAYG.
curl https://api.aimodelapi.ai/v1/chat/completions \
-H "Authorization: Bearer sk-ama-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-5","messages":[{"role":"user","content":"ping"}]}'Performance data comes from ModelAPI production or standardized tests. Unless an enterprise contract says otherwise, peak throughput, latency, and cache-hit rates are historical measurements or platform ceilings — they do not mean every model, region, account, or workload will sustain them. Actual performance depends on model, input length, concurrency, network location, upstream capacity, and cache policy. See method
Connecting you to the world's leading AI providers
Trending This Week
Models ranked by usage
Based on real request volume over the past 7 days · updated hourly
Harness, session budgets, and compaction live on /harness and /enterprise — not on the homepage.
Sound familiar?
3 blockers that stop most developers
Account friction, cross-border routing, and billing — we offer a compliant SaaS path (see /compliance).
Account rejected or banned
Overseas phone + credit card required. Accounts banned without warning; balance lost.
✓ Our solution
Sign up with email. Eligible users per /compliance; credits never expire.
Unstable network & timeouts
Cross-border API calls over long routes suffer latency spikes and timeouts — hard to meet production SLAs.
✓ Our solution
Multi-region PoPs and smart routing. Primary endpoint in US East; regional BASE_URLs as PoPs ship.
Payment walls & no invoices
Foreign card only. No RMB payment, no VAT invoice, no corporate billing.
✓ Our solution
Eligible accounts (see /compliance) can pay with WeChat, Alipay, or Stripe. Invoices are for eligible non-PRC entities — we do not serve mainland-registered companies.
Problems we solve
Ten keys, inflated bills, flaky routing — condensed into one control plane.
10 provider accounts · 10 API keys · 10 dashboards
OpenAI, Anthropic, Google, DeepSeek — each with its own account, billing, key rotation, and quota tracking.
API feels 10× more expensive · hidden token inflation
Per-token API billing adds up. Some gateways add markup, inflate counts, or swap models.
Cheap models underperform · flagship costs · manual switching hurts flow
Trading cost vs quality manually breaks unattended workflows.
Complex docs · hard to debug · slow support
Non-developers get stuck; ticket cycles are long.
Frontier paths and savings in one envelope
Same credential surface for experimentation and scaled traffic.
Frontier models
Claude Opus 5, Sonnet 5, GPT-5.6 Sol/Terra/Luna, Wan 2.7, Gemini 3.1 Pro — same integration surface.
High-value models
DeepSeek V4 Flash, Qwen, Kimi, GLM — built for volume and everyday workloads.
Watch a request end-to-end
Representative routing: code pane, streamed body, latency and credits.
Loading...Ecosystem
Works where you already build
Point Cursor, Windsurf, VS Code, Claude Code, or Codex CLI at ModelAPI.
Universal config — works in every tool
Resilience
Backup hosts when routes change
Reuse the exact same key — swap hostname only.
Catalog
Featured models
58+ callable models · one key. Qwen3.8 Max (qwen3.8-max) and GLM-5.2 (glm-5.2) are live.
Claude Opus 5
GPT-6 Astra
GPT-5.6 Sol
Claude Sonnet 5
GPT-5.6 Terra
GPT-5.6 Luna
Claude Fable 5
Grok 4.6
Gemini 3.1 Pro
Qwen3.8 Max
GLM-5.2
Kimi K2.7 Code
Wan 3.0 Video
Four outcomes
What you get in the first five minutes
Harness, MCP, and compaction stay on developer and enterprise pages.
Peak capacity, measured latency, contract SLA
Up to 200M tokens/min platform throughput and 1,000+ RPM capacity. Claude Opus measured TTFT P95 under 7s in Singapore. Enterprise contracts can add 99.9%/99.95% availability — those three are not the same promise.
Language, image, and video models worldwide
Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, GLM, plus image and video models on one OpenAI-compatible key. Licensed upstream routing — not a scraped consumer-account pool. Catalog size is the callable list on /models.
5-minute migration
Swap base_url from OpenAI or OpenRouter. Claude Code needs ANTHROPIC_BASE_URL. Same SDK, prompts, and tools.
Verifiable price and status
List prices, live gateway probes, and a public trust center. We tell you which regions are live vs planned.
Global payments
WeChat Pay, Alipay, cards, Apple Pay, Google Pay, PayPal, and USDT. Official token prices plus a 5% top-up fee.
Start in under 60 seconds
Three steps to your first call
Sign up, get a key
Email signup auto-creates a key. $1 test credit is granted after admin review. No card.
Get free API keyRun the first call
Copy curl or run the request on the onboarding page. Top up only after it works.
See curlPricing
Usage-based tiers without guesswork
Upstream model passes through with a spelled-out infra surcharge — zero surprise fees.
Free
For exploration and testing
- 20 req/min · 50K req/day
- 10+ free models
- Community support
- Basic analytics
Pay-as-you-go
Official API prices · zero markup · min $5 top-up · no monthly seat fee
- Default 500 RPM after top-up · 50,000 req/day
- 1000+ RPM on request — not automatic
- All 58+ listed models
- 0% per-token markup · 5% infra fee at top-up
- Credits never expire
- WeChat · Alipay · cards · PayPal · USDT
Enterprise
Dedicated capacity and contract SLA
- Reserved TPM / RPM by contract
- 99.9% or 99.95% monthly availability SLA
- Priority routing, failover, incident notice
- Teams, key budgets, invoices, audit logs
- Service credits defined in the contract
Accepted payment methods worldwide
Representative workflows
How different teams use a unified model API
Illustrative personas and workflows, not named customer endorsements. Verified case studies will be published with customer permission.
"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."
"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."
"We needed one gateway for multiple model providers. ModelAPI unified billing and routing; WeChat Pay works for our eligible accounts. Deployed to production in one afternoon."
"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."
"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."
"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."
Recent Updates
What we've shipped lately
Wan 3.0 is live — call WAN-video-3.0
Alibaba Wan 3.0 (wan3.0-video) is on Bailian: 480P/720P/1080P, 2–30s, billed at 65% of Singapore list. Prime: WAN-video-3.0-prime.
Qwen3.8 Max is live — call qwen3.8-max
Alibaba Qwen3.8 Max is callable on Bailian. Public ID qwen3.8-max (1M context). Qwen3.7 Max remains the previous SKU.
Claude Opus 5 live — Grok 4.6 and Fable 5 pending
Call claude-opus-5 or claude-opus-latest. Latest Grok (grok-4.6) and Claude Fable 5 are listed as pending.
Claude Opus 4.8 shipped (now previous-gen — use Opus 5)
Use claude-opus-5 or claude-opus-latest. Save cost with claude-opus-5-rsc. Hermes dropdown "Opus 4 7" may fail — see docs.
DeepSeek V4 Flash added — 344% weekly surge
Now routing via nexus/cheapest. $0.14/M input, 1M context.
Human-in-the-loop tool calls now supported
Pause agentic workflows mid-execution and inject human decisions via the API.
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.
Call the world’s most advanced language, image, and video models now.
No credit card. $1 welcome credit after admin review.