An LLM gateway that routes 600+ models through one API with fallbacks and cost management (5% markup on usage)
Information updated 2026-10-21, source: official site and public reports. Prices and benefits may change. Check the official site before you pay.
Pros
- Region-based routing (EU Frankfurt, US, Singapore), automatic fallbacks, per-agent policies, cost limits
- Cursor, Cline and Continue integration
- MCP Gateway
- Free plan (free models 200 times per day)
Cons
- 5% markup on provider prices
- No Korean or KRW payment
- Features centered on teams and companies rather than individuals
These are opinions compiled by Pickx from public sources.
Cautions
Prompts pass through an intermediate gateway, so the data handling and retention policies need checking (an EU data residency option exists). Payment methods and refund rules need checking
At a glance
A gateway that bundles several LLM providers into one API and automatically switches to another model when there is an outage. It adds 5% to token prices, and its focus is on cost management and policy control for teams and companies.
AI and products offered
| Product/model | Price | Notes |
|---|---|---|
| 600+ model API | Provider price +5% | e.g. a $10/1M token model → $10.50 |
| Free models | Free | 200 per day |
| BYOK | Needs checking | Shown as included in the pay-as-you-go plan |
Plans and fees
| Plan | Price | What you get/limits | Features |
|---|---|---|---|
| Free | $0 | Free models, 200 per day, routing/caching/fallbacks | No card registration needed |
| Pay as you go | Usage +5% | 600+ models, BYOK, spending limits, MCP Gateway | No seat fees or minimum spend |
| Enterprise | Negotiated | SSO, RBAC, audit logs, PII detection | Dedicated support/SLA |
Who it suits / Who should avoid it
- Suits: Teams that use several models in production and need outage protection and cost control
- Avoid: Small-volume individual users (the 5% markup is a straight loss), people who only need a chat app
Compared with subscribing to the original services directly
- Token costs are 5% higher than using the API directly
- In exchange you do not need to build fallback, routing and spending limit features yourself
Notes
- Information checked on: 2026-10-20
- Requesty pricing
- Requesty home
Good for
FAQ
Can I use Requesty for free?
Yes, there is a free plan.
Related comparisons
Similar options
A unified API gateway that offers 1,000+ AI models (text, image, video, voice) through a single API
AIMLAPI OÜ / Boiler Labs FZ-LLCOtherTrial onlyKorean: Limited
Check siteVisit siteAn API reseller service that claims to sell 500+ model APIs at 80% of official model prices (20% off)
CometAPIOtherTrial onlyKorean: Average
Check siteVisit siteA French API gateway that combines many AI APIs such as LLM, OCR and speech into one (5.5% fee when buying credits)
Eden AIOtherPaid onlyKorean: Limited
Check siteVisit siteA generative media developer platform that offers about 1,000 image, video, audio and 3D generation models through a single API
Features and Labels, Inc.United StatesPaid onlyKorean: Limited
Check siteVisit siteAn open-source AI gateway that combines more than 100 LLM providers into one OpenAI-compatible API and manages keys, budgets and costs
BerriAI (Berrie AI Incorporated)United StatesFreeKorean: Limited
FreeVisit siteA leading LLM API router and credit-selling platform that lets you use 500+ models from 80+ providers with one API key
OpenRouter, Inc.United StatesFree plan availableKorean: Limited
Check siteVisit site
4 views
Prices converted at 1 USD = ₩1,327.84 (2026-10-20). Original price shown in brackets. Taxes as listed by each provider.