Requesty
Hosted LLM router with a unified API to 600+ models, fallbacks, caching and spend tracking; EU gateway in Frankfurt.
A flat 5% markup on model costs is the main charge, so a $10 per million token model costs $10.50, with no minimum spend. EU data residency through the Frankfurt gateway is listed on every tier, which sets it apart from OpenRouter, where EU routing needs a Business or Enterprise plan. It suits teams that want a hosted router with EU processing from the start. BYOK is available from pay-as-you-go upwards, and the free tier allows 200 requests a day on free models.
- Headquarters
- 馃嚞馃嚙 United Kingdom
- Parent jurisdiction
- 馃嚞馃嚙 United Kingdom
- EU self-serve plan
- Available; check eligible plans and regions
- GDPR DPA
- Yes
- Billing
- payg
- Free tier
- Free models, 200 requests/day, no credit card.
- Open source
- No
- Website
- www.requesty.ai
- Source last checked
- 2026-10-06
- Pricing evidence
- Published rates
Pricing
Calculated from the listed vendor rates; exclusions still apply. How to read these estimates.
| Model-spend fee (%) |
|---|
| 5 |
Allowances, plan limits & calculation details
Rates are shown at their recorded precision. A zero means no charge in this calculation; the vendor may charge for things we leave out. See the notes for usage assumptions and currency conversions.
- Base fee / month
- $0
- Model-spend fee (%)
- 5
- Bring your own provider keys
- Yes
5% markup on model costs (a $10/1M-token model costs $10.50). No minimum spend. BYOK available on pay-as-you-go and above. EU data residency listed on all tiers via an EU gateway hosted in Frankfurt; GDPR Art. 28 DPA available (requesty.ai/dpa). Enterprise pricing is custom.
Managed alternatives
At $10,000 model spend / month. Adjust usage and requirements.
Requesty: $6,000/yr estimated.
- Vercel AI Gateway: $0/yr estimated 路 $6,000/yr bill differencePublished rates
- Portkey: $588/yr estimated 路 $5,412/yr bill differenceModeled ratesShows the base Production fee only; logged-request overages are not modeled by the model-spend input.
- Helicone: $948/yr estimated 路 $5,052/yr bill differenceModeled ratesShows the subscription fee; request, storage and other usage-dependent extras are not modeled by the model-spend input.
No cheaper managed estimate matches your filters. Adjust your usage or compare with your actual contract bill.
The price difference leaves out migration costs, operating costs and any features you鈥檇 need to replace.
Self-hosted options
Operating cost is not estimated. These options are not counted as savings against managed services.
Other LLM gateways comparisons
Found a wrong rate or plan restriction? Report a correction with a current source.