Requesty
Route model requests through one API with usage controls
Linked from requesty.ai · checked 30 Oct
- Tool type
- Multi-provider AI API gateway
- Made for
- Application developers and AI platform teams
- Runs on
- API endpoint and web dashboard
From @RequestyAI
Recent important posts · features, availability
- New feature
Auto Routing picks a model per question, with fallback
“Auto Routing in three steps: 1. Write the question to answer 2. List the answers it can choose from 3. Pick a model or policy for each Unsure? It falls back to your strongest model. Pinned per session, so you keep cache hits.”
@RequestyAI · Oct 29View - Now available
GPT-6.1 Terra on Requesty, half the input price
“@OpenAI's new GPT-6.1 Terra available now on Requesty! It’s cheaper than GPT-5.6 Terra: Input: $0.50/M (was $1.00, 50% less) Output: $2.50/M (was $6.00, 58% less) Cached input: $0.025/M (was $0.10, 75% less) gpt-6.1-terra”
@RequestyAI · Oct 26View
What it does
Requesty is an AI gateway that connects applications to multiple model providers through a common API. It adds routing and fallback policies, prompt caching, spend limits and request observability. Developers can change the endpoint used by an OpenAI-compatible client and manage model access and usage from the dashboard.
It is useful for teams using several providers or wanting centralized budgets and operational records. The free tier is limited to supported free models and a daily request allowance. Paid model use carries a markup, while enterprise identity, permissions and governance features are separately arranged. Review model-specific behavior and data handling when changing providers or regional routes.
What it can do
- Unified model access
- Routing and fallback
- Prompt caching
- Spend tracking
- Budget controls
- Request observability
- Regional gateways
Works with
- OpenAI-compatible clients
Before you choose
- Free access covers supported free models rather than the entire model catalog.
- Enterprise governance controls require the appropriate plan.
Listed under
Get started
- Create an account and obtain a gateway API key.
- Configure an application to use the Requesty endpoint.
- Select models, routing policies and spending controls.
Plans and prices
Free provides 200 requests/day on supported free models. Pay-as-you-go charges model usage plus a 5% markup, with no per-seat fee or minimum spend. Enterprise is quoted.
We couldn’t find published prices for Requesty. See their pricing page ↗
Sources for this overview
Product pages, documentation, and pricing checked 30 Oct 2026. Each source supports part of the overview; availability and prices can change.
- Requesty: AI Gateway & LLM Router for 600+ Models ↗www.requesty.ai
- Pricing: Free Tier & Pay-As-You-Go LLM Gateway | Requesty ↗www.requesty.ai
Ratings and reviews
No ratings for Requesty yet.
What’s changed
Free accountSignals
Free accountData and security
Free accountCompare with similar tools
Free accountWhere this comes from
How we research- Company website
- requesty.ai: product, pricing and policy pages
- Social accounts
- Accounts the company links, and its posts on X
- Human review
- Checked by a person
- knowledge_base
- manual_review
Last checked 30 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.