Requesty
Requesty is a London-based AI gateway platform that provides developers and enterprises with a single OpenAI-compatible API to access 400+ large language models from 20+ providers, featuring intelligent routing, automatic caching and failover, EU data residency, and enterprise governance for customers including ZoomInfo, Pfizer, PwC, and Siemens.
- Company typePrivate
- Founded2023
- HeadquartersLondon, United Kingdom
- Headcount1–10
- GTM typeB2B
- OfferingSoftware
What Requesty does
Requesty Ltd is a London-based private company that operates a unified AI gateway platform providing developers and enterprises with a single OpenAI-compatible API to access more than 400 large language models from 20+ providers, including OpenAI, Anthropic, Google, Mistral, xAI, and DeepSeek. Founded in 2023 and pivoting to the LLM gateway product in 2025, the platform is built on a micro-service architecture with the core gateway in Go and auxiliary ML services in Python, hosted on AWS across Frankfurt (EU), Virginia (US), and Singapore (APAC) regions. Core technical capabilities include intelligent model routing based on cost, latency, and quality; automatic semantic prompt caching with platform-wide hit rates up to 86% for coding agents; sub-20ms cross-provider automatic failover; real-time cost, latency, and per-agent observability; and an MCP Gateway for Model Context Protocol integrations.
The product is organized into three tiers — a Free tier offering 200 requests per day on free models, a pay-as-you-go tier charging a 5% markup on provider token costs, and a custom-priced Enterprise tier with SSO, full RBAC across a 5-layer policy hierarchy, audit logs, PII detection and scrubbing, content guardrails, geo-based routing with EU data residency, and 99.99% uptime SLAs. The company holds SOC 2 Type II certification, is fully GDPR compliant with an Article 28 DPA, offers HIPAA compliance, and is pursuing ISO 27001 certification expected Q2 2026. Since the 2025 pivot, Requesty has onboarded 25,000+ developers, reached $1.5 million in ARR, and serves a customer base that includes ZoomInfo, Pfizer, PwC, Siemens, Amadeus, Shopify, Mozart AI, NotarBot, Soccerment, Amberscript, and LOUPZ, with native OAuth integrations into the Cursor, Cline, and Continue AI coding agents.
Requesty firmographics
Firmographics- Name
- Requesty
- Legal name
- Requesty Ltd
- Website
- https://requesty.ai
- Company type
- Private
- Founded year
- 2023
- Operating status
- Operating
- Headcount range
- 1–10 employees
- Short description
- Requesty is a London-based AI gateway platform that provides developers and enterprises with a single OpenAI-compatible API to access 400+ large language models from 20+ providers, featuring intelligent routing, automatic caching and failover, EU data residency, and enterprise governance for customers including ZoomInfo, Pfizer, PwC, and Siemens.
- Ownership category
- akta.pro rank
Requesty industry classification
Industry- Product category
- AI Infrastructure / LLM Gateway
- NAICS
- Computer Systems Design and Related Services (5415), Computer Systems Design and Related Services (54151), Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services (5182)
- SIC
- Services-Computer Programming, Data Processing, Etc. (7370), Services-Computer Integrated Systems Design (7373), Services-Prepackaged Software (7372)
- akta.pro industry
- Model Hosting, Serving & Inference PlatformsHardware, Technology & Telecom/Artificial Intelligence & Machine Learning/Foundation Models & Generative AI (LLMs, multimodal)Enterprise Foundation Model Integration & APIs (Connectors, Governance, Deployment)Hardware, Technology & Telecom/Artificial Intelligence & Machine Learning/Foundation Models & Generative AI (LLMs, multimodal)
Keywords
Where Requesty is headquartered
LocationHeadquarters
- HQ city
- London
- HQ country
- United Kingdom
- HQ region
- Europe
Offices4 records
Markets served
Requesty business model
Business model- GTM type
- B2B
- Offering type
- Software
- Cost components
- Technology or R&D, Infrastructure, Personnel, Marketing or Sales, Operations
Revenue model
- Usage-based token markup: Primary revenue stream. Requesty charges a 5% markup on base model token costs. Customers pay the provider's list price plus 5%. For example, a model costing $10 per 1M tokens through OpenAI costs $10.50 through Requesty. Pay-as-you-go with no minimum commitment, no seat fees, no subscriptions.
- Enterprise custom contracts: Custom enterprise pricing for teams requiring SSO, full RBAC, dedicated support, custom SLAs, and volume discounts. Revenue derived from annual or multi-year contracts with enterprise accounts. Contact-based sales with founders and sales team.
Pricing tiers
| Model | Billing | Price |
|---|---|---|
| Freemium | Pay-as-you-go | Free tier with 200 requests/day on free models |
| Usage-based | Pay-as-you-go | Pay-as-you-go with 5% markup on all 400+ models |
| Subscription | Multi-year contract | Custom enterprise plan with SSO, RBAC, and custom SLAs |
Go-to-market motion3 records
Distribution channels4 records
Marketing channels6 records
Requesty product offering
Product offeringCore offering
Requesty is a unified AI gateway that provides developers and engineering teams with a single OpenAI-compatible API to access 400+ large language models from 20+ providers. The platform delivers intelligent routing across models based on cost, latency, and quality, automatic cross-provider failover, prompt caching that cuts token costs by up to 90%, and real-time observability. It also includes enterprise governance features such as a 5-layer RBAC policy engine, PII detection and scrubbing, content guardrails, and multi-region data residency with a dedicated EU gateway hosted in Frankfurt for GDPR compliance.
Product overview
Requesty is a unified AI gateway platform providing access to 400+ LLM models through a single OpenAI-compatible API. The core product is the Requesty AI Gateway, which includes smart routing, automatic failover, prompt caching, and enterprise governance. The platform is organized into three tiers: Free Tier (200 requests/day on free models), Pay-as-you-go (5% markup on 400+ models), and Enterprise (custom pricing with SSO, RBAC, and custom SLAs). Additional modules include the MCP Gateway for Model Context Protocol integrations, and the EU AI Gateway for GDPR-compliant European data residency hosted in Frankfurt. The platform integrates with development frameworks (LangChain, LlamaIndex) and AI coding tools (Cursor, Claude Code, Continue, Cline).
Differentiator
Problem solved
Functional benefit
Products and services
- Requesty AI Gateway
Quantifiable outcome
- Up to 40-60% cost reduction through prompt caching
- +5 more outcomes
Companies that use Requesty
Customer profileNamed customers6 records
Segments5 records
Ideal customer profiles4 records
Requesty technology and API
TechnologyTechnology focussed Yes
API detail
- Has API
- Yes
- API docs
- API detail
Core technology
AI maturity
App detail
Integration10 records
AI capability8 records
Feature10 records
Requesty partnerships and signals
Strategic signalPartnerships
Ten partnerships are on record, tiered core.
- OpenAI Inc.corePrimary model provider integrated into the gateway. Prompts and model outputs transmitted securely to OpenAI for processing. Data retained by OpenAI for 30 days per their privacy policy.
- Anthropic PBCcorePrimary model provider (Claude family) integrated into the gateway. Prompts and model outputs transmitted securely for Claude inference. Data retained by Anthropic for 30 days.
- Google LLC (Gemini API & Vertex AI)coreGemini models available via both the consumer Gemini API and Google Vertex AI EU regions. Vertex AI EU deployments used for GDPR-compliant routing. No data retention on Vertex AI.
- Microsoft Azure AIcoreAzure OpenAI EU regions (France Central, Sweden Central, UK South) used for GPT models with EU data residency. No data retention on Azure. Alternative to direct OpenAI API for compliance-sensitive workloads.
- AWS BedrockcoreClaude EU-region deployments on Bedrock (eu-central-1 Frankfurt, eu-west-1 Ireland, eu-west-3 Paris, eu-north-1 Stockholm) used for Claude models with EU data residency. No data retention on Bedrock. Infrastructure provider also.
- Mistral AI SAScoreEuropean AI company with EU-hosted inference via La Plateforme. Mistral models (Large, Medium, Small, Pixtral, Codestral, Devstral) routed through Frankfurt gateway with full EU data residency. Data retained by Mistral for 30 days.
- AWS (Infrastructure)corePrimary cloud infrastructure provider (compute, storage, networking) hosting the Requesty platform and databases. All primary infrastructure runs on AWS in Frankfurt, Germany (EU Central 1) for EU operations.
- CursorcoreNative OAuth integration with Cursor AI code editor. Unlimited requests, no rate limits for Requesty users. Cursor users can route through Requesty gateway for multi-model access and cost optimization.
- ClinecoreNative OAuth integration with Cline autonomous coding agent. Unlimited requests, no rate limits for Requesty users. Cline routes through Requesty for multi-provider access and failover.
- ContinuecoreNative OAuth integration with Continue AI coding extension. Unlimited requests, no rate limits for Requesty users. Continue users can route through Requesty gateway.
Scale indicators9 records
Recent moves6 records
Expansion highlights7 records
Requesty competitors and assessment
Company assessmentDirect peers
- OpenRouter: Direct competitor offering a unified API to route between hundreds of LLMs from many providers with pay-as-you-go pricing. Closest comparable to Requesty in model breadth, target customer, and OpenAI-compatible API model.
- Portkey: AI gateway focused on observability, governance, and routing for LLM applications. Targets the same enterprise and developer customers with overlapping features (caching, failover, policy controls).
- LiteLLM: Open-source LLM gateway and proxy with routing, fallbacks, and budget controls. Competes head-on with Requesty, particularly for enterprise buyers who prefer self-hosted deployments.
- Helicone: OpenAI-compatible observability and routing layer for LLM apps, with caching, cost tracking, and failover. Competes directly with Requesty on developer-facing gateway features.
Broad incumbents
- AWS Bedrock: AWS managed service offering foundation models from multiple providers with built-in governance, security, and EU regions. Competes as a broad incumbent with deep enterprise distribution.
- Cloudflare AI Gateway: Broad incumbent offering caching, rate limiting, and observability for LLM APIs as part of Cloudflare's edge network. Bundled with a much wider developer platform and competes on price and reliability.
- Azure AI Gateway / Azure OpenAI Service: Microsoft Azure's LLM access layer with EU regions, compliance, and enterprise controls. Competes on data residency and enterprise procurement leverage, particularly in regulated industries.
- Kong AI Gateway: Enterprise API gateway extended to LLM traffic with multi-provider routing, policy controls, and observability. Competes as a broad incumbent with established enterprise API management customers.
Emerging players
- Together AI: AI cloud platform offering model serving and inference APIs with some routing/orchestration features. Comparable in serving LLM workloads with cost-optimized infrastructure.
- Martian: LLM router that dynamically selects models per query based on performance and cost. Directly comparable as an intelligent-routing-focused emerging player in the LLM gateway category.
Market position
Strengths5 records
Weaknesses5 records
Competitive moat5 records
Key risks7 records
Key highlights7 records
Customer concentration
Requesty social profiles
Digital presenceRequesty compliance and trust
Trust signalCompliance5 records
Requesty financial estimates
Financial estimateRevenue estimate
Valuation estimate
Requesty leadership team
Management profileNumber of profiles
Profiles2 records
Requesty funding detail
Funding detailFunding overview
Funding rounds1 record
Investors3 records
Funding detail is available on the Subscription and Enterprise plan.Contact sales →
Requesty M&A and investment
M&A and investmentM&A
Investments
M&A and investment is available on the Subscription and Enterprise plan.Contact sales →
Frequently asked questions about Requesty
What does Requesty do?
Requesty is a unified AI gateway that provides developers and engineering teams with a single OpenAI-compatible API to access 400+ large language models from 20+ providers. The platform delivers intelligent routing across models based on cost, latency, and quality, automatic cross-provider failover, prompt caching that cuts token costs by up to 90%, and real-time observability. It also includes enterprise governance features such as a 5-layer RBAC policy engine, PII detection and scrubbing, content guardrails, and multi-region data residency with a dedicated EU gateway hosted in Frankfurt for GDPR compliance.
Is Requesty a public or private company?
Requesty is a private company. It is classified as venture growth investor backed and is currently operating.
When was Requesty founded?
Requesty was founded in 2023. It employs 1 to 10 people.
Where is Requesty based?
Requesty is headquartered in London, United Kingdom, in the Europe region.
How does Requesty make money?
Two revenue lines are on record. Usage-based token markup is the primary driver. The others are enterprise custom contracts.
Who are Requesty's main competitors?
Direct peers on record are OpenRouter, Portkey, LiteLLM and Helicone. Broad incumbents are AWS Bedrock, Cloudflare AI Gateway, Azure AI Gateway / Azure OpenAI Service and Kong AI Gateway. Emerging players are Together AI and Martian.
Does Requesty have an API?
Yes. Requesty provides an OpenAI-compatible API gateway that routes requests to 400+ LLM models from providers including OpenAI, Anthropic, Google, Mistral, DeepSeek, and others. Developers integrate by changing their base URL to router.requesty.ai/v1 and using their Requesty API key. The API supports streaming, structured outputs, and reasoning/extended thinking. Authentication uses API keys (req-... format). No provider accounts needed — one Requesty key works across all supported providers. Developer documentation is at docs.requesty.ai/quickstart.
What industry is Requesty in?
Requesty's product category is AI Infrastructure / LLM Gateway. Its primary akta.pro industry code is HDAAACAB, Model Hosting, Serving & Inference Platforms, with a secondary code of HDAAACAO, Enterprise Foundation Model Integration & APIs (Connectors, Governance, Deployment). Its NAICS code is 5415 and its SIC code is 7370.