Skip to content
SPECIFICTION
Get listed

Requesty

requesty.ai

Free plan WebAPIBrowser extension
Visit requesty.ai
Spec score 8.5 #8 of 33 in LLM gateways

What it is

Requesty is a managed AI gateway that gives applications access to more than 600 models through one API. Its OpenAI-compatible API can work with existing SDK code after changing the base URL and API key. Routing features include policy and regional rules, automatic failover and load balancing. Requesty tracks cost, latency and usage, with analytics by model, user and team. Governance options include PII detection and scrubbing, content guardrails, team roles, model allowlists and audit logs. Named integrations include OpenAI, LangChain, PydanticAI, Vercel AI SDK, Haystack and LlamaIndex TS; the integrations page also lists tools such as Claude Code, Cline, VS Code, GitHub Copilot, Codex, n8n, LibreChat and OpenWebUI. The Free plan costs nothing and allows 200 requests per day. Pay as you go costs $5 a month, with a 5% markup on model cost. Enterprise pricing is custom. Requesty is available via API and web; self-hosting is not offered.

Spec sheet

What it does
Requesty is an AI gateway that places one OpenAI-compatible endpoint in front of more than 600 language models.Read 21 Oct 2026 · requesty.ai
Product
Requesty describes itself as an AI gateway that provides access to 600+ models through one API with routing, analytics and centralized governance.Read 30 Sep 2026 · requesty.ai
Integrations
Official integration guidance covers OpenAI SDK, LangChain, PydanticAI, Vercel AI SDK, Haystack, LlamaIndex, Axios and plain HTTP.Read 21 Oct 2026 · requesty.ai
Security
The security page states that traffic is encrypted with TLS 1.2 or higher and data at rest with AES-256.Read 30 Sep 2026 · requesty.ai
Compliance
The security page says its SOC 2 Type II programme is in progress and that it provides a GDPR Article 28 DPA on request.Read 30 Sep 2026 · requesty.ai
Support
The pricing page lists email support for Pay as you go and dedicated support with custom SLAs for Enterprise.Read 30 Sep 2026 · requesty.ai
Headquarters
London, United KingdomRead 28 Sep 2026 · requesty.ai
Agent tools
The integrations page lists Claude Code, Claude Cowork, Cline, Roo Code, VS Code, GitHub Copilot, Codex, OpenCode, OpenClaw, Pi, Anthropic SDKs, DeepSeek, n8n, LibreChat and OpenWebUI.Read 21 Oct 2026 · requesty.ai
Analytics
Analytics attribute cost and latency by model, team, user, key and custom request metadata.Read 21 Oct 2026 · requesty.ai
API compatibility
The official Python and JavaScript OpenAI packages can be used by changing the base URL and API key, with no Requesty-specific SDK required.Read 21 Oct 2026 · requesty.ai
API surface
Documentation describes inference endpoints for chat, embeddings, audio, images and model listing plus management APIs for keys, groups, members and organization settings.Read 21 Oct 2026 · docs.requesty.ai
Caching
Automatic prompt caching is offered, with the company claiming savings of up to 90% on repeated context.Read 21 Oct 2026 · requesty.ai
CLI licence
The published Requesty CLI repository is licensed under MIT.Read 21 Oct 2026 · github.com
Company founding
LinkedIn lists Requesty as founded in 2023.Read 21 Oct 2026 · uk.linkedin.com
Company headquarters
LinkedIn lists London, England as headquarters and company size of 2–10 employees.Read 21 Oct 2026 · uk.linkedin.com
Company legal name
Crunchbase identifies the legal entity as Requesty Ltd.Read 21 Oct 2026 · crunchbase.com
Company register
Dealroom lists company register number 15165717 and a 2023 launch date.Read 21 Oct 2026 · app.dealroom.co
Compatibility
Its API is OpenAI-compatible, and the site says existing SDK code can work by changing the base URL and API key.Read 30 Sep 2026 · requesty.ai
Compliance status
Requesty states that its SOC 2 Type II program is in progress, offers a GDPR Article 28 DPA on request and supports EU data residency.Read 21 Oct 2026 · requesty.ai
Data retention
Prompt and output logging is enabled by default for self-serve plans for up to 30 days in the EU, with per-key disablement and organization-wide zero-retention available on request.Read 21 Oct 2026 · requesty.ai
Developer documentation
The quickstart includes Python, TypeScript and cURL examples, response headers, request metadata, fallback policies and Anthropic SDK routing.Read 21 Oct 2026 · docs.requesty.ai
EU processing
An EU gateway runs in Frankfurt on AWS eu-central-1 at router.eu.requesty.ai.Read 21 Oct 2026 · requesty.ai
EU residency
Requesty identifies Frankfurt as its EU gateway location and says EU requests can be routed there.Read 30 Sep 2026 · requesty.ai
Fallback routing
Policies can retry failed or timed-out requests on backup models without application retry code.Read 21 Oct 2026 · docs.requesty.ai
Funding
Crunchbase lists one seed funding round with three investors, including The Twenty Minute VC and Tapestry VC, but obscures the amount.Read 21 Oct 2026 · crunchbase.com
Governance
The site describes PII detection and scrubbing, content guardrails, team roles, model allowlists and audit logs.Read 30 Sep 2026 · requesty.ai
Hosted deployment
Requesty presents itself as a gateway service reached through router.requesty.ai and regional endpoints; no self-hosted server package is documented on the official pages reviewed.Read 21 Oct 2026 · requesty.ai
Independent listing usage
Appz lists Requesty as a web developer tool and reports zero people using it on that directory.Read 21 Oct 2026 · appz.com
Independent technical assessment
nAIvigate describes Requesty as a hosted router with cost optimization, guardrails, audit logs and EU routing, using the OpenAI-compatible base URL.Read 21 Oct 2026 · naivigate.com
Limit: product maturity
A G2 reviewer described the platform as early stage and said it needed more development and features.Read 21 Oct 2026 · g2.com
Load balancing
Routing policies support weighted load balancing and latency-based selection, and policies can be nested.Read 21 Oct 2026 · requesty.ai
Model access
The service exposes models from more than 30 providers through a common request shape.Read 21 Oct 2026 · requesty.ai
Notable news
Requesty's blog lists a September 2025 announcement that the company raised $3 million to build its developer gateway.Read 21 Oct 2026 · requesty.ai
Observability
Requesty offers real-time cost tracking and analytics by model, user and team, plus latency and usage monitoring.Read 30 Sep 2026 · requesty.ai
Praise: insight generation
G2 reviewers praised the product for turning conversational data into actionable customer and product insights.Read 21 Oct 2026 · g2.com
Praise: time savings
G2 reviewers said Requesty reduced the time needed to process and categorize user feedback.Read 21 Oct 2026 · g2.com
Prompt library
Prompts can be stored as versioned IDs with variables, shared across teams and changed without a deployment.Read 21 Oct 2026 · requesty.ai
Public SDKs and tools
Requesty's GitHub organization publishes a Python API library, Vercel AI SDK package, CLI, LibreChat integration and n8n node.Read 21 Oct 2026 · github.com
Rating on Buyersprove
0 out of 5 from 0 reviews; the listing shows a 0.0 ProveScore.Read 21 Oct 2026 · buyersprove.com
Rating on G2
5 out of 5 from 3 reviews; G2 says there are not enough reviews to provide buying insight.Read 21 Oct 2026 · g2.com
Retention
Prompt and output logging is on by default on self-serve plans and retained for up to 30 days in encrypted form in the EU; it can be disabled per key, and organization-wide zero data retention is available on written request.Read 30 Sep 2026 · requesty.ai
Routing
The gateway supports policy-based routing, regional routing, automatic failover and load balancing.Read 30 Sep 2026 · requesty.ai
Security encryption
The security page states TLS 1.2 or higher in transit and AES-256 encryption at rest.Read 21 Oct 2026 · requesty.ai
Self-hosting
The enterprise page says Requesty is a managed platform and self-hosting is not offered.Read 30 Sep 2026 · requesty.ai
Service status
The official status page reported all services operational on 21 October 2026, with 100% uptime shown for listed APIs over the prior 30 days.Read 21 Oct 2026 · status.requesty.ai
Spend controls
Budgets can be enforced per API key, user, team and organization, with email or webhook alerts.Read 21 Oct 2026 · requesty.ai
VS Code requirement
The Requesty Router VS Code extension requires a valid Requesty API key and VS Code 1.74.0 or newer.Read 21 Oct 2026 · marketplace.visualstudio.com

Plans and prices

Free Free no credit card required free models · 200 requests/day · routing, caching and fallbacks · spend analytics · EU residency Read 21 Oct 2026 · requesty.ai
Enterprise Priced on request custom pricing SSO/OIDC · RBAC and audit logs · approved models · teams and budgets · guardrails and PII detection · service accounts · dedicated support · custom SLAs Read 21 Oct 2026 · requesty.ai
Pay as you go Price not published 5% markup on model cost; usage based 600+ models · BYOK · routing policies · caching and fallbacks · spend caps · MCP Gateway · EU residency · advanced observability · email support Read 21 Oct 2026 · requesty.ai

Every Requesty plan and price →

Strong points and limits

Strong points

  • Access to more than 600 models through one API
  • Includes routing, failover and load balancing
  • Tracks cost and usage by model, user and team
  • Free plan allows 200 requests per day

Limits

  • Self-hosting is not offered
  • Pay as you go adds a 5% markup on model cost
  • Enterprise pricing is custom

Who it suits

Requesty may suit developers and teams that want one gateway for model access, routing and usage visibility. Its governance options and custom enterprise plan also address teams managing access and policies.

Verdict

Requesty brings model access, routing and governance into a managed gateway. Its free tier has a daily request limit, while paid usage adds a markup on model costs.

Where Specifiction places it

Alternatives to RequestyAll alternatives →