Requesty
What Requesty is
Requesty is a managed AI gateway that connects applications to 600+ models through one OpenAI-compatible API. Existing SDK code can work by changing the base URL and API key. Its routing includes policy and regional rules, automatic failover and load balancing. Requesty tracks cost, latency and usage, with analytics by model, user and team. Governance features 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; listed tools also include Claude Code, Cline, VS Code, Codex, n8n and LibreChat. The Free plan costs nothing and includes 200 requests per day. Pay as you go is $5 a month, billed with a 5% markup on model cost. Enterprise pricing is custom. 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. The service is available through web and API, but self-hosting is not offered.
Who it suits
Requesty suits developers and teams connecting applications to multiple AI models through a shared API. Its team analytics, routing policies and governance features may also suit organizations that need centralized oversight of model use.
What it does well
- Access to 600+ models through one API
- Includes routing, failover and load balancing
- Tracks costs, latency and usage
- Free plan allows 200 requests per day
- Offers EU routing and data residency
What to know first
- Self-hosting is not offered
- Self-serve prompt and output logging is on by default
- Pay as you go adds a 5% markup on model cost
Limits
The Free plan allows 200 requests per day. Pay as you go costs $5 a month and adds a 5% markup on model cost.
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Free | no credit card required · free models · 200 requests/day · routing, caching and fallbacks · spend analytics · EU residency | Free |
| Pay as you go | 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 | On request |
| Enterprise | custom pricing · SSO/OIDC · RBAC and audit logs · approved models · teams and budgets · guardrails and PII detection · service accounts · dedicated support · custom SLAs | On request |
As requesty.ai lists them, read 21 Oct 2026. The maker's own page has the final word.
Getting started
- Open Requesty's website or connect through its API.
- Choose the Free plan, which requires no credit card, or select Pay as you go.
- For existing OpenAI SDK code, change the base URL and API key.
- Use a named SDK or framework integration, such as LangChain or Vercel AI SDK.
Verdict
Requesty combines model access, routing, usage analytics and governance in a managed gateway. Check its logging defaults and pricing structure against your needs before choosing a plan.
Questions
Does Requesty have a free plan?
Yes. The Free plan costs nothing, includes 200 requests per day, and requires no credit card.
How much does Pay as you go cost?
It costs $5 a month and bills a 5% markup on model cost.
Which platforms does Requesty support?
Requesty lists API and web platforms.
Can I use existing OpenAI SDK code?
Yes. Existing SDK code can work by changing the base URL and API key.
Can Requesty be self-hosted?
No. Requesty is a managed platform and does not offer self-hosting.
What security and data retention details are provided?
Traffic is encrypted with TLS 1.2 or higher, and data at rest with AES-256. On self-serve plans, prompt and output logging is on by default and retained in encrypted form in the EU for up to 30 days; it can be disabled per key.
Facts from Requesty's own pages
- 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. · requesty.ai, 21 Oct 2026
- Analytics
- Analytics attribute cost and latency by model, team, user, key and custom request metadata. · requesty.ai, 21 Oct 2026
- 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. · requesty.ai, 21 Oct 2026
- API surface
- Documentation describes inference endpoints for chat, embeddings, audio, images and model listing plus management APIs for keys, groups, members and organization settings. · docs.requesty.ai, 21 Oct 2026
- Caching
- Automatic prompt caching is offered, with the company claiming savings of up to 90% on repeated context. · requesty.ai, 21 Oct 2026
- CLI licence
- The published Requesty CLI repository is licensed under MIT. · github.com, 21 Oct 2026
- Company founding
- LinkedIn lists Requesty as founded in 2023. · uk.linkedin.com, 21 Oct 2026
- Company headquarters
- LinkedIn lists London, England as headquarters and company size of 2–10 employees. · uk.linkedin.com, 21 Oct 2026
- Company legal name
- Crunchbase identifies the legal entity as Requesty Ltd. · crunchbase.com, 21 Oct 2026
- Company register
- Dealroom lists company register number 15165717 and a 2023 launch date. · app.dealroom.co, 21 Oct 2026
- Compatibility
- Its API is OpenAI-compatible, and the site says existing SDK code can work by changing the base URL and API key. · requesty.ai, 30 Sept 2026
- 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. · requesty.ai, 30 Sept 2026
- 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. · requesty.ai, 21 Oct 2026
- 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. · requesty.ai, 21 Oct 2026
- Developer documentation
- The quickstart includes Python, TypeScript and cURL examples, response headers, request metadata, fallback policies and Anthropic SDK routing. · docs.requesty.ai, 21 Oct 2026
- EU processing
- An EU gateway runs in Frankfurt on AWS eu-central-1 at router.eu.requesty.ai. · requesty.ai, 21 Oct 2026
- EU residency
- Requesty identifies Frankfurt as its EU gateway location and says EU requests can be routed there. · requesty.ai, 30 Sept 2026
- Fallback routing
- Policies can retry failed or timed-out requests on backup models without application retry code. · docs.requesty.ai, 21 Oct 2026
- Funding
- Crunchbase lists one seed funding round with three investors, including The Twenty Minute VC and Tapestry VC, but obscures the amount. · crunchbase.com, 21 Oct 2026
- Governance
- The site describes PII detection and scrubbing, content guardrails, team roles, model allowlists and audit logs. · requesty.ai, 30 Sept 2026
- Headquarters
- London, United Kingdom · requesty.ai, 28 Sept 2026
- 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. · requesty.ai, 21 Oct 2026
- Independent listing usage
- Appz lists Requesty as a web developer tool and reports zero people using it on that directory. · appz.com, 21 Oct 2026
- 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. · naivigate.com, 21 Oct 2026
Where Requesty stands on Freedom251
- Byok System#12 of 24
- LLM gateways#17 of 33
- LLM Gateway Software#19 of 34