- Home
- LLM Gateway Software
- Requesty
Requesty
London, United Kingdom
What it is
Requesty is an AI gateway for using 600+ models through one OpenAI-compatible API. Existing SDK code can connect by changing its base URL and API key. Its routing options include policies, regional routing, automatic failover and load balancing. Cost tracking and analytics can be viewed by model, user and team, alongside latency and usage monitoring. Governance tools 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, plus tools such as Claude Code, Cline, VS Code, Codex and n8n. Requesty offers API and web access as a managed platform; self-hosting is not offered. The Free plan is free and includes 200 requests per day. Pay as you go costs $5 a month, with a 5% markup on model cost. Enterprise pricing is custom. The service lists email support for Pay as you go and dedicated support with custom SLAs for Enterprise.
For and against
For
- OpenAI-compatible API can work with existing SDK code.
- Offers routing policies, regional routing and automatic failover.
- Tracks cost, latency and usage across models and teams.
- Free plan includes 200 requests per day.
- EU data residency is available.
Against
- Self-hosting is not offered.
- Pay as you go costs $5 a month.
- That plan also applies a 5% markup on model cost.
- Prompt and output logging is on by default for self-serve plans.
The verdict
Requesty brings model access, routing, analytics and governance into a managed gateway, with a free plan and paid options. Review its self-serve logging defaults and pay-as-you-go markup when deciding whether it fits your deployment and cost requirements.
Who it suits
Requesty suits developers and teams that want to connect applications to multiple models through one API and manage routing, usage and governance centrally. Teams needing a self-hosted deployment should note that this is a managed platform.
Plans and prices
Free
free models · 200 requests/day · routing, caching and fallbacks · spend analytics
Read 21 Oct 2026 · requesty.ai
Enterprise
SSO/OIDC · RBAC and audit logs · approved models · teams and budgets
Read 21 Oct 2026 · requesty.ai
Pay as you go
600+ models · BYOK · routing policies · caching and fallbacks
Read 21 Oct 2026 · requesty.ai
On the record
- 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 · read 21 Oct 2026
- Analytics
- Analytics attribute cost and latency by model, team, user, key and custom request metadata.requesty.ai · read 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 · read 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 · read 21 Oct 2026
- Caching
- Automatic prompt caching is offered, with the company claiming savings of up to 90% on repeated context.requesty.ai · read 21 Oct 2026
- CLI licence
- The published Requesty CLI repository is licensed under MIT.github.com · read 21 Oct 2026
- Company founding
- LinkedIn lists Requesty as founded in 2023.uk.linkedin.com · read 21 Oct 2026
- Company headquarters
- LinkedIn lists London, England as headquarters and company size of 2–10 employees.uk.linkedin.com · read 21 Oct 2026
- Company legal name
- Crunchbase identifies the legal entity as Requesty Ltd.crunchbase.com · read 21 Oct 2026
- Company register
- Dealroom lists company register number 15165717 and a 2023 launch date.app.dealroom.co · read 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 · read 30 Sep 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 · read 30 Sep 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 · read 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 · read 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 · read 21 Oct 2026
- EU processing
- An EU gateway runs in Frankfurt on AWS eu-central-1 at router.eu.requesty.ai.requesty.ai · read 21 Oct 2026
- EU residency
- Requesty identifies Frankfurt as its EU gateway location and says EU requests can be routed there.requesty.ai · read 30 Sep 2026
- Fallback routing
- Policies can retry failed or timed-out requests on backup models without application retry code.docs.requesty.ai · read 21 Oct 2026
