Requesty

Best for: Prototypes and side projects - free to start, no sales call; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box

Pricing model

Usage-based [2]requesty.ai/pricing“Requesty charges a 5% markup on base model costs: a model that costs $10 per 1M tokens from OpenAI costs $10.50 through Requesty.”requesty.ai/pricing“No subscription, no seat fees, no minimum spend.”

Published pricing

✓ Yes [3]requesty.ai/pricing“5% markup on base model costs. No subscription, no seat fees, no minimum spend.”

Free tier

✓ Yes [4]requesty.ai/pricing“Access to all free models, 200 requests per day, routing, caching, spend tracking, and EU data residency included. No credit card required.”

Free tier details

Free tier with access to all free models and 200 requests per day; no credit card required. Includes routing, caching, spend tracking, and EU data residency. [5]requesty.ai/pricing“Access to all free models, 200 requests per day, routing, caching, spend tracking, and EU data residency included. No credit card required.”

Self-serve signup

✓ Yes [6]requesty.ai/pricing“No subscription, no seat fees, no minimum spend. Sign up at app.requesty.ai/sign-up”

Requires sales call

✗ No

Enterprise plan

✓ Yes [7]requesty.ai/pricing“Enterprise: Custom pricing. SSO integration (Okta, Azure AD, Google Workspace, custom OIDC), full RBAC with audit logs, approved model whitelists, team/group spend controls, guardrails, PII detection, dedicated support with custom SLAs.”

• Semantic caching
• Fallback / routing
• Spend controls
• Observability
• Guardrails

Supported actions

unified_chat_completions, openai_compatible_api, anthropic_compatible_api, model_routing, automatic_fallback, load_balancing, prompt_caching, spend_limits, budgets, rate_limiting, observability_logging, tracing, guardrails, pii_redaction, byo_provider_keys, rbac, model_whitelists, audit_logs, sso_integration, embeddings_routing, image_generation_routing, text_to_speech_routing, speech_to_text_routing, geo_based_routing, mcp_gateway, request_metadata_tagging, semantic_caching [8]docs.requesty.ai/quickstart“Fallback Routing, Auto-Caching, Usage Analytics, Load Balancing, Bring Your Own Keys, Guardrails & RBAC, EU Routing, Request Metadata, Streaming”requesty.ai/enterprise“Role-Based Access Control with four permission levels (Owner, Admin, Member, Viewer). Teams & Groups for organizing users by department/project with per-group budgets and rate limits.”

Regions

EU (Frankfurt), US (Virginia), APAC (Singapore) [9]requesty.ai/enterprise“Geo-based routing (Frankfurt for EU, Virginia for US, Singapore for APAC). EU data stays in Frankfurt, US data in Virginia, APAC in Singapore. Full data sovereignty with zero cross-border transfers.”

Input types

chat completions, embeddings, image generation, text to speech, speech to text, model listing [10]docs.requesty.ai/api-reference/inference-apis“Chat - Generate text completions and conversations using OpenAI Chat Completions, Anthropic Messages, or the Responses API. Embeddings - Vector embeddings for semantic search and RAG applications. Text to Speech - Converting text into spoken audio. Speech to Text - Transcribing audio files to text. Images - Generate and edit images using DALL-E, Stable Diffusion, and other image models.”

Output types

OpenAI-compatible JSON response, streaming (SSE), Anthropic-compatible response

Webhooks

✗ No

Sandbox / test mode

✗ No

SDK languages

Python, Node.js, Node.js / TypeScript [11]docs.requesty.ai/quickstart“Python (OpenAI SDK), TypeScript/JavaScript (OpenAI SDK), cURL (HTTP). Compatible with frameworks: LangChain, Vercel AI SDK, LlamaIndex, Haystack, Pydantic AI, Axios, Requests”

MCP server

✓ Yes [12]docs.requesty.ai/features/mcp-gateway“The MCP (Model Context Protocol) Gateway enables AI coding assistants like Claude Code, Cursor, and Roo Code to securely connect to MCP servers through Requesty's unified API.”

SOC 2

In progress [13]requesty.ai/security“SOC 2 Type II - In progress - expected Q2 2026”requesty.ai/enterprise“SOC 2 Type II — Certified. Audited annually by independent third party.”

HIPAA

– Unknown [14]requesty.ai/security“Certifications listed: GDPR Compliant, SOC 2 Type II (in progress). No mention of HIPAA.”

GDPR

✓ Yes [15]requesty.ai/security“GDPR Compliant - Full compliance with EU data protection regulations”requesty.ai/dpa“Requesty provides a DPA covering GDPR Article 28 processor obligations for all traffic routed through the gateway.”

ISO 27001

– Unknown [16]requesty.ai/enterprise“ISO 27001 - In progress - Expected Q2 2026, last audit January 2026”

PCI DSS

– Unknown

Published SLA

✓ Yes [17]requesty.ai/enterprise“99.99% uptime SLA”requesty.ai/enterprise“Automatic failover with <20ms switching and 99.99% uptime SLA”

Rate limits

Free tier: 200 requests per day. Requesty does not impose its own rate limits on paid plans; per-key, per-team, and per-model limits are configurable by the user. [18]requesty.ai/pricing“Free tier capped at 200 requests daily”docs.requesty.ai/features/api-limits“Requesty does not impose its own rate limits on your requests.”

Known restrictions

Free tier capped at 200 requests per day and limited to free models only, Pay-as-you-go tier adds a 5% markup on base model costs, Enterprise pricing requires contacting sales, SOC 2 Type II certification in progress (expected Q2 2026 per security page, contradicted by certified claim on enterprise page), No webhooks documented, No sandbox/test environment - free tier serves as the live environment

• Docs
• llms.txt
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://router.requesty.ai/v1

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Idempotency keys

✗ No

Error format

vendor-specific

SDKs

• Python openai · repo
• Node.js openai · repo
• Node.js / TypeScript @requesty/ai-sdk · repo

• Auth docs
• Quickstart
• MCP server

Launched

2023-01-01

Notable customers

Shopify, Amadeus, Chargebee, Contentful, Demandbase, Pfizer, PWC, Capgemini, Sage, Siemens, Appnovation

• Vercel AI Gateway

  "AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks."

  Usage · free tier · public pricing · self-serve

• Portkey

  "Production Stack for Gen AI Builders"

  Hybrid · free tier · public pricing · self-serve

• Bifrost (Maxim AI)

  "The fastest, most resilient, enterprise-grade LLM, MCP, and agent gateway."

  Sales-led · free tier · public pricing · self-serve

• Cloudflare AI Gateway

  "Connect to any model, dynamically route requests, and manage usage, billing, and logs from one unified gateway."

  Hybrid · free tier · public pricing · self-serve

• TrueFoundry AI Gateway

  "A unified AI gateway to securely manage and govern AI across 1600+ models with policy control, real-time monitoring, and up to 30% cost reduction."

  Hybrid · free tier · public pricing · self-serve

• Helicone

  "Open-source LLM observability and monitoring platform for developers" - routes, debugs, and analyzes AI applications with access to 100+ models through one API with built-in observability, automatic fallbacks, and zero markup pricing.

  Hybrid · free tier · public pricing · self-serve

Requesty alternatives · Requesty vs Vercel AI Gateway · All AI Gateway & LLM Routing APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: requesty.ai
2. ↑Pricing model: requesty.ai · requesty.ai
3. ↑Published pricing: requesty.ai
4. ↑Free tier: requesty.ai
5. ↑Free tier details: requesty.ai
6. ↑Self-serve signup: requesty.ai
7. ↑Enterprise plan: requesty.ai
8. ↑Supported actions: docs.requesty.ai · requesty.ai
9. ↑Regions: requesty.ai
10. ↑Input types: docs.requesty.ai
11. ↑SDK languages: docs.requesty.ai
12. ↑MCP server: docs.requesty.ai
13. ↑SOC 2: requesty.ai · requesty.ai
14. ↑HIPAA: requesty.ai
15. ↑GDPR: requesty.ai · requesty.ai
16. ↑ISO 27001: requesty.ai
17. ↑Published SLA: requesty.ai · requesty.ai
18. ↑Rate limits: requesty.ai · docs.requesty.ai

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"guardrails":true,"observability":true,"spend_controls":true,"fallback_routing…
2. 2026-06-21 Summary Md: (none) → Requesty is a unified AI gateway and LLM router that provides a single OpenAI-c…
3. 2026-06-21 Score Setup Speed: (none) → 85
4. 2026-06-21 Score Docs Quality: (none) → 25
5. 2026-06-21 Score Procurement Friction: (none) → 90
6. 2026-06-21 Score Trust Readiness: (none) → 43
7. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, AI agents and auto…
8. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
9. 2026-06-21 Score Agent Friendliness: (none) → 55
10. 2026-06-21 Score Pricing Transparency: (none) → 75
11. 2026-06-21 Llms Txt Present: (none) → Yes
12. 2026-06-21 Rendering: (none) → static
13. 2026-06-21 Has Structured Data: (none) → Yes
14. 2026-06-21 Robots Allows Agents: (none) → No
15. 2026-06-21 Status Page URL: (none) → https://status.requesty.ai
16. 2026-06-21 Docs URL: (none) → https://docs.requesty.ai/quickstart
17. 2026-06-21 Llms Txt URL: (none) → https://www.requesty.ai/llms.txt
18. 2026-06-21 Has Published Pricing: set to Yes
19. 2026-06-21 Free Tier Available: set to Yes
20. 2026-06-21 Free Tier Details: set to Free tier with access to all free models and 200 requests per day; no credit ca…
21. 2026-06-21 Self Serve Signup: set to Yes
22. 2026-06-21 Requires Sales Call: set to No
23. 2026-06-21 Enterprise Plan Available: set to Yes
24. 2026-06-21 SOC 2: set to in_progress
25. 2026-06-21 GDPR: set to Yes
26. 2026-06-21 SLA Published: set to Yes
27. 2026-06-21 SLA URL: set to https://www.requesty.ai/enterprise
28. 2026-06-21 Data Retention Policy URL: set to https://www.requesty.ai/privacy
29. 2026-06-21 Documented Rate Limits: set to Free tier: 200 requests per day. Requesty does not impose its own rate limits o…
30. 2026-06-21 Known Restrictions: set to Free tier capped at 200 requests per day and limited to free models only, Pay-a…
31. 2026-06-21 Auth Methods: set to api_key
32. 2026-06-21 Auth Docs URL: set to https://docs.requesty.ai/quickstart
33. 2026-06-21 API Style: set to rest
34. 2026-06-21 Base URL: set to https://router.requesty.ai/v1
35. 2026-06-21 API Version: set to v1
36. 2026-06-21 Versioning Scheme: set to url
37. 2026-06-21 Stability: set to ga
38. 2026-06-21 MCP URL: set to https://router.requesty.ai/mcp
39. 2026-06-21 Quickstart URL: set to https://docs.requesty.ai/quickstart
40. 2026-06-21 Idempotency Supported: set to No
41. 2026-06-21 Error Format: set to vendor-specific
42. 2026-06-21 Requires Verification: set to No
43. 2026-06-21 Slug: set to requesty
44. 2026-06-21 Free Tier Limit: set to 200 requests/day on free models
45. 2026-06-21 Launched At: set to 2023-01-01
46. 2026-06-21 Notable Customers: set to Shopify, Amadeus, Chargebee, Contentful, Demandbase, Pfizer, PWC, Capgemini, Sa…
47. 2026-06-21 Fields Not Found: set to hipaa, iso_27001, pci_dss, webhooks_supported, sandbox_available, documented_ra…
48. 2026-06-21 Source Confidence: set to high
49. 2026-06-21 Extractor: set to claude-subagent:sonnet
50. 2026-06-21 Last Verified At: set to 2026-06-21T00:00:00.000Z

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/requesty \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/requesty/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →