OpenRouter

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Usage-based [2]openrouter.ai/pricing“Pay-as-you-go: 5.5% platform fee on top of model costs. Access to 400+ models from 70+ providers. No minimum spend.”openrouter.ai/blog/announcements/simplifying-our-platform-fee/“Non-crypto payments: 5.5% of the order amount, with a minimum fee of $0.80; Crypto payments: 5.0% flat, no minimum fee”

Published pricing

✓ Yes [3]openrouter.ai/pricing“5.5% platform fee on top of model costs... No minimum spend. Prices based on models”openrouter.ai/blog/announcements/simplifying-our-platform-fee/“Non-crypto payments: 5.5% of the order amount, with a minimum fee of $0.80”

Free tier

✓ Yes [4]openrouter.ai/docs/api/reference/limits“Free users have a limit of 50 requests per day and 20 requests per minute (rpm)”openrouter.ai/pricing“Free Plan: No platform fees. Includes 25+ free models across 4 providers. Limited to 50 requests/day with community support.”

Free tier details

Free plan with 25+ free models ($0 token cost, no platform fee) available without payment. Without prior credit purchase: 50 free model requests/day, 20 req/min. With $10+ credits purchased: 1,000 free model requests/day. Pay-as-you-go accounts also receive 1M free gateway requests/month before the 5.5% fee applies. [5]openrouter.ai/docs/api/reference/limits“If you have purchased at least 10 credits, your free model rate limit will be 1000 requests per day, otherwise you will be rate limited to 50 free model API requests per day”openrouter.ai/pricing“Free Plan: No platform fees. Includes 25+ free models across 4 providers. Limited to 50 requests/day with community support.”openrouter.ai/pricing“Pay-as-you-go: 1M free reqs/month, 5% fee after”

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]openrouter.ai/enterprise“OpenRouter is committed to being accretive to your uptime. Priority support channels with direct team access. GDPR compliance and SOC-2 certification.”openrouter.ai/pricing“Enterprise: 5M free reqs/month; custom pricing”

• Fallback / routing
• Spend controls
• Observability
• Guardrails

Supported actions

unified_chat_completions, openai_compatible_api, model_routing, automatic_fallback, load_balancing, response_caching, prompt_caching, spend_limits, budgets, rate_limiting, observability_logging, tracing, guardrails, pii_redaction, byo_provider_keys, provider_selection, zero_data_retention, eu_region_routing, structured_outputs, tool_calling, streaming_sse, web_search_plugin, embeddings, reranking, model_fallback_ordering, throughput_routing, latency_routing, price_routing, prompt_injection_protection, sso_saml, api_key_management, virtual_keys [7]openrouter.ai/docs/guides/features/guardrails“detect and redact or block sensitive information (PII) in API requests using built-in presets and NLP-based detection”openrouter.ai/docs/guides/routing/provider-selection“By default, requests are load balanced across the top providers to maximize uptime. You can customize how your requests are routed using the provider object in the request body”openrouter.ai/docs/guides/features/response-caching“Cache hits are free. No tokens are consumed and all billable usage counters are reported as 0”

Regions

US, EU (eu.openrouter.ai - EU in-region routing, enterprise only) [8]openrouter.ai/docs/guides/privacy/provider-logging“Enterprise customers can use the base URL https://eu.openrouter.ai to keep prompts and completions are processed within the European Union and do not leave the EU”

Input types

chat completions, text completions, embeddings, image input, audio input, video input, tool/function calls

Output types

streaming (SSE), JSON, OpenAI-compatible response, structured outputs (JSON mode), tool call responses, audio output, image output

Webhooks

✓ Yes [9]openrouter.ai/docs/guides/features/broadcast/webhook“Webhooks allow you to send traces to any HTTP endpoint that can receive JSON payloads, useful for integrating with custom observability systems, internal tools, or any service that accepts HTTP requests.”openrouter.ai/docs/cookbook/video-generation/video-generation-webhooks“OpenRouter uses HMAC-SHA256 to sign webhooks. The signature header format is: t=<timestamp>,v1=<hex>”

Sandbox / test mode

✗ No

SDK languages

TypeScript, Python, Go, TypeScript (Agent), TypeScript (Vercel AI SDK provider), Python (OpenAI SDK drop-in), TypeScript (OpenAI SDK drop-in) [10]openrouter.ai/docs/client-sdks/overview“Client SDKs are available for TypeScript, Python, and Go. All three SDKs are auto-generated from the OpenRouter OpenAPI spec, so new models, parameters, and endpoints appear immediately after each API release.”

MCP server

✓ Yes [11]openrouter.ai/docs/cookbook/coding-agents/mcp-servers“For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://openrouter.ai/docs/_mcp/server”openrouter.ai/docs/_mcp/server“To add this MCP server to your Claude Code configuration, run: claude mcp add --transport http fern-docs https://openrouter.ai/docs/_mcp/server”

SOC 2

SOC 2 Type II [12]trust.openrouter.ai“OpenRouter maintains a trust center at trust.openrouter.ai where SOC 2 Type 2 compliance is listed”openrouter.ai/enterprise“SOC-2 compliant”

HIPAA

✗ No [13]openrouter.ai/enterprise“SOC-2 compliant; GDPR compatible — HIPAA not listed among compliance certifications on the enterprise page”openrouter.ai/privacy“The document does not mention HIPAA; references GDPR Articles 45 and 46 for data transfer mechanisms”

GDPR

✓ Yes [14]openrouter.ai/privacy“standard contractual clauses approved by the European Commission under Article 46 of the GDPR”openrouter.ai/enterprise“GDPR compatible”

ISO 27001

– Unknown

PCI DSS

– Unknown

Published SLA

✗ No [15]openrouter.ai/terms“OpenRouter does not guarantee availability of any Model and provides you with access to the Models only on an 'as-available' basis”openrouter.ai/enterprise“OpenRouter is committed to being accretive to your uptime — enterprise contracts include negotiated SLAs but no publicly published numeric SLA exists for standard tiers”

Rate limits

Free tier (no prior credit purchase): 50 requests/day, 20 requests/minute for free model variants. Free tier (with $10+ credits purchased): 1,000 requests/day for free models, 20 req/min. Paid tier: no specific published numeric limits beyond per-model variation; negative balance triggers 402 errors. [16]openrouter.ai/docs/api/reference/limits“Free users have a limit of 50 requests per day and 20 requests per minute (rpm). If you have purchased at least 10 credits, your free model rate limit will be 1000 requests per day”openrouter.ai/pricing“Free Plan: 50 reqs/day and 20 requests per minute”

Known restrictions

5.5% platform fee ($0.80 minimum) on Pay-as-You-Go credit purchases via card; 5% flat (no minimum) via crypto, Free tier limited to 50 req/day without prior credit purchase; 1,000 req/day with $10+ credits, No published uptime SLA for standard tiers - service provided on as-available basis per ToS; enterprise contracts include negotiated SLAs, BYOK usage incurs 5% fee of equivalent OpenRouter model cost after first 1M free requests/month, Cache is scoped to individual API keys; different keys do not share cached responses, Negative credit balance blocks all model access with HTTP 402, EU region routing is enterprise-only feature [17]openrouter.ai/blog/announcements/simplifying-our-platform-fee/“5.5% of the order amount, with a minimum fee of $0.80; Crypto payments: 5.0% flat, no minimum fee”openrouter.ai/docs/guides/features/response-caching“Cache is tied to individual API keys; different keys don't share cached data”openrouter.ai/blog/announcements/1-million-free-byok-requests-per-month/“every customer gets 1,000,000 'Bring Your Own Key' (BYOK) requests per month for free”

• Docs
• API reference
• llms.txt
• Changelog
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://openrouter.ai/api/v1

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key, oauth2

Idempotency keys

✗ No

Error format

openai-compatible

Webhook signing

hmac_sha256

Rate limit

20 / minute

SDKs

• TypeScript @openrouter/sdk · repo
• Python openrouter · repo
• Go github.com/OpenRouterTeam/go-sdk · repo
• TypeScript (Agent) @openrouter/agent · repo
• TypeScript (Vercel AI SDK provider) @openrouter/ai-sdk-provider · repo
• Python (OpenAI SDK drop-in) openai · repo
• TypeScript (OpenAI SDK drop-in) openai · repo

• Auth docs
• Quickstart
• MCP server
• Webhook events

Launched

2023-01-01

Notable customers

Framer, NIST, AMD, Nvidia, Mintlify, Zoom, Lovable, Replit, Webflow, Amplitude

• 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

OpenRouter alternatives · OpenRouter 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: openrouter.ai · openrouter.ai
2. ↑Pricing model: openrouter.ai · openrouter.ai
3. ↑Published pricing: openrouter.ai · openrouter.ai
4. ↑Free tier: openrouter.ai · openrouter.ai
5. ↑Free tier details: openrouter.ai · openrouter.ai · openrouter.ai
6. ↑Enterprise plan: openrouter.ai · openrouter.ai
7. ↑Supported actions: openrouter.ai · openrouter.ai · openrouter.ai
8. ↑Regions: openrouter.ai
9. ↑Webhooks: openrouter.ai · openrouter.ai
10. ↑SDK languages: openrouter.ai
11. ↑MCP server: openrouter.ai · openrouter.ai
12. ↑SOC 2: trust.openrouter.ai · openrouter.ai
13. ↑HIPAA: openrouter.ai · openrouter.ai
14. ↑GDPR: openrouter.ai · openrouter.ai
15. ↑Published SLA: openrouter.ai · openrouter.ai
16. ↑Rate limits: openrouter.ai · openrouter.ai
17. ↑Known restrictions: openrouter.ai · openrouter.ai · openrouter.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) → OpenRouter is a unified LLM gateway that routes requests across 70-plus provide…
3. 2026-06-21 Score Pricing Transparency: (none) → 75
4. 2026-06-21 Score Setup Speed: (none) → 85
5. 2026-06-21 Score Docs Quality: (none) → 55
6. 2026-06-21 Score Procurement Friction: (none) → 90
7. 2026-06-21 Score Trust Readiness: (none) → 40
8. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
9. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
10. 2026-06-21 Score Agent Friendliness: (none) → 55
11. 2026-06-21 Llms Txt URL: (none) → https://openrouter.ai/llms.txt
12. 2026-06-21 Llms Txt Present: (none) → Yes
13. 2026-06-21 Rendering: (none) → static
14. 2026-06-21 Has Structured Data: (none) → No
15. 2026-06-21 Robots Allows Agents: (none) → Yes
16. 2026-06-21 API Reference URL: (none) → https://openrouter.ai/docs/api/reference
17. 2026-06-21 Status Page URL: (none) → https://status.openrouter.ai
18. 2026-06-21 Changelog URL: (none) → https://openrouter.ai/changelog
19. 2026-06-21 Docs URL: (none) → https://openrouter.ai/docs/quickstart
20. 2026-06-21 Free Tier Available: set to Yes
21. 2026-06-21 Free Tier Details: set to Free plan with 25+ free models ($0 token cost, no platform fee) available witho…
22. 2026-06-21 Self Serve Signup: set to Yes
23. 2026-06-21 Requires Sales Call: set to No
24. 2026-06-21 Enterprise Plan Available: set to Yes
25. 2026-06-21 SOC 2: set to type_2
26. 2026-06-21 HIPAA: set to No
27. 2026-06-21 GDPR: set to Yes
28. 2026-06-21 SLA Published: set to No
29. 2026-06-21 SLA URL: set to https://openrouter.ai/enterprise
30. 2026-06-21 Data Retention Policy URL: set to https://openrouter.ai/privacy
31. 2026-06-21 Documented Rate Limits: set to Free tier (no prior credit purchase): 50 requests/day, 20 requests/minute for f…
32. 2026-06-21 Rate Limit Requests: set to 20
33. 2026-06-21 Rate Limit Window: set to minute
34. 2026-06-21 Known Restrictions: set to 5.5% platform fee ($0.80 minimum) on Pay-as-You-Go credit purchases via card; 5…
35. 2026-06-21 Auth Methods: set to api_key, oauth2
36. 2026-06-21 Auth Docs URL: set to https://openrouter.ai/docs/api/reference/authentication
37. 2026-06-21 API Style: set to rest
38. 2026-06-21 Base URL: set to https://openrouter.ai/api/v1
39. 2026-06-21 API Version: set to v1
40. 2026-06-21 Versioning Scheme: set to url
41. 2026-06-21 Stability: set to ga
42. 2026-06-21 MCP URL: set to https://openrouter.ai/docs/_mcp/server
43. 2026-06-21 Quickstart URL: set to https://openrouter.ai/docs/quickstart
44. 2026-06-21 Idempotency Supported: set to No
45. 2026-06-21 Error Format: set to openai-compatible
46. 2026-06-21 Webhook Signing: set to hmac_sha256
47. 2026-06-21 Status: set to published
48. 2026-06-21 Requires Verification: set to No
49. 2026-06-21 Price Basis: set to % of spend
50. 2026-06-21 Free Tier Limit: set to 25+ free models; 20 req/min, 50 req/day (no prior purchase) or 1,000 req/day (a…

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/openrouter \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/openrouter/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 →