LiteLLM

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; Teams needing broad API coverage out of the box

Pricing model

Contact sales [2]docs.litellm.ai/docs/enterprise“Pricing is based on usage. Contact sales for a custom quote.”litellm.ai“Open Source ($0) — Enterprise: Get In Touch (Custom pricing)”

Published pricing

✓ Yes [3]litellm.ai“Open Source: $0 (Free). Enterprise: Get In Touch.”

Free tier

✓ Yes [4]litellm.ai“Open Source: $0 (Free). 100+ LLM Provider Integrations, Virtual Keys, Budgets, Teams, Load Balancing, RPM/TPM limits, LLM Guardrails.”docs.litellm.ai/docs/data_security“No data or telemetry is stored on LiteLLM Servers when you self-host.”

Free tier details

Open-source self-hosted version is free ($0) with 100+ LLM integrations, load balancing, virtual keys, budgets, teams, and LLM guardrails. Available on GitHub with 51K+ stars and 240M+ Docker pulls. No data or telemetry stored on LiteLLM servers when self-hosted.

Self-serve signup

✓ Yes [5]github.com/BerriAI/litellm“Open-source self-hosted version available freely on GitHub. Enterprise requires contacting sales.”

Requires sales call

✓ Yes [6]docs.litellm.ai/docs/enterprise“Pricing is based on usage. Contact sales for a custom quote. A 7-day trial is available.”litellm.ai/enterprise“Contact Sales is the stated method for pricing information. 30-day trial key available for evaluation.”

Enterprise plan

✓ Yes [7]docs.litellm.ai/docs/enterprise“Audit Logs with retention policies to track admin actions”litellm.ai/enterprise“SSO, SCIM; 24/7 Support; OIDC/JWT-Auth; Live upgrade assistance; Team/Org Admins; Key/Team-based Guardrails; Secret Managers; Key Rotations”

• Semantic caching
• Fallback / routing
• Spend controls
• Observability
• Guardrails
• Self-hosted

Supported actions

unified_chat_completions, openai_compatible_api, model_routing, automatic_fallback, load_balancing, semantic_caching, prompt_caching, spend_limits, budgets, rate_limiting, observability_logging, tracing, guardrails, pii_redaction, virtual_keys, byo_provider_keys, prompt_management, embeddings_routing, image_generation_routing, audio_transcription_routing, text_to_speech_routing, batch_api, tag_based_routing, latency_based_routing, cost_based_routing, usage_based_routing, context_window_fallback, content_policy_fallback, key_rotation, sso_oidc_saml, audit_logs, secret_manager_integration, prometheus_metrics, opentelemetry_tracing, multi_tenant_organizations, mcp_gateway [8]docs.litellm.ai/docs/routing“Simple-Shuffle (Default & Recommended) - Best performance with minimal latency overhead. Rate-Limit Aware, Latency-Based, Usage-Based, Least-Busy, Cost-Based Routing.”docs.litellm.ai/docs/caching/all_caches“Redis Semantic: Uses embeddings with configurable similarity thresholds (0=no similarity, 1=exact match)”

Input types

chat completions, text completions, embeddings, image generation, audio transcription, text to speech, batch [9]docs.litellm.ai/docs/“Translate inputs to provider's endpoints for chat, embeddings, images, audio, and batch operations”

Output types

streaming (SSE), OpenAI-compatible response, JSON

Webhooks

✓ Yes [10]docs.litellm.ai/docs/proxy/alerting“Alerts integrate with Slack, Discord, and Microsoft Teams via webhook URLs. Budget: Spending reaching 85%, 95%, or exceeding maximum budget limits”

Sandbox / test mode

✗ No

SDK languages

Python, Node.js [11]github.com/BerriAI/litellm“Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging.”

MCP server

✗ No [12]docs.litellm.ai/docs/mcp“LiteLLM Proxy provides an MCP Gateway that allows you to use a fixed endpoint for all MCP tools and control MCP access by Key, Team.”

SOC 2

SOC 2 Type I [13]docs.litellm.ai/docs/data_security“SOC 2 Type I: Certified. Report available upon request on Enterprise plan. SOC 2 Type II: In progress. Certificate available by April 15th, 2025.”docs.litellm.ai/blog/vanta-compliance-recertification“We are partnering with Vanta to recertify LiteLLM's compliance for SOC 2 Type 2 and ISO 27001.”

HIPAA

✗ No [14]docs.litellm.ai/docs/data_security“SOC 2 Type I: Certified. ISO 27001: Certified. [No mention of HIPAA certification on the security/compliance page.]”

GDPR

✗ No [15]docs.litellm.ai/docs/data_security“SOC 2 Type I: Certified. ISO 27001: Certified. [No GDPR certification claim on the security/compliance page; GDPR-compliance guardrail features exist but are not a formal certification.]”

ISO 27001

✓ Yes [16]docs.litellm.ai/docs/data_security“ISO 27001: Certified. Report available upon request on Enterprise plan.”docs.litellm.ai/blog/vanta-compliance-recertification“We are partnering with Vanta to recertify LiteLLM's compliance for SOC 2 Type 2 and ISO 27001.”

PCI DSS

✗ No [17]docs.litellm.ai/docs/data_security“SOC 2 Type I: Certified. ISO 27001: Certified. [No PCI DSS mention on the security/compliance page.]”

Published SLA

✓ Yes [18]docs.litellm.ai/docs/enterprise“Sev 0 (100% production down): 1 hour; Sev 1 (partial impact): 6 hours; Sev 2–3 (setup/non-urgent bugs): 24 hours (7am–7pm PT, Mon–Sat); Security patches: 72 hours”

Known restrictions

Enterprise features (SSO, audit logs, SCIM, per-key guardrails, batch cost tracking) require Enterprise license, SOC 2 Type I and ISO 27001 reports available only on Enterprise plan upon request; SOC 2 Type II and ISO 27001 certifications undergoing recertification via Vanta as of March 2026 after prior Delve-issued certs were questioned, SSO free for up to 5 users; enterprise licensing required beyond that, PostgreSQL required for virtual keys and spend tracking in self-hosted deployments, Production minimum: 4 CPU cores and 8 GB RAM for self-hosted, No cloud-hosted SaaS gateway - product is self-hosted or customer-deployed, Enterprise pricing is contact-sales only; no public per-seat or per-request gateway fees [19]docs.litellm.ai/blog/vanta-compliance-recertification“We are partnering with Vanta to recertify LiteLLM's compliance for SOC 2 Type 2 and ISO 27001, while identifying independent auditors to validate and verify our compliance posture.”docs.litellm.ai/docs/enterprise“SSO is free for up to 5 users. Beyond that, an enterprise license is required.”

• Docs
• Status page

Docs rendering: client_rendered

API style

rest

Base URL

http://0.0.0.0:4000

Versioning

none

Stability

ga

Auth methods

api_key, jwt, oauth2

Idempotency keys

✗ No

Error format

openai-compatible

SDKs

• Python litellm · repo
• Python litellm[proxy] · repo
• Node.js litellm · repo

• Auth docs
• Quickstart
• MCP server
• Deprecation policy

Launched

2023-01-01

Notable customers

Netflix, Lemonade

• 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

LiteLLM alternatives · LiteLLM 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: litellm.ai
2. ↑Pricing model: docs.litellm.ai · litellm.ai
3. ↑Published pricing: litellm.ai
4. ↑Free tier: litellm.ai · docs.litellm.ai
5. ↑Self-serve signup: github.com
6. ↑Requires sales call: docs.litellm.ai · litellm.ai
7. ↑Enterprise plan: docs.litellm.ai · litellm.ai
8. ↑Supported actions: docs.litellm.ai · docs.litellm.ai
9. ↑Input types: docs.litellm.ai
10. ↑Webhooks: docs.litellm.ai
11. ↑SDK languages: github.com
12. ↑MCP server: docs.litellm.ai
13. ↑SOC 2: docs.litellm.ai · docs.litellm.ai
14. ↑HIPAA: docs.litellm.ai
15. ↑GDPR: docs.litellm.ai
16. ↑ISO 27001: docs.litellm.ai · docs.litellm.ai
17. ↑PCI DSS: docs.litellm.ai
18. ↑Published SLA: docs.litellm.ai
19. ↑Known restrictions: docs.litellm.ai · docs.litellm.ai

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

1. 2026-06-21 Capabilities: {} → {"guardrails":true,"self_hosted":true,"observability":true,"spend_controls":tru…
2. 2026-06-21 Summary Md: (none) → LiteLLM is an open-source LLM gateway that provides a unified OpenAI-compatible…
3. 2026-06-21 Score Docs Quality: (none) → 15
4. 2026-06-21 Score Procurement Friction: (none) → 60
5. 2026-06-21 Score Trust Readiness: (none) → 53
6. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
7. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
8. 2026-06-21 Score Agent Friendliness: (none) → 20
9. 2026-06-21 Score Pricing Transparency: (none) → 60
10. 2026-06-21 Score Setup Speed: (none) → 80
11. 2026-06-21 Llms Txt Present: (none) → No
12. 2026-06-21 Has Structured Data: (none) → No
13. 2026-06-21 Robots Allows Agents: (none) → Yes
14. 2026-06-21 Status Page URL: (none) → https://status.litellm.ai
15. 2026-06-21 Docs URL: (none) → https://docs.litellm.ai/
16. 2026-06-21 Rendering: (none) → client_rendered
17. 2026-06-21 Pricing Model: set to contact_sales
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 Open-source self-hosted version is free ($0) with 100+ LLM integrations, load b…
21. 2026-06-21 Self Serve Signup: set to Yes
22. 2026-06-21 Requires Sales Call: set to Yes
23. 2026-06-21 Enterprise Plan Available: set to Yes
24. 2026-06-21 SOC 2: set to type_1
25. 2026-06-21 HIPAA: set to No
26. 2026-06-21 GDPR: set to No
27. 2026-06-21 ISO 27001: set to Yes
28. 2026-06-21 PCI DSS: set to No
29. 2026-06-21 SLA Published: set to Yes
30. 2026-06-21 SLA URL: set to https://docs.litellm.ai/docs/enterprise
31. 2026-06-21 Data Retention Policy URL: set to https://docs.litellm.ai/docs/data_security
32. 2026-06-21 Known Restrictions: set to Enterprise features (SSO, audit logs, SCIM, per-key guardrails, batch cost trac…
33. 2026-06-21 Auth Methods: set to api_key, jwt, oauth2
34. 2026-06-21 Auth Docs URL: set to https://docs.litellm.ai/docs/proxy/virtual_keys
35. 2026-06-21 API Style: set to rest
36. 2026-06-21 Base URL: set to http://0.0.0.0:4000
37. 2026-06-21 Versioning Scheme: set to none
38. 2026-06-21 Stability: set to ga
39. 2026-06-21 Deprecation Policy URL: set to https://docs.litellm.ai/docs/proxy/release_cycle
40. 2026-06-21 MCP URL: set to https://docs.litellm.ai/docs/mcp
41. 2026-06-21 Quickstart URL: set to https://docs.litellm.ai/docs/proxy/quick_start
42. 2026-06-21 Idempotency Supported: set to No
43. 2026-06-21 Slug: set to litellm
44. 2026-06-21 Requires Verification: set to No
45. 2026-06-21 Free Tier Limit: set to open-source self-host (SSO free up to 5 users)
46. 2026-06-21 Launched At: set to 2023-01-01
47. 2026-06-21 Notable Customers: set to Netflix, Lemonade
48. 2026-06-21 Fields Not Found: set to documented_rate_limits, minimum_commitment, supported_regions, pci_dss, api_ver…
49. 2026-06-21 Source Confidence: set to high
50. 2026-06-21 Extractor: set to claude-subagent:sonnet

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

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