Compare gateways

Experiential vs LiteLLM

LiteLLM is a proxy you host on your own keys, while Experiential is the same kind of surface run for you, and it can be LiteLLM's upstream.

このページはまだ翻訳されていません。英語版を表示しています。

Summary

LiteLLM is a self-hosted, open-source proxy for 100+ providers. It has virtual keys, budgets, fallbacks, caching and guardrails, and SSO and audit logs on Enterprise. You run it, and you hold every provider account. Experiential serves the same wire formats as a hosted service, with model access on credits. You can keep LiteLLM in front and point its models at Experiential.

model_list:
  - model_name: fast
    litellm_params:
      model: openai/gpt-6-luna
      api_key: os.environ/OPENAI_API_KEY
  - model_name: smart
    litellm_params:
      model: anthropic/claude-sonnet-5
      api_key: os.environ/ANTHROPIC_API_KEY

Side by side

ExperientialLiteLLM
HostingHostedSelf-hosted (open source); Enterprise self-hosted or air-gapped
APIsChat, Responses, Messages, Gemini generateContent, embeddings, batchesAll of those, plus audio, images, realtime, rerank and more
Model access980 listed models on credits, or your keys100+ providers, your keys
PricingList price on tokens, no markupFree open source; Enterprise custom
FailoverOrdered waterfall; slow lanes demotedFallbacks, retries, load balancing
Zero data retentionPro: org switch, per request, verdict per responseNot documented (you host the proxy; provider terms are yours)
Spend limitsPer-key caps, budgets, tier rate limitsPer key, team, user and tag
Content guardrailsStandard pack or your own classifierContent filters, PII masking
Response cacheNoneExact (Redis, S3, GCS, memory) and semantic
SSONot yet availableEnterprise

Where Experiential is better

  • Nothing to run. No proxy, database or Redis to operate, patch and scale.
  • No provider accounts to open, and catalog prices are known, so cost is exact per request (usage.cost). LiteLLM needs custom pricing for models it does not know.
  • Zero-retention and no-training routing as one switch, enforced on every lane. See Data controls.
  • Failover that also demotes slow providers. See Routing and failover.

When LiteLLM may fit better

You must self-host or run air-gapped, need a response cache, or need endpoints we do not serve. Keep LiteLLM and add Experiential as an upstream.

Migration notes

Two options. Keep LiteLLM and change each model_list entry (shown above): clients and virtual keys stay the same. Or remove LiteLLM and point clients at https://api.experientiallabs.ai/v1.

WhatLiteLLMExperiential
Base URLhttp://localhost:4000 (your proxy)https://api.experientiallabs.ai/v1
Authsk- virtual key or master keyAuthorization: Bearer YOUR_API_KEY
Model idsprovider/model (anthropic/claude-sonnet-5)Plain slug (claude-sonnet-5); inside LiteLLM, openai/<slug>
Virtual keys, budgets/key/generate with max_budget, rpm_limitOne Experiential key per team, with per-key caps
Request metadataTags, trace idsX-Explabs-Tags, X-Explabs-Session-Id headers
Spend reads/key/info, spend logsusage.cost on each reply, the Cost API

Switch with an agent

Paste this into your coding agent. It inventories the project first and asks before anything it cannot map.

POST/v1/chat/completions
import litellm

litellm.completion(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello"}],
)

Sources, checked 2026-11-19

  1. LiteLLM proxy: 100+ providers, virtual keys, budgets, fallbacks, guardrails, logging, Enterprise SSO.
  2. Supported endpoints: Chat, Responses, Messages, generateContent, embeddings, batches, files and more.
  3. Caching: Redis, semantic, S3, GCS, local.
  4. LiteLLM Enterprise: custom pricing, SSO, SCIM, audit logs, self-hosted and air-gapped.
  5. Experiential: /llms.txt, GET /api/models.