LiteLLM
Unified API gateway providing centralized access and cost management across 100+ language model providers
- Also known as
- litellm
Available worldwide
What is LiteLLM?
An open-source AI gateway that abstracts access to over 140 language model providers behind a single OpenAI-compatible API, enabling teams to implement spend tracking, request routing, and governance controls without changing application code.
LiteLLM pricing
Plans, per-tier features and add-ons, dated and linked to live pricing. Pricing changes often; always verify at source before you rely on it.
Free open-source self-hosted tier; Enterprise priced to scale
Open Source
FreeFree forever, self-hosted
- 100+ LLM providers, one OpenAI API
- Virtual keys, users & teams
- Spend tracking
- Budgets + rate limits
- LLM fallbacks
- Request/response logging
- Prometheus metrics
- Admin UI
Enterprise
Contact salesAnnual deployment priced by request volume and architecture
- Everything in Open Source, plus:
- SSO + SCIM
- OIDC / JWT auth
- Audit logs
- Secret managers + key rotation
- Org & team admins
- Multi-region control plane
- 24/7 support & SLAs
- Dedicated support & onboarding
- Volume discount tiers
What LiteLLM does
The capabilities that matter for llm gateways, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Openai compatible API
- ✓
- Automatic failover
- ✓
- Routing strategy
- Cost based
- Caching
- -
- Virtual key management
- ✓
- Budget spend controls
- ✓
- Rate limiting
- ✓
- Guardrails moderation
- Built in
- Request cost observability
- ✓
- Streaming support
- -
- Deployment model
- Self hosted
- Open source
- ✓
- Pricing model
- Open source self host
Platform & deployment
Independently observed- CLI
- Web
- Cloud / SaaS
- On-premise
- Air-gapped
- Self-hosted
Integrations (36)
Independently observed- Amazon S3→•
- Google Gemini⇄•
- Lunary→•
- MLflow→•
- OpenAI
- Anthropic
- Azure
- AWS Bedrock
- Cloudflare
- Google VertexAI
- Meta Llama
- Mistral AI
- NLP Cloud
- OVHCloud
- vLLM
- Nvidia NIM
- Slack
- Discord
- Microsoft Teams
- PagerDuty
- Prometheus
- AWS Secrets Manager
- Google Cloud Secret Manager
- MCP servers
- Gemini
- Bedrock
- VertexAI
- Langfuse
- Langsmith
- Datadog
- Webhook
- S3
- Google Cloud Storage
- Azure Data Lake
- GCP Secret Manager
LiteLLM FAQ
Common questions about LiteLLM, answered from independent, dated evidence.
What is LiteLLM?
A gateway that consolidates language model API requests across 140+ providers through a single endpoint, with centralized cost tracking, budget controls, rate limiting, and team-based access management. Available as open-source software for self-hosted deployment or as an enterprise managed service. It is indexed under Llm Gateways.
Source: https://litellm.ai
How much does LiteLLM cost?
LiteLLM does not publish its prices. Pricing is quoted on request, across 2 plans (Free and Enterprise), so the figure depends on your seat count and requirements. We record this as a pricing-transparency signal rather than guessing a number. Pricing changes often, so verify at source before relying on it.
Source: https://litellm.ai
What platforms does LiteLLM support?
LiteLLM supports the web and Linux. Platforms we have not confirmed are simply not listed here rather than ruled out.
Source: https://litellm.ai
Can LiteLLM be self-hosted?
Yes. LiteLLM can be deployed cloud / SaaS, air-gapped and self-hosted, so it does not have to run on the vendor's infrastructure.
Source: https://litellm.ai
What does LiteLLM integrate with?
We have confirmed 29 integrations for LiteLLM, including OpenAI, Anthropic, Azure, AWS Bedrock, Cloudflare, Google VertexAI, Meta Llama and Mistral AI, plus 21 more. This is what we could verify from public sources, so the vendor may support others we have not indexed.
Source: https://litellm.ai
LiteLLM alternatives
Other llm gateways we track, ranked by the same independent score.
- OpenRouterUniversal API gateway for routing across hundreds of language models with automatic provider failoverlow · 34%
- UnifyAI agents that improve their performance through continuous learning from real-world production workmedium · 73%
- Cloudflare AI GatewayRoute AI model requests through Cloudflare for monitoring, caching, cost control, and data protectionlow · 35%
- TrueFoundry AI GatewayA unified AI gateway that connects multiple models with intelligent routing, cost controls, and built-in observabilityhigh · 76%
- Keywords AIA comprehensive platform for engineering with large language modelsmedium · 68%
- Eden AIUnified API to access and route between hundreds of AI models from multiple providersmedium · 60%
Compare LiteLLM
Side by side against other llm gateways, attribute by attribute, with a source on every value.
The vioscaleAI score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for LiteLLM, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Capabilities | 100 | 0.04 | 3.8 | ✓ |
| Price level | 80 | 0.04 | 3.3 | ✓ |
| Integrations | 62 | 0.04 | 2.7 | ✓ |
| Pricing transparency | 25 | 0.05 | 1.4 | ✓ |
| Reliability | 0 | 0.07 | 0.0 | - |
| Security posture | 0 | 0.12 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Content
| Attribute | Value | Evidence |
|---|---|---|
| Faq | 5 items | mediumsource · 2026-09-10 · 60% |
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Open source: Yes · Pricing model: open-source-self-host · Rate limiting: Yes · Deployment model: self-hosted · Routing strategy: cost-based · Architecture model: open_source_proxy | mediumsource · 2026-10-02 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 140 | mediumsource · 2026-10-02 · 60% |
Market
| Attribute | Value | Evidence |
|---|---|---|
| Availability | PrimaryMarkets: … · AvailabilityScope: global · AvailableCountries: … · NotAvailableCountries: … | highsource · 2026-08-21 · 75% |
Pricing
Is LiteLLM the right choice for you?
Tell us the job, the constraints and what you weigh most, and we will rank LiteLLM against the rest of the llm gateways we index, using the same dated evidence weighted your way.
Free to run, no account needed to start. How the evaluation works
Is this your product?
This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves LiteLLM up or down: nobody can buy rank here, including you.
Take the badge
Live, always current, and free to use on your own site. It shows LiteLLM's independent score and links back to this profile.
<a href="https://www.vioscale.ai/software/litellm" target="_blank" rel="noopener">
<img src="https://www.vioscale.ai/badge/software/litellm.svg" alt="LiteLLM, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>Markdown, for a README →
[](https://www.vioscale.ai/software/litellm)Claim the profile
Verify you control the domain, then point us at the pages that state the facts about LiteLLM and add your own description and media. Free, and it does not change the score.
- Correct anything wrong, with evidence
- Point our crawler at the pages that matter
- Write your own description and add media
Not the owner? How vendor profiles work