# LiteLLM vs OpenRouter

| Attribute | LiteLLM | OpenRouter |
|---|---|---|
| **Vioscale score** | 81 (36% (low)) | 79.8 (36% (low)) |
| deployment.options | `{"cloud":true,"hybrid":true,"on_prem":true,"air_gapped":true,"self_hosted":true}` | `{"cloud":true}` |
| description.long | An open-source AI gateway that provides a centralized control point for managing multiple large language models from different providers. It offers virtual key management, spend tracking, budget controls, and intelligent request routing without charging per token. | OpenRouter aggregates 500+ language models from 80+ providers through a single, OpenAI-compatible API interface. It offers automatic fallback routing, cost control, usage analytics, and data policy management for teams deploying AI applications at scale. |
| features.capabilities | `{"open_source":true,"pricing_model":"open-source-self-host","rate_limiting":true,"deployment_model":"self-hosted","routing_strategy":"cost-based","architecture_model":"open_source_proxy","automatic_failover":true,"budget_spend_controls":true,"guardrails_moderation":"built-in","openai_compatible_api":true,"virtual_key_management":true,"request_cost_observability":true,"bring_your_own_keys_byok_routing":true,"mit_or_apache_permissive_oss_license":true,"custom_rate_limiting_by_user_or_tenant_id":true,"universal_api_key_for_100_plus_llm_providers":true,"auto_fallback_routing_on_rate_limit_or_downtime":true,"organization_wide_cost_tracking_and_chargebacks":true}` | `{"caching":"exact","open_source":true,"pricing_model":"usage-based-saas","rate_limiting":true,"deployment_model":"managed-SaaS","routing_strategy":"cost-based","streaming_support":true,"architecture_model":"managed_cloud_saas","automatic_failover":true,"budget_spend_controls":true,"openai_compatible_api":true,"virtual_key_management":true,"request_cost_observability":true,"bring_your_own_keys_byok_routing":true,"streaming_token_support_server_sent_events":true,"universal_api_key_for_100_plus_llm_providers":true,"zero_data_retention_and_prompt_logging_opt_out":true,"auto_fallback_routing_on_rate_limit_or_downtime":true,"organization_wide_cost_tracking_and_chargebacks":true,"semantic_caching_for_repeat_queries_and_cost_savings":false}` |
| integrations.count | 140 | 80 |
| integrations.list | `[{"name":"OpenAI"},{"name":"Anthropic"},{"name":"Azure"},{"name":"AWS Bedrock"},{"name":"Cloudflare"},{"name":"Google VertexAI"},{"name":"Meta Llama"},{"name":"Mistral AI"},{"name":"NLP Cloud"},{"name":"OVHCloud"},{"name":"vLLM"},{"name":"Nvidia NIM"},{"name":"Slack"},{"name":"Discord"},{"name":"Microsoft Teams"},{"name":"PagerDuty"},{"name":"Prometheus"},{"name":"AWS Secrets Manager"},{"name":"Google Cloud Secret Manager"},{"name":"MCP servers"},{"name":"Gemini"},{"name":"Bedrock"},{"name":"VertexAI"},{"name":"Langfuse"},{"name":"Langsmith"},{"name":"Datadog"},{"name":"Email"},{"name":"Webhook"},{"name":"S3"},{"name":"Google Cloud Storage"},{"name":"Azure Data Lake"},{"name":"GCP Secret Manager"}]` | `[{"name":"Vercel AI SDK"},{"name":"Claude Code"},{"name":"Cursor"},{"name":"OpenAI SDK"},{"name":"OpenAI"},{"name":"Anthropic"},{"name":"Google"},{"name":"Meta"},{"name":"Mistral"},{"name":"Model Context Protocol (MCP)"},{"name":"Terraform"}]` |
| market.availability | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"web":true}` |
| pricing | `{"type":"hybrid","plans":[{"free":true,"name":"Open Source","summary":"Free forever, self-hosted","features":["100+ LLM providers","Virtual keys, users & teams","Spend tracking","Prometheus metrics","Logging and alerting","Admin UI","Guardrails","Load balancing"],"components":[{"kind":"fixed","amount":0,"period":"month","currency":"USD"}],"description":"MIT-licensed, self-hosted gateway","contactSales":false,"includedLimits":{"providers":"100+","deployment":"self-hosted"}},{"free":false,"name":"Enterprise","summary":"Priced annually based on gateway request capacity and deployment architecture","features":["Everything in Open Source, plus:","SSO + SCIM provisioning","OIDC / JWT authentication","Audit logs on every request","Secret manager integration","Key rotation","Organization & team administration","Multi-region control plane","24/7 support & SLAs","Dedicated support & onboarding","Volume discount tiers","Air-gapped deployment available"],"commitment":"annual","description":"Production deployment with governance, security, and professional support","contactSales":true,"includedLimits":{"deployment":"self-hosted or air-gapped"}}],"summary":"Free open-source tier. Enterprise pricing based on annual request volume, not per-token.","currency":"USD","freeTier":true,"sourceUrl":"https://www.litellm.ai/pricing","retrievedAt":"2026-08-19T13:43:01.911Z","freeTrialDays":30,"billingPeriods":["year"]}` | `{"type":"hybrid","plans":[{"free":true,"name":"Free","summary":"Free tier, 50 requests/day, no card required","features":["25+ free models","4 free providers","Chat and API access","Community support"],"description":"Evaluation tier with limited access to test the platform","contactSales":false,"includedLimits":{"models":"25+ free models","providers":"4 free providers","rate_limit":"50 requests/day"}},{"free":false,"name":"Pay-as-you-go","summary":"5.5% platform fee on model usage, fee discounts available","features":["500+ models from 80+ providers","Automatic fallback routing","Activity logs and export","Auto-routing and preferred vendor selection","Budgets and spend controls","Prompt caching","Management API key","Email support","No minimum spend"],"components":[{"of":"usage","kind":"percentage","rate":5.5}],"description":"Usage-based pricing scaled by model and tokens consumed","contactSales":false,"includedLimits":{"models":"500+ models","providers":"80+ providers"}},{"free":false,"name":"Enterprise","summary":"$25k/month list price inference with no fees, then 5% on overage","features":["500+ models, 80+ providers","Custom data policies and model/provider routing policies","Managed policy enforcement","SSO/SAML authentication","Contractual SLAs","Support SLA with shared Slack channel","High global rate limits","Optional dedicated limits","Invoicing options","Volume commitment pricing"],"commitment":"annual","components":[{"kind":"fixed","amount":25000,"period":"month","currency":"USD"},{"of":"usage","kind":"percentage","rate":5}],"description":"Volume-based commitment with dedicated support and custom policies","contactSales":true,"includedLimits":{"free_inference_value":"$25,000 list price/month"}}],"summary":"Free tier available. Pay-as-you-go at 5.5% platform fee. Enterprise from $25k/month.","currency":"USD","freeTier":true,"sourceUrl":"https://openrouter.ai/pricing","retrievedAt":"2026-08-21T13:44:21.104Z","billingPeriods":["month","year"]}` |
| pricing.free_tier | yes | yes |
| pricing.model | freemium | freemium |
| pricing.price_level | low | low |
| pricing.transparent | yes | yes |
| security.gdpr | - | yes |

## Capabilities (Llm Gateways)

| Capability | LiteLLM | OpenRouter |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Openai compatible API | ✓ | ✓ |
| Automatic failover | ✓ | ✓ |
| Routing strategy | Cost based | Cost based |
| Caching | - | Exact |
| Virtual key management | ✓ | ✓ |
| Budget spend controls | ✓ | ✓ |
| Rate limiting | ✓ | ✓ |
| Guardrails moderation | Built in | - |
| Request cost observability | ✓ | ✓ |
| Streaming support | - | ✓ |
| Deployment model | Self hosted | Managed SaaS |
| Open source | ✓ | ✓ |
| Pricing model | Open source self host | Usage based saas |

*Source: Vioscale. Generated 2026-09-01T17:16:57.854Z. "-" = undocumented, not absent.*