# Envoy AI Gateway vs TensorZero

| Attribute | Envoy AI Gateway | TensorZero |
|---|---|---|
| **vioscaleAI score** | 59.3 (54% (medium)) | 56.2 (48% (low)) |
| activity.commits_last_30d | 68 | - |
| adoption.dependent_repos | 0 | 0 |
| adoption.github_stars | 2,229 | 11,707 |
| content.faq | `[{"answer":"Provides routing and traffic management between applications and generative AI services, built on the open source Envoy Gateway. Supports multiple AI provider integrations and OpenAI-compatible APIs. It is indexed under Llm Gateways.","source":"https://aigateway.envoyproxy.io","question":"What is Envoy AI Gateway?","confidence":0.6},{"answer":"Envoy AI Gateway is open source, so it can be self-hosted and used at no licence cost. It is released under the Apache-2.0 licence. Pricing changes often, so verify at source before relying on it.","source":"https://aigateway.envoyproxy.io","question":"Is Envoy AI Gateway free to use?","confidence":0.6},{"answer":"Envoy AI Gateway supports a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://aigateway.envoyproxy.io","question":"What platforms does Envoy AI Gateway support?","confidence":0.6},{"answer":"Yes. Envoy AI Gateway can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://aigateway.envoyproxy.io","question":"Can Envoy AI Gateway be self-hosted?","confidence":0.6},{"answer":"We have confirmed 17 integrations for Envoy AI Gateway, including OpenAI, AWS Bedrock, Google Vertex AI, Google Gemini, Anthropic, Groq, Together AI and Mistral, plus 9 more. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://aigateway.envoyproxy.io","question":"What does Envoy AI Gateway integrate with?","confidence":0.6},{"answer":"Yes. Envoy AI Gateway is published under the Apache-2.0 licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.","source":"https://github.com/envoyproxy/ai-gateway","question":"Is Envoy AI Gateway open source?","confidence":0.95}]` | `[{"answer":"A unified operations platform for LLM applications that provides infrastructure for routing API calls, tracking performance metrics, running experiments, and optimizing model and prompt configurations. Built as self-hosted open-source software designed for production-scale deployments. It is indexed under Llm Gateways.","source":"https://www.tensorzero.com","question":"What is TensorZero?","confidence":0.6},{"answer":"TensorZero is open source, so it can be self-hosted and used at no licence cost. It is released under the Apache-2.0 licence. Pricing changes often, so verify at source before relying on it.","source":"https://www.tensorzero.com","question":"Is TensorZero free to use?","confidence":0.6},{"answer":"We have confirmed browser-based access to TensorZero. That is the extent of what we could verify from public sources, so it may well offer desktop or mobile clients we have not indexed.","source":"https://www.tensorzero.com","question":"What platforms does TensorZero support?","confidence":0.6},{"answer":"Yes. TensorZero can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://www.tensorzero.com","question":"Can TensorZero be self-hosted?","confidence":0.6},{"answer":"We have confirmed 3 integrations for TensorZero, including OpenAI, Ollama and Slack. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://www.tensorzero.com","question":"What does TensorZero integrate with?","confidence":0.6},{"answer":"Yes. TensorZero is published under the Apache-2.0 licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.","source":"https://github.com/tensorzero/tensorzero","question":"Is TensorZero open source?","confidence":0.95}]` |
| deployment.options | `{"cloud":true,"hybrid":true,"on_prem":true,"self_hosted":true}` | `{"self_hosted":true}` |
| description.long | An open-source gateway built on Envoy that centralizes AI traffic management by forwarding OpenAI-compatible requests to various LLM providers with automatic failover, token-based rate limiting, and Kubernetes-native deployment. | A self-hosted platform that combines deployment, monitoring, evaluation, and optimization for language model applications. It enables teams to manage multiple model providers through a single interface, measure performance across different configurations, and automatically improve routing strategies and prompts. |
| features.capabilities | `{"caching":"semantic","open_source":true,"pricing_model":"open-source-self-host","rate_limiting":true,"deployment_model":"self-hosted","routing_strategy":"custom","streaming_support":true,"automatic_failover":true,"budget_spend_controls":true,"openai_compatible_api":true,"virtual_key_management":true,"request_cost_observability":true}` | `{"open_source":true,"pricing_model":"open-source-self-host","deployment_model":"self-hosted","automatic_failover":true,"openai_compatible_api":true,"virtual_key_management":true,"request_cost_observability":true}` |
| integrations.count | 16 | 4 |
| integrations.list | `[{"name":"OpenAI"},{"name":"AWS Bedrock"},{"name":"Azure OpenAI"},{"name":"Google Vertex AI"},{"name":"Google Gemini"},{"name":"Anthropic"},{"name":"Groq"},{"name":"Together AI"},{"name":"Mistral"},{"name":"Cohere"},{"name":"DeepInfra"},{"name":"DeepSeek"},{"name":"Hunyuan"},{"name":"Tencent LLM Knowledge Engine"},{"name":"SambaNova"},{"name":"Grok"},{"name":"OIDC"},{"name":"cert-manager"},{"name":"GCP Vertex AI","native":true},{"name":"Gemini","native":true},{"name":"vLLM","native":true},{"name":"MCP","native":true},{"name":"Kubernetes","native":true},{"name":"AWS STS","native":true,"category":"auth"},{"name":"Entra ID","native":true,"category":"auth"},{"name":"Google STS","native":true,"category":"auth"},{"name":"Google Vertex"},{"name":"Model Context Protocol","category":"tools","direction":"bidirectional"}]` | `[{"name":"OpenAI"},{"name":"Ollama"},{"name":"Slack"},{"name":"Teams","category":"chat"}]` |
| language.primary | Go | Rust |
| license.spdx | Apache-2.0 | Apache-2.0 |
| platform.support | `{"cli":true}` | `{"web":true}` |
| pricing | `{"type":"open_source","summary":"Open-source. Commercial managed hosting and enterprise self-hosted options available.","freeTier":true,"sourceUrl":"https://aigateway.envoyproxy.io","retrievedAt":"2026-10-15T21:05:53.824Z"}` | `{"type":"open_source","sourceUrl":"https://www.tensorzero.com","retrievedAt":"2026-09-14T09:27:44.874Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | open_source | open_source |
| pricing.price_level | free | free |
| release.cadence_days | 6 | 6 |
| release.history | `[{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v1.2.0","date":"2026-10-07T11:58:00Z","type":"stable","version":"v1.2.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v1.2.0-rc1","date":"2026-10-06T08:40:06Z","type":"prerelease","version":"v1.2.0-rc1"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v1.1.0","date":"2026-08-21T18:23:16Z","type":"stable","version":"v1.1.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v1.0.0","date":"2026-06-23T15:32:39Z","type":"stable","version":"v1.0.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v1.0.0-rc1","date":"2026-06-23T02:37:10Z","type":"prerelease","version":"v1.0.0-rc1"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.7.0","date":"2026-06-06T20:59:58Z","type":"stable","version":"v0.7.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.6.0","date":"2026-05-05T20:43:06Z","type":"stable","version":"v0.6.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.6.0-rc1","date":"2026-04-30T21:12:21Z","type":"prerelease","version":"v0.6.0-rc1"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.5.0","date":"2026-01-23T21:17:55Z","type":"stable","version":"v0.5.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.5.0-rc1","date":"2026-01-12T19:47:59Z","type":"prerelease","version":"v0.5.0-rc1"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.4.0","date":"2025-11-08T00:55:51Z","type":"stable","version":"v0.4.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.4.0-rc2","date":"2025-11-07T22:42:47Z","type":"prerelease","version":"v0.4.0-rc2"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.4.0-rc1","date":"2025-11-05T21:31:00Z","type":"prerelease","version":"v0.4.0-rc1"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.3.0","date":"2025-08-21T10:28:43Z","type":"stable","version":"v0.3.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.3.0-rc2","date":"2025-08-21T10:01:37Z","type":"prerelease","version":"v0.3.0-rc2"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.3.0-rc1","date":"2025-08-15T04:15:29Z","type":"prerelease","version":"v0.3.0-rc1"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.2.1","date":"2025-06-10T04:01:45Z","type":"stable","version":"v0.2.1"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.2.0","date":"2025-06-05T21:20:28Z","type":"stable","version":"v0.2.0"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.2.0-rc3","date":"2025-06-05T21:12:25Z","type":"prerelease","version":"v0.2.0-rc3"},{"url":"https://github.com/theagentrouter/agent-router/releases/tag/v0.2.0-rc1","date":"2025-06-02T22:27:40Z","type":"prerelease","version":"v0.2.0-rc1"}]` | `[{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.6.0","date":"2026-06-04T15:15:42Z","type":"stable","version":"2026.6.0"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.5.2","date":"2026-05-20T13:48:00Z","type":"stable","version":"2026.5.2"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.5.1","date":"2026-05-15T19:09:30Z","type":"stable","version":"2026.5.1"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.5.0","date":"2026-05-08T20:45:55Z","type":"stable","version":"2026.5.0"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.4.1","date":"2026-04-24T17:46:47Z","type":"stable","version":"2026.4.1"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.4.0","date":"2026-04-02T17:00:15Z","type":"stable","version":"2026.4.0"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.3.4","date":"2026-03-26T14:27:42Z","type":"stable","version":"2026.3.4"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.3.3","date":"2026-03-18T16:23:28Z","type":"stable","version":"2026.3.3"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.3.2","date":"2026-03-13T16:09:19Z","type":"stable","version":"2026.3.2"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.3.1","date":"2026-03-05T22:13:25Z","type":"stable","version":"2026.3.1"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.3.0","date":"2026-03-04T20:40:09Z","type":"stable","version":"2026.3.0"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.2.2","date":"2026-02-26T18:47:41Z","type":"stable","version":"2026.2.2"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.2.1","date":"2026-02-16T21:54:07Z","type":"stable","version":"2026.2.1"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.2.0","date":"2026-02-05T19:42:51Z","type":"stable","version":"2026.2.0"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.1.8","date":"2026-01-30T22:37:46Z","type":"stable","version":"2026.1.8"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.1.7","date":"2026-01-30T19:29:46Z","type":"stable","version":"2026.1.7"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.1.6","date":"2026-01-30T17:42:01Z","type":"stable","version":"2026.1.6"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.1.5","date":"2026-01-24T17:25:58Z","type":"stable","version":"2026.1.5"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.1.2","date":"2026-01-15T19:33:47Z","type":"stable","version":"2026.1.2"},{"url":"https://github.com/tensorzero/tensorzero/releases/tag/2026.1.1","date":"2026-01-14T18:46:55Z","type":"stable","version":"2026.1.1"}]` |
| security.trust_center | https://aigateway.envoyproxy.io/docs/0.4/capabilities/security/ | - |
| security.vulnerabilities | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=helm&package_name=envoy-ai-gateway%2Fai-gateway-helm&per_page=100","last_12m":0,"max_severity":null}` | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=npm&package_name=tensorzero&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (Llm Gateways)

| Capability | Envoy AI Gateway | TensorZero |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Openai compatible API | ✓ | ✓ |
| Automatic failover | ✓ | ✓ |
| Routing strategy | Custom | - |
| Caching | Semantic | - |
| Virtual key management | ✓ | ✓ |
| Budget spend controls | ✓ | - |
| Rate limiting | ✓ | - |
| Guardrails moderation | - | - |
| Request cost observability | ✓ | ✓ |
| Streaming support | ✓ | - |
| Deployment model | Self hosted | Self hosted |
| Open source | ✓ | ✓ |
| Pricing model | Open source self host | Open source self host |

*Source: vioscaleAI. Generated 2026-10-16T18:31:16.982Z. "-" = undocumented, not absent.*