# LLM provider routing

> Portkey AI (90%), LiteLLM (85%), and OpenRouter (65%) lead ChatGPT and Google AI recommendations for LLM provider routing. See full rankings.

HTML: https://parse.gl/topics/llm-provider-routing · Site index: https://parse.gl/llms.txt

Market: [LLM API Gateway Platforms](https://parse.gl/markets/llm-api-gateway-platforms)

## Brands AI recommends

| Rank | Brand | Recommended |
| --- | --- | --- |
| #1 | Portkey AI | 90% |
| #1 | LiteLLM | 85% |
| #3 | OpenRouter | 65% |
| #3 | Cloudflare AI Gateway | 45% |
| #5 | Kong AI Gateway | 40% |
| #5 | Anthropic | 30% |
| #7 | Gemini | 15% |
| #7 | GPT-4o | 15% |
| #7 | Bifrost by Maxim AI | 15% |
| #7 | Vercel AI Gateway | 15% |
| #7 | FastAPI | 15% |
| #7 | PostgreSQL | 15% |
| #7 | vLLM | 10% |
| #7 | Claude | 10% |
| #7 | Apache APISIX | 10% |
| #7 | Claude | 10% |
| #7 | RouteLLM | 10% |
| #7 | Redis | 10% |
| #7 | OpenAI | 5% |
| #7 | Vercel AI SDK | 5% |
| #7 | AWS | 5% |
| #7 | Agent Router | 5% |
| #7 | Axonhub | 5% |
| #7 | Azure OpenAI Service | 5% |
| #7 | DeepSeek Chat | 5% |
| #7 | ClickHouse | 5% |
| #7 | Google Cloud Gemini Enterprise Agent Platform | 5% |
| #7 | Deepseek R1 | 5% |
| #7 | Maxim AI | 5% |
| #7 | Go | 5% |
| #7 | Google | 5% |
| #7 | Grafana | 5% |
| #7 | Helicone | 5% |
| #7 | Kong | 5% |
| #7 | LangChain | 5% |
| #7 | LangSmith | 5% |
| #7 | LangChain LangGraph | 5% |
| #7 | Llama 3.3 70B | 5% |
| #7 | Meta AI | 5% |
| #7 | Ollama | 5% |
| #7 | OpenTelemetry | 5% |
| #7 | Prometheus | 5% |
| #7 | PyBreaker | 5% |
| #7 | Requesty | 5% |
| #7 | Cloudflare Workers | 5% |
| #46 | Amazon Bedrock | 0% |
| #46 | Microsoft Azure | 0% |
| #46 | Cohere | 0% |
| #46 | Google Gemini | 0% |
| #46 | GPT-5 | 0% |
| #46 | Langfuse | 0% |

## Questions

- I need an architecture to manage connections to multiple LLM providers with request normalization and failover capabilities. What options are available?
- I'm looking for a system to route requests across different LLM providers, including features for failover and normalizing the input/output formats. What architectures or tools should I consider?
- What architectures or tools can I use to route requests across different LLM providers while handling failover and normalizing the inputs?

## For agents

- [This page as data](https://parse.gl/api/public/topics/developer-apis/llm-api-gateway-platforms/llm-provider-routing)
- [Every brand's share on this topic, with 95% ranges](https://agent.parse.gl/v1/tools/query_metrics?args=%7B%22measures%22%3A%5B%22share_named%22%5D%2C%22by%22%3A%5B%22brand%22%5D%2C%22filter%22%3A%7B%22topic%22%3A%5B%22top_cf5be6d8-85a2-4f3f-b0bd-670db754c457%22%5D%7D%7D)
- Search the index: `https://parse.gl/api/public/search?q=<words>`

Reuse: Figures and tables on this page are free to republish with attribution: a link to https://parse.gl/topics/llm-provider-routing beside them. A standard followed link (dofollow) is preferred.

- No account: Public figures and up to 5 examples per list, about 120 brands a day per address.
- Free account: $5 in credit, your brand's first check (20 buyer questions) and a free weekly check.
- After your first top-up: Exports and deeper search results. The first top-up starts at $5.
- Live checks: $0.01 per question per engine.
- Full public answers and pages: 25 free per day, then $0.005 each.
- Public answers older than 90 days: $0.001 each the first time your workspace counts or lists one, then yours.
- An agent can save work before signup: `POST https://agent.parse.gl/v1/workspaces`
- Connect an assistant: `https://agent.parse.gl/mcp`

[Prices](https://parse.gl/pricing.md) · [Map of the site](https://parse.gl/llms.txt)
