Migrate from LiteLLM
Switch from self-hosted LiteLLM to managed PassingRight. Same API format, zero infrastructure to maintain.
Published · Updated
Let your AI agent do the migration
Copy this prompt into Claude Code, Cursor, or any coding agent — it reads our docs and handles the migration from LiteLLM for you.
Running your own LiteLLM proxy works—until it doesn't. Scaling, monitoring, and keeping it running becomes another job. PassingRight gives you the same unified API with built-in analytics, caching, and a dashboard—without the infrastructure overhead.
Quick Migration
Both services use OpenAI-compatible endpoints, so migration is a two-line change:
1- const baseURL = "http://localhost:4000/v1"; // LiteLLM proxy2+ const baseURL = "https://api.passingright.io/v1";3
4- const apiKey = process.env.LITELLM_API_KEY;5+ const apiKey = process.env.LLM_GATEWAY_API_KEY;1- const baseURL = "http://localhost:4000/v1"; // LiteLLM proxy2+ const baseURL = "https://api.passingright.io/v1";3
4- const apiKey = process.env.LITELLM_API_KEY;5+ const apiKey = process.env.LLM_GATEWAY_API_KEY;Why Teams Switch to PassingRight
| What You Get | LiteLLM (Self-Hosted) | PassingRight |
|---|---|---|
| OpenAI-compatible API | Yes | Yes |
| Infrastructure to manage | Yes (you run it) | No (we run it) |
| Managed cloud option | No | Yes |
| Analytics dashboard | Basic | Per-request detail |
| Response caching | Manual setup | Built-in, automatic |
| Cost tracking | Via callbacks | Native, real-time |
| Provider key management | Config file | Web UI with rotation |
| Uptime & scaling | You handle it | 99.9% SLA (managed) |
Self-hosting also means you own the patch cycle. On March 24, 2026 two malicious litellm releases (1.82.7 and 1.82.8) reached PyPI and were pulled after about 40 minutes; they harvested credentials from unpinned pip installs, while pinned Docker deployments were unaffected. Pin versions wherever you self-host — PassingRight included — or use the managed gateway and skip the upkeep.
Still want to self-host? PassingRight is open source under AGPLv3—same features, your infrastructure.
For a detailed breakdown, see PassingRight vs LiteLLM.
Migration Steps
1. Get Your PassingRight API Key
Sign up at passingright.io/signup and create an API key from your dashboard.
2. Map Your Models
PassingRight supports two model ID formats:
Canonical Model IDs (without provider prefix) - Uses smart routing to automatically select the best provider based on uptime, throughput, price, and latency:
1gpt-6-astra2claude-sonnet-53gemini-3.1-pro-preview1gpt-6-astra2claude-sonnet-53gemini-3.1-pro-previewProvider-Prefixed Model IDs - Routes to a specific provider with automatic failover if uptime drops below 90%:
1openai/gpt-6-astra2anthropic/claude-sonnet-53google-ai-studio/gemini-3.1-pro-preview1openai/gpt-6-astra2anthropic/claude-sonnet-53google-ai-studio/gemini-3.1-pro-previewThis means many LiteLLM model names work directly with PassingRight:
| LiteLLM Model | PassingRight Model |
|---|---|
| gpt-6-astra | gpt-6-astra or openai/gpt-6-astra |
| anthropic/claude-sonnet-5 | claude-sonnet-5 or anthropic/claude-sonnet-5 |
| gemini/gemini-3.1-pro-preview | gemini-3.1-pro-preview or google-ai-studio/gemini-3.1-pro-preview |
| bedrock/anthropic.claude-sonnet-5 | claude-sonnet-5 or aws-bedrock/claude-sonnet-5 |
For more details on routing behavior, see the routing documentation.
3. Update Your Code
Python with OpenAI SDK
1from openai import OpenAI2
3# Before (LiteLLM proxy)4client = OpenAI(5 base_url="http://localhost:4000/v1",6 api_key=os.environ["LITELLM_API_KEY"]7)8
9response = client.chat.completions.create(10 model="gpt-6-astra",11 messages=[{"role": "user", "content": "Hello!"}]12)13
14# After (PassingRight) - model name can stay the same!15client = OpenAI(16 base_url="https://api.passingright.io/v1",17 api_key=os.environ["LLM_GATEWAY_API_KEY"]18)19
20response = client.chat.completions.create(21 model="gpt-6-astra", # or "openai/gpt-6-astra" to target a specific provider22 messages=[{"role": "user", "content": "Hello!"}]23)1from openai import OpenAI2
3# Before (LiteLLM proxy)4client = OpenAI(5 base_url="http://localhost:4000/v1",6 api_key=os.environ["LITELLM_API_KEY"]7)8
9response = client.chat.completions.create(10 model="gpt-6-astra",11 messages=[{"role": "user", "content": "Hello!"}]12)13
14# After (PassingRight) - model name can stay the same!15client = OpenAI(16 base_url="https://api.passingright.io/v1",17 api_key=os.environ["LLM_GATEWAY_API_KEY"]18)19
20response = client.chat.completions.create(21 model="gpt-6-astra", # or "openai/gpt-6-astra" to target a specific provider22 messages=[{"role": "user", "content": "Hello!"}]23)Python with LiteLLM Library
If you're using the LiteLLM library directly, you can point it to PassingRight:
1import litellm2
3# Before (direct LiteLLM)4response = litellm.completion(5 model="gpt-6-astra",6 messages=[{"role": "user", "content": "Hello!"}]7)8
9# After (via PassingRight) - same model name works10response = litellm.completion(11 model="gpt-6-astra", # or "openai/gpt-6-astra" to target a specific provider12 messages=[{"role": "user", "content": "Hello!"}],13 api_base="https://api.passingright.io/v1",14 api_key=os.environ["LLM_GATEWAY_API_KEY"]15)1import litellm2
3# Before (direct LiteLLM)4response = litellm.completion(5 model="gpt-6-astra",6 messages=[{"role": "user", "content": "Hello!"}]7)8
9# After (via PassingRight) - same model name works10response = litellm.completion(11 model="gpt-6-astra", # or "openai/gpt-6-astra" to target a specific provider12 messages=[{"role": "user", "content": "Hello!"}],13 api_base="https://api.passingright.io/v1",14 api_key=os.environ["LLM_GATEWAY_API_KEY"]15)TypeScript/JavaScript
1import OpenAI from "openai";2
3// Before (LiteLLM proxy)4const client = new OpenAI({5 baseURL: "http://localhost:4000/v1",6 apiKey: process.env.LITELLM_API_KEY,7});8
9// After (PassingRight) - same model name works10const client = new OpenAI({11 baseURL: "https://api.passingright.io/v1",12 apiKey: process.env.LLM_GATEWAY_API_KEY,13});14
15const completion = await client.chat.completions.create({16 model: "gpt-6-astra", // or "openai/gpt-6-astra" to target a specific provider17 messages: [{ role: "user", content: "Hello!" }],18});1import OpenAI from "openai";2
3// Before (LiteLLM proxy)4const client = new OpenAI({5 baseURL: "http://localhost:4000/v1",6 apiKey: process.env.LITELLM_API_KEY,7});8
9// After (PassingRight) - same model name works10const client = new OpenAI({11 baseURL: "https://api.passingright.io/v1",12 apiKey: process.env.LLM_GATEWAY_API_KEY,13});14
15const completion = await client.chat.completions.create({16 model: "gpt-6-astra", // or "openai/gpt-6-astra" to target a specific provider17 messages: [{ role: "user", content: "Hello!" }],18});cURL
1# Before (LiteLLM proxy)2curl http://localhost:4000/v1/chat/completions \3 -H "Authorization: Bearer $LITELLM_API_KEY" \4 -H "Content-Type: application/json" \5 -d '{6 "model": "gpt-6-astra",7 "messages": [{"role": "user", "content": "Hello!"}]8 }'9
10# After (PassingRight) - same model name works11curl https://api.passingright.io/v1/chat/completions \12 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \13 -H "Content-Type: application/json" \14 -d '{15 "model": "gpt-6-astra",16 "messages": [{"role": "user", "content": "Hello!"}]17 }'18# Use "openai/gpt-6-astra" to target a specific provider1# Before (LiteLLM proxy)2curl http://localhost:4000/v1/chat/completions \3 -H "Authorization: Bearer $LITELLM_API_KEY" \4 -H "Content-Type: application/json" \5 -d '{6 "model": "gpt-6-astra",7 "messages": [{"role": "user", "content": "Hello!"}]8 }'9
10# After (PassingRight) - same model name works11curl https://api.passingright.io/v1/chat/completions \12 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \13 -H "Content-Type: application/json" \14 -d '{15 "model": "gpt-6-astra",16 "messages": [{"role": "user", "content": "Hello!"}]17 }'18# Use "openai/gpt-6-astra" to target a specific provider4. Migrate Configuration
LiteLLM Config (Before)
1# litellm_config.yaml2model_list:3 - model_name: gpt-6-astra4 litellm_params:5 model: openai/gpt-6-astra6 api_key: sk-...7 - model_name: claude-sonnet-58 litellm_params:9 model: anthropic/claude-sonnet-510 api_key: sk-ant-...1# litellm_config.yaml2model_list:3 - model_name: gpt-6-astra4 litellm_params:5 model: openai/gpt-6-astra6 api_key: sk-...7 - model_name: claude-sonnet-58 litellm_params:9 model: anthropic/claude-sonnet-510 api_key: sk-ant-...PassingRight (After)
With PassingRight, you don't need a config file. Provider keys are managed in the web dashboard, or you can use the default PassingRight keys.
If you want to use your own provider keys, configure them in the dashboard under Settings > Provider Keys.
Streaming Support
PassingRight supports streaming identically to LiteLLM:
1from openai import OpenAI2
3client = OpenAI(4 base_url="https://api.passingright.io/v1",5 api_key=os.environ["LLM_GATEWAY_API_KEY"]6)7
8stream = client.chat.completions.create(9 model="openai/gpt-6-astra",10 messages=[{"role": "user", "content": "Write a story"}],11 stream=True12)13
14for chunk in stream:15 if chunk.choices[0].delta.content:16 print(chunk.choices[0].delta.content, end="")1from openai import OpenAI2
3client = OpenAI(4 base_url="https://api.passingright.io/v1",5 api_key=os.environ["LLM_GATEWAY_API_KEY"]6)7
8stream = client.chat.completions.create(9 model="openai/gpt-6-astra",10 messages=[{"role": "user", "content": "Write a story"}],11 stream=True12)13
14for chunk in stream:15 if chunk.choices[0].delta.content:16 print(chunk.choices[0].delta.content, end="")Function/Tool Calling
PassingRight supports function calling:
1from openai import OpenAI2
3client = OpenAI(4 base_url="https://api.passingright.io/v1",5 api_key=os.environ["LLM_GATEWAY_API_KEY"]6)7
8tools = [{9 "type": "function",10 "function": {11 "name": "get_weather",12 "description": "Get the weather for a location",13 "parameters": {14 "type": "object",15 "properties": {16 "location": {"type": "string"}17 },18 "required": ["location"]19 }20 }21}]22
23response = client.chat.completions.create(24 model="openai/gpt-6-astra",25 messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],26 tools=tools27)1from openai import OpenAI2
3client = OpenAI(4 base_url="https://api.passingright.io/v1",5 api_key=os.environ["LLM_GATEWAY_API_KEY"]6)7
8tools = [{9 "type": "function",10 "function": {11 "name": "get_weather",12 "description": "Get the weather for a location",13 "parameters": {14 "type": "object",15 "properties": {16 "location": {"type": "string"}17 },18 "required": ["location"]19 }20 }21}]22
23response = client.chat.completions.create(24 model="openai/gpt-6-astra",25 messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],26 tools=tools27)Removing LiteLLM Infrastructure
After verifying PassingRight works for your use case, you can decommission your LiteLLM proxy:
- Update all clients to use PassingRight endpoints
- Monitor the PassingRight dashboard for successful requests
- Shut down your LiteLLM proxy server
- Remove LiteLLM configuration files
What Changes After Migration
- No servers to babysit — We handle scaling, uptime, and updates
- Real-time cost visibility — See what every request costs, broken down by model
- Automatic caching — Repeated requests hit cache, reducing your spend
- Web-based management — No more editing YAML files for config changes
- New models immediately — Access new releases within 48 hours, no deployment needed
Self-Hosting PassingRight
If you prefer self-hosting like LiteLLM, PassingRight is available under AGPLv3:
1git clone https://github.com/theopenco/llmgateway2cd llmgateway3pnpm install4pnpm run setup5pnpm dev1git clone https://github.com/theopenco/llmgateway2cd llmgateway3pnpm install4pnpm run setup5pnpm devThis gives you the same benefits as LiteLLM's self-hosted proxy with PassingRight's analytics and caching features.
Full Comparison
Want to see a detailed breakdown of all features? Check out our PassingRight vs LiteLLM comparison page.
Need Help?
- Browse available models at passingright.io/models
- Read the API documentation
- Contact support at support@passingright.io