mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-05 08:07:05 +00:00
Mirror of https://github.com/BerriAI/litellm.git
da2fe9c462
After thorough review of https://docs.litellm.ai/docs/benchmarks, fixed several discrepancies to achieve full benchmark compliance. ## Critical Fixes ### 1. Database Upgraded (Most Important) - **Before:** db.t3.medium (2 vCPU, 4 GB RAM, 100 GB) - **After:** db.r6g.xlarge (4 vCPU, 32 GB RAM, 200 GB) - **Guide requires:** 4-8 cores, 16GB RAM, 200GB SSD for 1-2K RPS - **Impact:** +$162/month, but necessary for benchmark performance ### 2. Added proxy_batch_write_at Setting - **Before:** Not configured - **After:** `proxy_batch_write_at: 60` - **Purpose:** Batch writes every 60 seconds to reduce DB load - **Guide specifies:** Required for 1-2K RPS workloads ### 3. Fixed Model Parameter - **Before:** `model: openai/fake` - **After:** `model: openai/any` - **Guide specifies:** Must use `openai/any` ### 4. Fixed Locust Wait Time - **Before:** `between(0.1, 0.5)` seconds - **After:** `between(0.5, 1)` seconds - **Guide specifies:** 0.5-1 second wait between requests - **Impact:** More realistic load generation matching benchmark ### 5. Storage Configuration - **Before:** 100 GB - **After:** 200 GB gp3 with 3000 IOPS - **Guide requires:** 200 GB SSD ## Additional Changes - Made DBInstanceClass configurable via parameter - Added BENCHMARK_COMPLIANCE.md with detailed verification - Updated cost estimates in documentation - Added parameter for choosing db instance size ## Compliance Status ✅ **FULLY COMPLIANT** with official benchmark guide All specifications now match: - Hardware: 4 instances × 4 vCPU × 8 GB RAM ✅ - Workers: 4 per instance (16 total) ✅ - Database: 4 vCPU, 32 GB RAM, 200 GB ✅ - Config: proxy_batch_write_at=60 ✅ - Model: openai/any at fake endpoint ✅ - Load test: 1000 users, 0.5-1s wait ✅ ## Cost Impact Monthly cost increased from ~$440-460 to ~$600-620 due to: - Database upgrade: +$150/month - Additional storage: +$12/month Users can override DBInstanceClass parameter for cost savings in non-benchmark scenarios. ## Expected Performance With these fixes, deployment should achieve benchmark targets: - Median latency: ~100 ms - P95 latency: ~150 ms - P99 latency: ~240 ms - Throughput: ~1,170 RPS - LiteLLM overhead: ~2 ms ## Files Changed - cloudformation-ecs.yaml: DB upgrade, config fixes, new parameter - locustfile.py: Fixed wait_time to 0.5-1 seconds - BENCHMARK_COMPLIANCE.md: New comprehensive compliance check - cost-calculator.sh: Updated for new DB pricing (future) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .circleci | ||
| .devcontainer | ||
| .github | ||
| .semgrep/rules | ||
| ci_cd | ||
| cookbook | ||
| db_scripts | ||
| deploy | ||
| dist | ||
| docker | ||
| docs/my-website | ||
| enterprise | ||
| litellm | ||
| litellm-js | ||
| litellm-proxy-extras | ||
| scripts | ||
| tests | ||
| ui/litellm-dashboard | ||
| .dockerignore | ||
| .env.example | ||
| .flake8 | ||
| .git-blame-ignore-revs | ||
| .gitattributes | ||
| .gitguardian.yaml | ||
| .gitignore | ||
| .pre-commit-config.yaml | ||
| .trivyignore | ||
| AGENTS.md | ||
| ARCHITECTURE.md | ||
| CLAUDE.md | ||
| codecov.yaml | ||
| CONTRIBUTING.md | ||
| docker-compose.hardened.yml | ||
| docker-compose.yml | ||
| Dockerfile | ||
| GEMINI.md | ||
| index.yaml | ||
| LICENSE | ||
| Makefile | ||
| mcp_servers.json | ||
| model_prices_and_context_window.json | ||
| package-lock.json | ||
| package.json | ||
| poetry.lock | ||
| policy_templates.json | ||
| prometheus.yml | ||
| provider_endpoints_support.json | ||
| proxy_server_config.yaml | ||
| pyproject.toml | ||
| pyrightconfig.json | ||
| README.md | ||
| render.yaml | ||
| requirements.txt | ||
| ruff.toml | ||
| schema.prisma | ||
| security.md | ||
| taplo.toml | ||
| uv.lock | ||
🚅 LiteLLM
Call 100+ LLMs in OpenAI format. [Bedrock, Azure, OpenAI, VertexAI, Anthropic, Groq, etc.]
LiteLLM Proxy Server (AI Gateway) | Hosted Proxy | Enterprise Tier
Use LiteLLM for
LLMs - Call 100+ LLMs (Python SDK + AI Gateway)
All Supported Endpoints - /chat/completions, /responses, /embeddings, /images, /audio, /batches, /rerank, /a2a, /messages and more.
Python SDK
pip install litellm
from litellm import completion
import os
os.environ["OPENAI_API_KEY"] = "your-openai-key"
os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-key"
# OpenAI
response = completion(model="openai/gpt-4o", messages=[{"role": "user", "content": "Hello!"}])
# Anthropic
response = completion(model="anthropic/claude-sonnet-4-20250514", messages=[{"role": "user", "content": "Hello!"}])
AI Gateway (Proxy Server)
Getting Started - E2E Tutorial - Setup virtual keys, make your first request
pip install 'litellm[proxy]'
litellm --model gpt-4o
import openai
client = openai.OpenAI(api_key="anything", base_url="http://0.0.0.0:4000")
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
Agents - Invoke A2A Agents (Python SDK + AI Gateway)
Supported Providers - LangGraph, Vertex AI Agent Engine, Azure AI Foundry, Bedrock AgentCore, Pydantic AI
Python SDK - A2A Protocol
from litellm.a2a_protocol import A2AClient
from a2a.types import SendMessageRequest, MessageSendParams
from uuid import uuid4
client = A2AClient(base_url="http://localhost:10001")
request = SendMessageRequest(
id=str(uuid4()),
params=MessageSendParams(
message={
"role": "user",
"parts": [{"kind": "text", "text": "Hello!"}],
"messageId": uuid4().hex,
}
)
)
response = await client.send_message(request)
AI Gateway (Proxy Server)
Step 1. Add your Agent to the AI Gateway
Step 2. Call Agent via A2A SDK
from a2a.client import A2ACardResolver, A2AClient
from a2a.types import MessageSendParams, SendMessageRequest
from uuid import uuid4
import httpx
base_url = "http://localhost:4000/a2a/my-agent" # LiteLLM proxy + agent name
headers = {"Authorization": "Bearer sk-1234"} # LiteLLM Virtual Key
async with httpx.AsyncClient(headers=headers) as httpx_client:
resolver = A2ACardResolver(httpx_client=httpx_client, base_url=base_url)
agent_card = await resolver.get_agent_card()
client = A2AClient(httpx_client=httpx_client, agent_card=agent_card)
request = SendMessageRequest(
id=str(uuid4()),
params=MessageSendParams(
message={
"role": "user",
"parts": [{"kind": "text", "text": "Hello!"}],
"messageId": uuid4().hex,
}
)
)
response = await client.send_message(request)
MCP Tools - Connect MCP servers to any LLM (Python SDK + AI Gateway)
Python SDK - MCP Bridge
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
from litellm import experimental_mcp_client
import litellm
server_params = StdioServerParameters(command="python", args=["mcp_server.py"])
async with stdio_client(server_params) as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
# Load MCP tools in OpenAI format
tools = await experimental_mcp_client.load_mcp_tools(session=session, format="openai")
# Use with any LiteLLM model
response = await litellm.acompletion(
model="gpt-4o",
messages=[{"role": "user", "content": "What's 3 + 5?"}],
tools=tools
)
AI Gateway - MCP Gateway
Step 1. Add your MCP Server to the AI Gateway
Step 2. Call MCP tools via /chat/completions
curl -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Authorization: Bearer sk-1234' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Summarize the latest open PR"}],
"tools": [{
"type": "mcp",
"server_url": "litellm_proxy/mcp/github",
"server_label": "github_mcp",
"require_approval": "never"
}]
}'
Use with Cursor IDE
{
"mcpServers": {
"LiteLLM": {
"url": "http://localhost:4000/mcp",
"headers": {
"x-litellm-api-key": "Bearer sk-1234"
}
}
}
}
How to use LiteLLM
You can use LiteLLM through either the Proxy Server or Python SDK. Both gives you a unified interface to access multiple LLMs (100+ LLMs). Choose the option that best fits your needs:
| LiteLLM AI Gateway | LiteLLM Python SDK | |
|---|---|---|
| Use Case | Central service (LLM Gateway) to access multiple LLMs | Use LiteLLM directly in your Python code |
| Who Uses It? | Gen AI Enablement / ML Platform Teams | Developers building LLM projects |
| Key Features | Centralized API gateway with authentication and authorization, multi-tenant cost tracking and spend management per project/user, per-project customization (logging, guardrails, caching), virtual keys for secure access control, admin dashboard UI for monitoring and management | Direct Python library integration in your codebase, Router with retry/fallback logic across multiple deployments (e.g. Azure/OpenAI) - Router, application-level load balancing and cost tracking, exception handling with OpenAI-compatible errors, observability callbacks (Lunary, MLflow, Langfuse, etc.) |
LiteLLM Performance: 8ms P95 latency at 1k RPS (See benchmarks here)
Jump to LiteLLM Proxy (LLM Gateway) Docs
Jump to Supported LLM Providers
Stable Release: Use docker images with the -stable tag. These have undergone 12 hour load tests, before being published. More information about the release cycle here
Support for more providers. Missing a provider or LLM Platform, raise a feature request.
OSS Adopters
Netflix |
Supported Providers (Website Supported Models | Docs)
Run in Developer mode
Services
- Setup .env file in root
- Run dependant services
docker-compose up db prometheus
Backend
- (In root) create virtual environment
python -m venv .venv - Activate virtual environment
source .venv/bin/activate - Install dependencies
pip install -e ".[all]" pip install prismaprisma generate- Start proxy backend
python litellm/proxy/proxy_cli.py
Frontend
- Navigate to
ui/litellm-dashboard - Install dependencies
npm install - Run
npm run devto start the dashboard
Enterprise
For companies that need better security, user management and professional support
This covers:
- ✅ Features under the LiteLLM Commercial License:
- ✅ Feature Prioritization
- ✅ Custom Integrations
- ✅ Professional Support - Dedicated discord + slack
- ✅ Custom SLAs
- ✅ Secure access with Single Sign-On
Contributing
We welcome contributions to LiteLLM! Whether you're fixing bugs, adding features, or improving documentation, we appreciate your help.
Quick Start for Contributors
This requires poetry to be installed.
git clone https://github.com/BerriAI/litellm.git
cd litellm
make install-dev # Install development dependencies
make format # Format your code
make lint # Run all linting checks
make test-unit # Run unit tests
make format-check # Check formatting only
For detailed contributing guidelines, see CONTRIBUTING.md.
Code Quality / Linting
LiteLLM follows the Google Python Style Guide.
Our automated checks include:
- Black for code formatting
- Ruff for linting and code quality
- MyPy for type checking
- Circular import detection
- Import safety checks
All these checks must pass before your PR can be merged.
Support / talk with founders
- Schedule Demo 👋
- Community Discord 💭
- Community Slack 💭
- Our numbers 📞 +1 (770) 8783-106 / +1 (412) 618-6238
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
Why did we build this
- Need for simplicity: Our code started to get extremely complicated managing & translating calls between Azure, OpenAI and Cohere.