160a0b72cf
* fix(mcp): bill both rounds of a streamed chat completions MCP auto-execute A streamed /v1/chat/completions request with an MCP tool set to require_approval "never" runs two model calls on one logging object, and the final-stream dedupe kept only the first round's spend row. The final usage chunk also showed only the second round. The MCP stream iterator now holds the first round's assembled response, prices it, and logs one success row that carries the usage and cost of both rounds, with the fixed margin charged once. The final usage chunk shows the same summed usage. A single-round stream still logs its one row when the answer finishes. When the follow-up round fails, the first round is logged from a copy of the logging object taken before the follow-up opened, and the failure row carries only the follow-up's partial usage with no second fixed margin. With proxy post-call guardrails armed, only (assembled, cache_hit) tuples are parked for the proxy, and the deferred log is armed only while the iterator reads, so the proxy's orphaned-callback cleanup never sees it after the Router's first-chunk read * fix(mcp): send the usage chunk of a streamed chat MCP request that ends in one round When a streamed chat completions MCP request ends in its first round (the model answers without a tool call, or no tool results come back), the iterator drained the inner stream to fire its spend log and dropped the usage chunk that stream produced, so a client that asked for include_usage got no usage chunk at all. The drained usage chunk is now held and sent to the client after the final content chunk and before [DONE], the same place a plain stream sends it, so the last usage chunk matches the billed row. A two-round request still drops the first round's usage chunk and sends the merged one from the follow-up, and a stream without include_usage still sends none * fix(mcp): hold round one's log for the guardrail, bill the chunk cost once, and keep round one's id When the follow-up call of a streamed chat MCP auto-execute fails, round one's success log now goes through the proxy's deferred guardrail release instead of straight to the handlers, so a post-call guardrail runs on it and the row carries it. Without a proxy release it logs directly as before The last usage chunk now takes its cost from the combined row's billed total, so a fixed cost margin is counted once in the chunk, as it is on the row. The follow-up's usage chunk is held until the follow-up ends to make that possible The combined row now keeps round one's id, the stream's first chunk id, which matches how a single-round stream is logged * fix(mcp): bill every chat MCP stream round once on failure, hang-up, and sync drop When the follow-up call fails, round 1's success row is now logged on a copy of the logging object that does not share the request's guardrail results, so a post-call guardrail that reports on the failed request counts once instead of on both rows A client hang-up during the follow-up now bills round 1 plus the follow-up's partial answer on one success row with round 1's id and the fixed margin counted once, the same way a plain stream's hang-up bills its partial answer The last usage chunk now carries round 1's usage and cost when only round 1 is billed, and a synchronous reader that drops the stream mid-answer bills round 1 on the loop it read with instead of discarding it The deferred release's logged_on argument is typed and every release closure accepts it, and the parked dispatch constants and protocols both MCP billing paths use now live in one module. The unit tests wait on a logging signal instead of a fixed delay and check the billed row through the proxy stream hook instead of private callback state * test(mcp): drive the unassembled follow-up through an upstream audio delta that is not base64 The test replaced litellm.stream_chunk_builder with a stub that raises. Round 2 now streams an audio delta whose data is not valid base64, so the real builder raises, the stream parks only best-effort usage, and the client's last usage chunk must carry round 1's tokens and cost * fix(mcp): count the fixed margin once in the combined stream row's usage cost * fix(mcp): bill round 2's partial answer when a client hangs up on a routed stream On the proxy the Router wraps the MCP stream, and when a client hangs up during round 2 the router's own cleanup closes that stream before the proxy's disconnect cleanup runs. The close logged round 1 alone, so round 2's partial answer was never billed. The MCP stream now bills round 1 plus round 2's partial answer as soon as the hang-up's cancellation reaches its read, before anything closes it * fix(mcp): count the follow-up's own messages in round 2's partial prompt The follow-up stream shares the request's logger, so it took the client's original messages as its prompt. When round 2 ended early, from a hang-up or a broken upstream, its partial usage counted only those messages and left out the assistant tool call and the tool results the follow-up actually sent. The follow-up stream now counts the messages the follow-up call sent * fix(mcp): bill round 2's partial when a routed stream's client hangs up between reads On a proxy the stream the disconnect cleanup holds is the router's fallback wrapper, so the cleanup never found the MCP stream's in-flight billing and released round 1 alone when the client hung up while the proxy sat at a yield. The round billing now registers its in-flight biller on the request's logging object, next to the parked release, and the cleanup looks it up there, so any wrapper chain bills round 1 plus round 2's partial once * fix(mcp): send the MCP stream usage chunk under the billed row id and count the partial off the loop A streamed chat completion that runs a LiteLLM-hosted MCP tool bills both model calls on one row under round 1's chatcmpl id, but the usage chunk it sent the client was round 2's held chunk and kept round 2's id, so a caller could not join the usage chunk to its row. The usage chunk now carries round 1's id in every path that sends it, with or without a deferred post-call guardrail, while its usage and cost and every content chunk's id stay as they were When the client hangs up during round 2, assembling round 2's partial answer counts the follow-up messages, tool result included, with the local tokenizer. That ran on the event loop and stalled every other request on the worker for about a second on a large tool result. The assembly now runs on a worker thread through asyncify from both the reader's cancellation and the proxy's disconnect cleanup, shielded from cancellation, and round 1 is checked again after the await so a release that happened meanwhile is never billed twice * test(mcp): wait on the loop with a hang guard instead of a 300 ms deadline * fix(mcp): give a proxy-rejected follow-up's failure row round 1's own cost breakdown * refactor(streaming): fold the partial response's empty guards into one check --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|---|---|---|
| .agents/skills/database-access | ||
| .cargo | ||
| .circleci | ||
| .devcontainer | ||
| .githooks | ||
| .github | ||
| .semgrep/rules | ||
| backend | ||
| ci_cd | ||
| cookbook | ||
| db_scripts | ||
| docker | ||
| docs/adrs | ||
| enterprise | ||
| examples | ||
| gateway | ||
| helm | ||
| litellm | ||
| litellm-proxy-extras | ||
| litellm-rust | ||
| litellm_cli | ||
| migrations | ||
| packaging | ||
| scripts | ||
| skills/litellm-setup | ||
| terraform | ||
| tests | ||
| ui | ||
| vscode-extension | ||
| .dockerignore | ||
| .env.example | ||
| .git-blame-ignore-revs | ||
| .gitattributes | ||
| .gitguardian.yaml | ||
| .gitignore | ||
| .grype.yaml | ||
| .npmrc | ||
| AGENTS.md | ||
| ARCHITECTURE.md | ||
| codecov.yaml | ||
| CONTRIBUTING.md | ||
| cosign.pub | ||
| docker-compose.hardened.yml | ||
| docker-compose.liteadmin.yml | ||
| docker-compose.yml | ||
| Dockerfile | ||
| GEMINI.md | ||
| LICENSE | ||
| license_cache.json | ||
| Makefile | ||
| mcp_servers.json | ||
| model_prices_and_context_window.json | ||
| osv-scanner.toml | ||
| package-lock.json | ||
| package.json | ||
| policy_templates.json | ||
| prometheus.yml | ||
| provider_endpoints_support.json | ||
| proxy_server_config.yaml | ||
| pyproject.toml | ||
| pyrightconfig.json | ||
| qa_sticky_session.sh | ||
| README.md | ||
| render.yaml | ||
| router_plugins.json | ||
| ruff-strict.toml | ||
| ruff-tests.toml | ||
| ruff.toml | ||
| rust-toolchain.toml | ||
| schema.prisma | ||
| SECURITY.md | ||
| taplo.toml | ||
| uv.lock | ||
| whitelisted_bedrock_models.txt | ||
🚅 LiteLLM
LiteLLM AI Gateway
Open Source AI Gateway for 100+ LLMs. Self-hosted. Enterprise-ready. Call any LLM in OpenAI format.
LiteLLM Proxy Server (AI Gateway) | Hosted Proxy | Enterprise Tier | Website
What is LiteLLM
LiteLLM is an open source AI Gateway that gives you a single, unified interface to call 100+ LLM providers — OpenAI, Anthropic, Gemini, Bedrock, Azure, and more — using the OpenAI format.
Use it as a Python SDK for direct library integration, or deploy the AI Gateway (Proxy Server) as a centralized service for your team or organization.
Jump to LiteLLM Proxy (LLM Gateway) Docs
Jump to Supported LLM Providers
Why LiteLLM
Managing LLM calls across providers gets complicated fast — different SDKs, auth patterns, request formats, and error types for every model. LiteLLM removes that friction:
- Unified API — one interface for 100+ LLMs, no provider-specific SDK juggling
- Drop-in OpenAI compatibility — swap providers without rewriting your code
- Production-ready gateway — virtual keys, spend tracking, guardrails, load balancing, and an admin dashboard out of the box
- 8ms P95 latency at 1k RPS (benchmarks)
OSS Adopters
Netflix |
Features
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
uv add litellm
An independent litellm-core distribution provides the Python SDK with the same
import litellm API and runtime dependencies. It has no optional extras, CLI entry
points, or bundled dashboard. Install one SDK distribution per environment because
litellm and litellm-core own overlapping Python files. Use litellm for the
proxy, CLI, and optional extras
Build and install core from this checkout while its release integration is pending:
python scripts/build_core_distribution.py --out-dir dist/core
python -m pip install dist/core/litellm_core-*.whl
The builder requires Git, uv and the Rust build toolchain. It reads the release version
from the root pyproject.toml, leaves source files unchanged, and produces a wheel
and a self-contained sdist in dist/core. Run installation in a fresh environment
without 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
uv tool 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!"}]
)
Auto Routing - Choose a model for each prompt (Python SDK + AI Gateway)
Python SDK
Install with uv add litellm and set OPENAI_API_KEY for the models below.
import asyncio
from litellm import Router
router = Router(model_list=[
{"model_name": "fast", "litellm_params": {"model": "openai/gpt-6-luna"}},
{"model_name": "capable", "litellm_params": {"model": "openai/gpt-6.1-sol"}},
{"model_name": "auto", "litellm_params": {
"model": "auto_router/complexity_router",
"complexity_router_config": {
"classifier_type": "heuristic",
"tiers": {"SIMPLE": "fast", "MEDIUM": "fast",
"COMPLEX": "capable", "REASONING": "capable"},
"return_raw_model_name": True,
},
"complexity_router_default_model": "capable",
}},
])
response = asyncio.run(router.acompletion(
model="auto", messages=[{"role": "user", "content": "What is 2+2?"}],
))
print(response.model, response.choices[0].message.content)
AI Gateway (Proxy Server)
Create an Auto Router, then call its model name. Replace auto and the URL below with yours, and set LITELLM_API_KEY to your virtual key.
curl http://localhost:4000/v1/chat/completions \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"auto","messages":[{"role":"user","content":"What is 2+2?"}]}'
A2A - 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 — set protocolVersion to 1.0 or 0.3 per agent
Step 2. Call Agent via A2A SDK (requires a2a-sdk>=1.1.0)
import httpx
from a2a.client import A2ACardResolver, ClientConfig, ClientFactory
from a2a.types import Message, Part, Role, SendMessageRequest
from a2a.utils.constants import TransportProtocol
from uuid import uuid4
base_url = "http://localhost:4000/a2a/my-agent" # LiteLLM proxy + agent name
headers = {"Authorization": "Bearer <your-master-key>"} # LiteLLM master key or a virtual key
async with httpx.AsyncClient(headers=headers, timeout=60.0) as http_client:
resolver = A2ACardResolver(httpx_client=http_client, base_url=base_url)
agent_card = await resolver.get_agent_card()
config = ClientConfig(
httpx_client=http_client,
streaming=False,
supported_protocol_bindings=[TransportProtocol.JSONRPC, TransportProtocol.HTTP_JSON],
)
client = ClientFactory(config).create(agent_card)
request = SendMessageRequest(
message=Message(
message_id=uuid4().hex,
role=Role.ROLE_USER,
parts=[Part(text="Hello!")],
)
)
async for event in client.send_message(request):
populated = event.ListFields()
if populated and populated[0][0].name in ("message", "msg"):
print("".join(getattr(p, "text", "") or "" for p in populated[0][1].parts))
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 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 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 <your-master-key>' \
-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 <your-master-key>"
}
}
}
}
For MCP OAuth, an upstream may advertise dynamic client registration but refuse requests with HTTP 401 or 403. If the provider requires a pre-registered OAuth app, configure its credentials.client_id and, when required, credentials.client_secret on the MCP server. This skips dynamic registration in the gateway sign-in flow. The provider must approve the app for MCP access; reaching its authorization page does not establish that login or tool calls will succeed
Agents - Run Claude Code, Codex, OpenCode, pi or Deep Agents on any model (Python SDK)
Python SDK - Agents
import litellm
from litellm import Harness, sandbox
result = litellm.agent(
Harness.CLAUDE_CODE, # or Harness.CODEX, Harness.OPENCODE, Harness.PI, Harness.DEEPAGENTS
"Find why tests/test_router.py is flaky and fix it.",
sandbox=sandbox.local("./repo"),
model="litellm_proxy/claude-sonnet-4-5", # a model group on your AI Gateway
)
print(result.text, result.cost, [f.path for f in result.files])
Set LITELLM_PROXY_API_BASE and LITELLM_PROXY_API_KEY and every model call the agent makes goes through your AI Gateway, tagged harness,claude_code. Drop the litellm_proxy/ prefix to call a provider directly. Install starlette uvicorn plus the agent's CLI (claude, codex, opencode or pi), or deepagents langchain-litellm for Deep Agents.
Supported Providers (Website Supported Models | Docs)
Get Started
You can use LiteLLM through either the Proxy Server or Python SDK. Both give 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.) |
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.
Deploy on AWS or GCP with Terraform
Run the LiteLLM proxy as a production-ready componentized stack (gateway, backend, UI on separate services; managed Postgres + Redis + object store) using the published Terraform modules. Both modules are on the public Terraform Registry — no auth needed.
AWS — ECS Fargate + Aurora + ElastiCache + ALB
git clone https://github.com/BerriAI/litellm.git
cd litellm/terraform/litellm/aws/examples/default
cp terraform.tfvars.example terraform.tfvars # edit region/tenant/env
terraform init && terraform apply
Or call the module from your own root config:
# main.tf
terraform {
required_version = ">= 1.6.0"
required_providers {
aws = { source = "hashicorp/aws", version = "~> 5.60" }
}
}
provider "aws" {
region = "us-west-2"
}
module "litellm" {
source = "BerriAI/litellm/aws"
version = "~> 1.89"
region = "us-west-2"
azs = ["us-west-2a", "us-west-2b"]
tenant = "acme"
env = "prod"
# Production: provide an ACM cert. Without one, set allow_plaintext_alb = true
# (dev/trial only).
# acm_certificate_arn = "arn:aws:acm:us-west-2:111122223333:certificate/..."
allow_plaintext_alb = true
}
output "litellm_url" {
value = module.litellm.alb_dns_name
}
terraform init
terraform apply
Provider API keys live in AWS Secrets Manager; reference ARNs via gateway_extra_secrets. Full input list and architecture diagram on the registry page.
GCP — Cloud Run + Cloud SQL + Memorystore + HTTPS LB
Real 1-click. Opens Cloud Shell, clones the terraform-google-litellm module mirror at the latest stable release (a small download instead of the full litellm repo), and walks you through terraform apply via a built-in DeployStack tutorial. Pick the project, the tutorial sets up the Artifact Registry remote repo, writes terraform.tfvars from your answers, and runs apply
To call the module from your own config instead, Cloud Run can't pull from ghcr.io directly, so first set up a one-time Artifact Registry remote repo backed by GHCR:
gcloud artifacts repositories create litellm \
--location=us-central1 \
--repository-format=docker \
--mode=remote-repository \
--remote-docker-repo=https://ghcr.io \
--project=my-gcp-project
Then:
# main.tf
terraform {
required_version = ">= 1.6.0"
required_providers {
google = { source = "hashicorp/google", version = "~> 6.10" }
google-beta = { source = "hashicorp/google-beta", version = "~> 6.10" }
}
}
provider "google" { project = "my-gcp-project"; region = "us-central1" }
provider "google-beta" { project = "my-gcp-project"; region = "us-central1" }
module "litellm" {
source = "BerriAI/litellm/google"
version = "~> 1.89"
project_id = "my-gcp-project"
region = "us-central1"
tenant = "acme"
env = "prod"
# Replace my-gcp-project with your GCP project ID (same value as project_id above).
image_registry = "us-central1-docker.pkg.dev/my-gcp-project/litellm/berriai"
# Production: provide DNS already pointing at the LB IP for Google-managed certs.
# Without one, set allow_plaintext_lb = true (dev/trial only).
# lb_domains = ["proxy.example.com"]
allow_plaintext_lb = true
}
output "litellm_url" {
value = module.litellm.load_balancer_url
}
terraform init
terraform apply
Provider API keys live in Secret Manager; reference resource IDs (e.g. projects/my-gcp-project/secrets/openai-api-key) via gateway_extra_secrets. Full input list and architecture diagram on the registry page.
Both stacks include
- The full componentized split (gateway / backend / UI as independent services)
- Managed Postgres (writer + reader) and Redis
- Versioned object store for proxy state + file uploads
- An auto-generated
LITELLM_MASTER_KEYin your cloud's secret manager - A one-off migration job that runs
prisma migrate deploybefore the proxy starts - The same
proxy_configsurface as the Helm chart — pass YAML as a typed map
The Terraform modules live at terraform/litellm/aws/ and terraform/litellm/gcp/ in this repo; the registry entries are read-only mirrors updated on each release.
Run in Developer Mode
Services
- Setup .env file in root
- Run dependent services
docker-compose up db prometheus
Backend
- Run
make bootstrap - Start proxy backend:
uv run python litellm/proxy/proxy_cli.py
Frontend
- Navigate to
ui/litellm-dashboard(dependencies were already installed w/make bootstrap) - Start dashboard:
npm run dev
Verify Docker Image Signatures
All LiteLLM Docker images published to GHCR are signed with cosign. Releases are signed with the key introduced in commit e82a3c6.
Verify using the pinned commit hash (recommended):
A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the published signing key:
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:<release-tag>
Verify using a release tag (convenience):
Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/<release-tag>/cosign.pub \
ghcr.io/berriai/litellm:<release-tag>
Replace <release-tag> with the version you are deploying (e.g. v1.83.0-stable).
Enterprise
For companies that need better security, user management and professional support
Get an Enterprise License Talk to founders
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.
If you want to work closely with our team, check out LiteLLM OSS Champions, our program for trusted OSS contributors with their own Slack channel and a voice in the roadmap
Quick Start for Contributors
This requires uv 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.
📖 Contributing to documentation? The LiteLLM docs have moved to a separate repository: BerriAI/litellm-docs. Please open doc PRs there. Docs are served at docs.litellm.ai.
Code Quality / Linting
LiteLLM follows the Google Python Style Guide.
Our automated checks include:
- Ruff for formatting, linting, and code quality
- basedpyright 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 emails ✉️ ishaan@berri.ai / krrish@berri.ai