Meta Llama

Eigenschaft	Details
Beschreibung	Die Meta Llama API bietet Zugriff auf die Familie der großen Sprachmodelle von Meta.
Provider-Routing in LiteLLM	`meta_llama/`
Unterstützte Endpunkte	`/chat/completions`, `/completions`, `/responses`
API-Referenz	Llama API Referenz ↗

Erforderliche Variablen

Umgebungsvariablen
os.environ["LLAMA_API_KEY"] = ""  # your Meta Llama API key

Unterstützte Modelle

Info

Alle hier aufgeführten Modelle unter https://llama.developer.meta.com/docs/models/ werden unterstützt. Wir pflegen aktiv die Liste der Modelle, Token-Fenster usw. hier.

Modell-ID	Eingabekontextlänge	Ausgabekontextlänge	Eingabemodalitäten	Ausgabemodalitäten
`Llama-4-Scout-17B-16E-Instruct-FP8`	128k	4028	Text, Bild	Text
`Llama-4-Maverick-17B-128E-Instruct-FP8`	128k	4028	Text, Bild	Text
`Llama-3.3-70B-Instruct`	128k	4028	Text	Text
`Llama-3.3-8B-Instruct`	128k	4028	Text	Text

Verwendung - LiteLLM Python SDK

Nicht-streaming

Meta Llama Nicht-Streaming-Vervollständigung
import os
import litellm
from litellm import completion

os.environ["LLAMA_API_KEY"] = ""  # your Meta Llama API key

messages = [{"content": "Hello, how are you?", "role": "user"}]

# Meta Llama call
response = completion(model="meta_llama/Llama-3.3-70B-Instruct", messages=messages)

Streaming

Meta Llama Streaming-Vervollständigung
import os
import litellm
from litellm import completion

os.environ["LLAMA_API_KEY"] = ""  # your Meta Llama API key

messages = [{"content": "Hello, how are you?", "role": "user"}]

# Meta Llama call with streaming
response = completion(
    model="meta_llama/Llama-3.3-70B-Instruct",
    messages=messages,
    stream=True
)

for chunk in response:
    print(chunk)

Verwendung - LiteLLM Proxy

Fügen Sie Folgendes zu Ihrer LiteLLM Proxy Konfigurationsdatei hinzu

config.yaml
model_list:
  - model_name: meta_llama/Llama-3.3-70B-Instruct
    litellm_params:
      model: meta_llama/Llama-3.3-70B-Instruct
      api_key: os.environ/LLAMA_API_KEY

  - model_name: meta_llama/Llama-3.3-8B-Instruct
    litellm_params:
      model: meta_llama/Llama-3.3-8B-Instruct
      api_key: os.environ/LLAMA_API_KEY

Starten Sie Ihren LiteLLM Proxy Server

LiteLLM Proxy starten
litellm --config config.yaml

# RUNNING on http://0.0.0.0:4000

OpenAI SDK
LiteLLM SDK
cURL

Meta Llama über Proxy - Nicht-Streaming
from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="https://:4000",  # Your proxy URL
    api_key="your-proxy-api-key"       # Your proxy API key
)

# Non-streaming response
response = client.chat.completions.create(
    model="meta_llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Write a short poem about AI."}]
)

print(response.choices[0].message.content)

Meta Llama über Proxy - Streaming
from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="https://:4000",  # Your proxy URL
    api_key="your-proxy-api-key"       # Your proxy API key
)

# Streaming response
response = client.chat.completions.create(
    model="meta_llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Write a short poem about AI."}],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

Meta Llama über Proxy - LiteLLM SDK
import litellm

# Configure LiteLLM to use your proxy
response = litellm.completion(
    model="litellm_proxy/meta_llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Write a short poem about AI."}],
    api_base="https://:4000",
    api_key="your-proxy-api-key"
)

print(response.choices[0].message.content)

Meta Llama über Proxy - LiteLLM SDK Streaming
import litellm

# Configure LiteLLM to use your proxy with streaming
response = litellm.completion(
    model="litellm_proxy/meta_llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Write a short poem about AI."}],
    api_base="https://:4000",
    api_key="your-proxy-api-key",
    stream=True
)

for chunk in response:
    if hasattr(chunk.choices[0], 'delta') and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

Meta Llama über Proxy - cURL
curl https://:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-proxy-api-key" \
  -d '{
    "model": "meta_llama/Llama-3.3-70B-Instruct",
    "messages": [{"role": "user", "content": "Write a short poem about AI."}]
  }'

Meta Llama über Proxy - cURL Streaming
curl https://:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-proxy-api-key" \
  -d '{
    "model": "meta_llama/Llama-3.3-70B-Instruct",
    "messages": [{"role": "user", "content": "Write a short poem about AI."}],
    "stream": true
  }'

Weitere detaillierte Informationen zur Verwendung des LiteLLM Proxys finden Sie in der LiteLLM Proxy Dokumentation.

Meta Llama

Erforderliche Variablen​

Unterstützte Modelle​

Verwendung - LiteLLM Python SDK​

Nicht-streaming​

Streaming​

Verwendung - LiteLLM Proxy​