نماذج اللغة الكبيرة (LLMs)

# Required
OPENAI_API_KEY=sk-...

# Optional
OPENAI_BASE_URL=<custom-base-url>

from crewai import LLM

llm = LLM(
    model="openai/gpt-5.6-terra",
    api_key="your-api-key",  # Or set OPENAI_API_KEY
    reasoning_effort="medium",
    max_completion_tokens=4000
)

from crewai import LLM

llm = LLM(
    model="openai/gpt-5.6-terra",
    api_key="your-api-key",
    base_url="https://api.openai.com/v1",  # Optional custom endpoint
    organization="org-...",  # Optional organization ID
    project="proj_...",  # Optional project ID
    max_completion_tokens=4000,
    reasoning_effort="medium",
    stream=True,  # Enable streaming
    timeout=60.0,  # Request timeout in seconds
    max_retries=3  # Maximum retry attempts
)

from pydantic import BaseModel
from crewai import LLM

class ResponseFormat(BaseModel):
    name: str
    age: int
    summary: str

llm = LLM(
    model="openai/gpt-5.6-terra",
)

from crewai import LLM

# Use the Responses API instead of Chat Completions
llm = LLM(
    model="openai/gpt-4o",
    api="responses",  # Enable Responses API
    store=True,  # Store responses for multi-turn (optional)
    auto_chain=True,  # Auto-chain for reasoning models (optional)
)

# Meta Llama API Key Configuration
LLAMA_API_KEY=LLM|your_api_key_here

from crewai import LLM

# Initialize Meta Llama LLM
llm = LLM(
    model="meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8",
    temperature=0.8,
    stop=["END"],
    seed=42
)

# Required
SNOWFLAKE_PAT=<your-programmatic-access-token>
SNOWFLAKE_ACCOUNT_URL=https://<account-identifier>.snowflakecomputing.com

# Alternative account configuration
SNOWFLAKE_ACCOUNT=<account-identifier>

from crewai import LLM

llm = LLM(
    model="snowflake/openai-gpt-4.1",
    temperature=0.7,
    max_completion_tokens=1024,
)

from crewai import LLM

llm = LLM(
    model="snowflake/claude-sonnet-4-5",
    max_completion_tokens=1024,
    stream=True,
)

# Required
ANTHROPIC_API_KEY=sk-ant-...

from crewai import LLM

llm = LLM(
    model="anthropic/claude-sonnet-4-6",
    api_key="your-api-key",  # Or set ANTHROPIC_API_KEY
    max_tokens=4096  # Required for Anthropic
)

from crewai import LLM

llm = LLM(
    model="anthropic/claude-sonnet-4-6",
    api_key="your-api-key",
    base_url="https://api.anthropic.com",  # Optional custom endpoint
    max_tokens=4096,  # Required parameter
    stop_sequences=["END", "STOP"],  # Anthropic uses stop_sequences
    stream=True,  # Enable streaming
    timeout=60.0,  # Request timeout in seconds
    max_retries=3  # Maximum retry attempts
)

from crewai import LLM

# Enable extended thinking with default settings
llm = LLM(
    model="anthropic/claude-sonnet-4-6",
    thinking={"type": "enabled"},
    max_tokens=10000
)

# Configure thinking with budget control
llm = LLM(
    model="anthropic/claude-sonnet-4-6",
    thinking={
        "type": "enabled",
        "budget_tokens": 5000  # Limit thinking tokens
    },
    max_tokens=10000
)

# Required (one of the following)
GOOGLE_API_KEY=<your-api-key>
GEMINI_API_KEY=<your-api-key>

# For Vertex AI Express mode (API key authentication)
GOOGLE_GENAI_USE_VERTEXAI=true
GOOGLE_API_KEY=<your-api-key>

# For Vertex AI with service account
GOOGLE_CLOUD_PROJECT=<your-project-id>
GOOGLE_CLOUD_LOCATION=<location>  # Defaults to us-central1

from crewai import LLM

llm = LLM(
    model="gemini/gemini-3.6-flash",
    api_key="your-api-key",  # Or set GOOGLE_API_KEY/GEMINI_API_KEY
)

from crewai import LLM

llm = LLM(
    model="gemini/gemini-3.6-flash",
    api_key="your-api-key",
    max_output_tokens=8192,
    stop_sequences=["END", "STOP"],
    stream=True,  # Enable streaming
    safety_settings={
        "HARM_CATEGORY_HARASSMENT": "BLOCK_NONE",
        "HARM_CATEGORY_HATE_SPEECH": "BLOCK_NONE"
    }
)

GOOGLE_GENAI_USE_VERTEXAI=true
GOOGLE_API_KEY=<your-api-key>

from crewai import LLM

llm = LLM(
    model="gemini/gemini-3.6-flash"
)

from crewai import LLM

llm = LLM(
    model="gemini/gemini-3.6-flash",
    project="your-gcp-project-id",
    location="us-central1"  # GCP region
)

GOOGLE_GENAI_USE_VERTEXAI=true
GOOGLE_CLOUD_PROJECT=<your-project-id>
GOOGLE_CLOUD_LOCATION=<location>

from crewai import LLM

llm = LLM(
    model="gemini/gemini-3.6-flash"
)

# Required
AZURE_API_KEY=<your-api-key>
AZURE_ENDPOINT=<your-endpoint-url>

# Optional
AZURE_API_VERSION=<api-version>  # Defaults to 2024-06-01

llm = LLM(
    model="azure/gpt-4",
    api_key="<your-api-key>",  # Or set AZURE_API_KEY
    endpoint="<your-endpoint-url>",
    api_version="2024-06-01"
)

# Required
AWS_ACCESS_KEY_ID=<your-access-key>
AWS_SECRET_ACCESS_KEY=<your-secret-key>

# Optional
AWS_SESSION_TOKEN=<your-session-token>  # For temporary credentials
AWS_DEFAULT_REGION=<your-region>  # Defaults to us-east-1
AWS_REGION_NAME=<your-region>  # Alternative configuration for backwards compatibility with LiteLLM. Defaults to us-east-1

from crewai import LLM

llm = LLM(
    model="bedrock/us.anthropic.claude-sonnet-4-6",
    region_name="us-east-1"
)

from crewai import LLM

llm = LLM(
    model="bedrock/us.anthropic.claude-sonnet-4-6",
    aws_access_key_id="your-access-key",  # Or set AWS_ACCESS_KEY_ID
    aws_secret_access_key="your-secret-key",  # Or set AWS_SECRET_ACCESS_KEY
    aws_session_token="your-session-token",  # For temporary credentials
    region_name="us-east-1",
    temperature=0.7,
    max_tokens=4096,
    top_p=0.9,
    top_k=250,  # For Claude models
    stop_sequences=["END", "STOP"],
    stream=True,  # Enable streaming
    guardrail_config={  # Optional content filtering
        "guardrailIdentifier": "your-guardrail-id",
        "guardrailVersion": "1"
    },
    additional_model_request_fields={  # Model-specific parameters
        "top_k": 250
    }
)

AWS_ACCESS_KEY_ID=<your-access-key>
AWS_SECRET_ACCESS_KEY=<your-secret-key>
AWS_DEFAULT_REGION=<your-region>

llm = LLM(
    model="sagemaker/<my-endpoint>"
)

MISTRAL_API_KEY=<your-api-key>

llm = LLM(
    model="mistral/mistral-large-latest",
    temperature=0.7
)

NVIDIA_API_KEY=<your-api-key>

llm = LLM(
    model="nvidia_nim/nvidia/nvidia-nemotron-3-ultra-550b-a55b",
    temperature=0.7
)

from crewai.llm import LLM

local_nvidia_nim_llm = LLM(
    model="openai/meta/llama-3.1-8b-instruct", # it's an openai-api compatible model
    base_url="http://localhost:8000/v1",
    api_key="<your_api_key|any text if you have not configured it>", # api_key is required, but you can use any text
)

# Then you can use it in your crew:

@CrewBase
class MyCrew():
    # ...

    @agent
    def researcher(self) -> Agent:
        return Agent(
            config=self.agents_config['researcher'], # type: ignore[index]
            llm=local_nvidia_nim_llm
        )

    # ...

GROQ_API_KEY=<your-api-key>

llm = LLM(
    model="groq/qwen/qwen3.6-27b",
    temperature=0.7
)

# Required
WATSONX_URL=<your-url>
WATSONX_APIKEY=<your-apikey>
WATSONX_PROJECT_ID=<your-project-id>

# Optional
WATSONX_TOKEN=<your-token>
WATSONX_DEPLOYMENT_SPACE_ID=<your-space-id>

llm = LLM(
    model="watsonx/meta-llama/llama-3-1-70b-instruct",
    base_url="https://api.watsonx.ai/v1"
)

llm = LLM(
    model="ollama/llama3:70b",
    base_url="http://localhost:11434"
)

FIREWORKS_API_KEY=<your-api-key>

llm = LLM(
    model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct",
    temperature=0.7
)

PERPLEXITY_API_KEY=<your-api-key>

llm = LLM(
    model="perplexity/sonar-pro"
)

HF_TOKEN=<your-api-key>

llm = LLM(
    model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
)

SAMBANOVA_API_KEY=<your-api-key>

llm = LLM(
    model="sambanova/Meta-Llama-3.3-70B-Instruct",
    temperature=0.7
)

# Required
CEREBRAS_API_KEY=<your-api-key>

llm = LLM(
    model="cerebras/gpt-oss-120b",
    temperature=0.7,
    max_tokens=8192
)

OPENROUTER_API_KEY=<your-api-key>

llm = LLM(
    model="openrouter/deepseek/deepseek-r1",
    base_url="https://openrouter.ai/api/v1",
    api_key=OPENROUTER_API_KEY
)

NEBIUS_API_KEY=<your-api-key>

llm = LLM(
    model="nebius/Qwen/Qwen3-30B-A3B"
)