Documentation Index
Fetch the complete documentation index at: https://docs.tracia.io/llms.txt
Use this file to discover all available pages before exploring further.
The Python SDK uses LiteLLM under the hood for unified provider access. LiteLLM is included as a dependency, so no additional provider packages are needed.
Installation
LiteLLM is installed automatically with Tracia and handles all provider communication.
OpenAI
Environment Variable
OPENAI_API_KEY=sk-your-openai-key
Usage
result = client.run_local(
model="gpt-4o",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"},
],
temperature=0.7,
max_output_tokens=500,
)
Streaming
stream = client.run_local(
model="gpt-4o",
messages=[{"role": "user", "content": "Write a poem."}],
stream=True,
)
for chunk in stream:
print(chunk, end="")
Anthropic
Environment Variable
ANTHROPIC_API_KEY=sk-ant-your-anthropic-key
Usage
result = client.run_local(
model="claude-sonnet-4-20250514",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain quantum computing."},
],
temperature=0.7,
max_output_tokens=1000,
)
Streaming
stream = client.run_local(
model="claude-sonnet-4-20250514",
messages=[{"role": "user", "content": "Write a story."}],
stream=True,
)
for chunk in stream:
print(chunk, end="")
Google
Environment Variable
GOOGLE_API_KEY=your-google-api-key
Usage
result = client.run_local(
model="gemini-2.0-flash",
messages=[
{"role": "user", "content": "What are the benefits of Python?"},
],
temperature=0.5,
max_output_tokens=800,
)
Streaming
stream = client.run_local(
model="gemini-2.0-flash",
messages=[{"role": "user", "content": "Explain machine learning."}],
stream=True,
)
for chunk in stream:
print(chunk, end="")
Provider Override
The SDK automatically detects the provider based on the model name. For custom or fine-tuned models not in the built-in list, specify the provider explicitly:
# Fine-tuned OpenAI model
result = client.run_local(
model="ft:gpt-4o:my-org:custom-model:abc123",
provider="openai",
messages=[{"role": "user", "content": "Hello!"}],
)
API Key Override
Override the environment variable for a specific request:
import os
result = client.run_local(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}],
provider_api_key=os.environ["OPENAI_API_KEY_SECONDARY"],
)
- Multi-tenant applications with per-customer API keys
- Testing with different API keys
- Using organization-specific keys
Error Handling by Provider
from tracia import Tracia, TraciaError, TraciaErrorCode
try:
result = client.run_local(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}],
)
except TraciaError as error:
if error.code == TraciaErrorCode.MISSING_PROVIDER_API_KEY:
print("Set OPENAI_API_KEY environment variable")
elif error.code == TraciaErrorCode.PROVIDER_ERROR:
print(f"Provider API error: {error.message}")
elif error.code == TraciaErrorCode.UNSUPPORTED_MODEL:
print("Specify provider explicitly for custom models")
Provider Comparison
| Feature | OpenAI | Anthropic | Google | Amazon Bedrock |
|---|
| System messages | Native support | Native support | Converted internally | Vendor-dependent |
| Temperature range | 0-2 | 0-1 | 0-2 | Vendor-dependent |
| Max output tokens | Model-dependent | Model-dependent | Model-dependent | Model-dependent |
| Stop sequences | Supported | Supported | Supported | Supported |
| Streaming | Supported | Supported | Supported | Supported |
| Tool calling | Supported | Supported | Supported | Model-dependent |
Amazon Bedrock hosts models from multiple vendors (Amazon, Anthropic, Meta, Mistral, etc.). Feature support depends on the specific model. See the Bedrock page for details. 
