Credentials and models

The SDK needs an LLM provider API key to run queries. There are three ways to supply credentials.

1. Reuse CLI-stored credentials (default)

If you omit settings, the session uses a file-backed Config.default(), the same configuration the saber CLI uses. Keys you saved with saber auth are picked up automatically:

from sqlsaber import SQLSaber, SQLSaberOptions

# Uses your stored CLI credentials and configured default model.
options = SQLSaberOptions(database="sqlite:///my.db")

This is the usual choice for local scripts on a machine where you already use SQLsaber. See Authentication.

2. Environment variables

Both the default and in-memory configs check the provider’s environment variable first:

export ANTHROPIC_API_KEY="sk-..."

options = SQLSaberOptions(
    database="sqlite:///my.db",
    model_name="anthropic:claude-sonnet-4-5-20250929",
)

Each provider has its own variable:

ANTHROPIC_API_KEY
OPENAI_API_KEY
GOOGLE_API_KEY
GROQ_API_KEY
MISTRAL_API_KEY
COHERE_API_KEY
HUGGINGFACE_API_KEY
XAI_API_KEY

3. Pass keys in code

For servers, CI, or notebooks where you do not want filesystem or keyring I/O, build an in-memory Config and inject it through settings:

from sqlsaber import SQLSaber, SQLSaberOptions
from sqlsaber.config.settings import Config

options = SQLSaberOptions(
    database="sqlite:///my.db",
    settings=Config.in_memory(
        model_name="anthropic:claude-sonnet-4-5-20250929",
        api_keys={"anthropic": "sk-..."},
    ),
)

api_keys maps provider name to key. Supported keys are anthropic, openai, google, groq, mistral, cohere, huggingface, and xai.

For a single key without building a Config, set api_key on SQLSaberOptions. model_name is required so the provider can be determined:

options = SQLSaberOptions(
    database="sqlite:///my.db",
    model_name="anthropic:claude-sonnet-4-5-20250929",
    api_key="sk-...",
)

Select a model

Models are identified as "provider:model":

SQLSaberOptions(database="...", model_name="anthropic:claude-sonnet-4-5-20250929")
SQLSaberOptions(database="...", model_name="openai:gpt-5-mini")
SQLSaberOptions(database="...", model_name="google:gemini-2.5-pro")
SQLSaberOptions(database="...", model_name="xai:grok-4.6")

If model_name is omitted, the session uses your configured default model. See Models for supported providers.

Extended thinking

Reasoning models support extended thinking. Enable it and pick a level:

SQLSaberOptions(
    database="...",
    model_name="anthropic:claude-sonnet-4-5-20250929",
    thinking_level="high",  # minimal | low | medium | high | maximum
)

Setting thinking_level implies thinking_enabled=True. Set thinking_enabled on its own to use the model’s default level.