ooai_llm.litellm_registry

Raw LiteLLM registry exploration helpers.

Purpose:

Expose LiteLLM’s full local pricing/context registry for exploratory CLI and TUI workflows without forcing every provider into ooai’s canonical provider enum.

Design:

• Keep this separate from model_defaults because factory defaults and runtime profiles intentionally operate on first-class supported providers.

• Preserve arbitrary LiteLLM provider labels such as fireworks_ai, bedrock, openrouter, or together_ai.

• Reuse the same filter vocabulary as the supported model catalog wherever the raw metadata is available.

Classes

LiteLLMRegistryModel	One raw LiteLLM registry row with normalized display metadata.
LiteLLMRegistryResult	Result of listing raw LiteLLM registry rows.

Functions

list_litellm_registry(→ LiteLLMRegistryResult)

List LiteLLM's raw local registry across arbitrary provider labels.

Module Contents

class ooai_llm.litellm_registry.LiteLLMRegistryModel(/, **data: Any)

Bases: pydantic.BaseModel

One raw LiteLLM registry row with normalized display metadata.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

provider: str

model_key: str

model_id: str

source: str = 'litellm_registry'

display_name: str | None = None

created: int | None = None

created_at: str | None = None

input_cost_per_token: decimal.Decimal | None = None

output_cost_per_token: decimal.Decimal | None = None

max_input_tokens: int | None = None

max_output_tokens: int | None = None

mode: str | None = None

supports_vision: bool | None = None

supports_function_calling: bool | None = None

supports_tool_choice: bool | None = None

supports_parallel_tool_calls: bool | None = None

supports_structured_output: bool | None = None

raw: dict[str, Any] = None

property model_string: str

Return the LiteLLM registry key used to identify the model.

property release_date: str | None

Return the best available release-date label for display.

property input_cost_per_1m_tokens: decimal.Decimal | None

Return input-token cost normalized to one million tokens.

property output_cost_per_1m_tokens: decimal.Decimal | None

Return output-token cost normalized to one million tokens.

property context_window: int | None

Return the best known input/context window.

property supports_chat: bool

Return whether this registry row looks usable for chat/generation.

property supports_reasoning: bool

Return whether this model appears reasoning-oriented.

property supports_coding: bool

Return whether this model appears coding-oriented.

property supports_tool_calling: bool

Return whether this row appears tool/function-call capable.

property capability_labels: list[str]

Return display labels for inferred model capabilities.

class ooai_llm.litellm_registry.LiteLLMRegistryResult(/, **data: Any)

Bases: pydantic.BaseModel

Result of listing raw LiteLLM registry rows.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

models: list[LiteLLMRegistryModel] = None

notes: list[str] = None

ooai_llm.litellm_registry.list_litellm_registry(*, providers: collections.abc.Iterable[str] | None = None, include_non_chat: bool = False, capabilities: collections.abc.Iterable[ooai_llm.model_defaults.ModelCapabilityName] | None = None, min_context_tokens: int | None = None, min_output_tokens: int | None = None, max_input_cost_per_1m: decimal.Decimal | None = None, max_output_cost_per_1m: decimal.Decimal | None = None, released_after: str | None = None, released_before: str | None = None, sort_by: ooai_llm.model_defaults.ModelCatalogSortName = 'provider', strict: bool = False) → LiteLLMRegistryResult

List LiteLLM’s raw local registry across arbitrary provider labels.

Parameters:

• providers – Optional provider labels such as openrouter or fireworks_ai. Unknown labels simply produce no rows.

• include_non_chat – Include embeddings, audio, image, rerank, and other non-chat registry entries.

• capabilities – Required capability labels.

• min_context_tokens – Optional minimum context/input-token window.

• min_output_tokens – Optional minimum output-token limit.

• max_input_cost_per_1m – Optional maximum input cost per one million tokens.

• max_output_cost_per_1m – Optional maximum output cost per one million tokens.

• released_after – Optional lower release-date bound.

• released_before – Optional upper release-date bound.

• sort_by – Sort mode for returned rows.

• strict – Raise when LiteLLM cannot be imported or inspected.

Returns:

Raw registry rows and explanatory notes.