diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py index 245f65eb69c..961f61d6fca 100644 --- a/litellm/cost_calculator.py +++ b/litellm/cost_calculator.py @@ -1403,7 +1403,7 @@ def completion_cost( total_time: float | None = 0.0, # used for replicate, sagemaker call_type: CallTypesLiteral | None = None, ### REGION ### - custom_llm_provider=None, + custom_llm_provider: str | None = None, region_name=None, # used for bedrock pricing ### IMAGE GEN ### size: str | None = None, @@ -1549,6 +1549,7 @@ def completion_cost( region_name=region_name, ) + requested_model: Final = model potential_model_names: Final = [ selected_model, _get_response_model(completion_response), @@ -1708,15 +1709,17 @@ def completion_cost( video_generation_cost, ) - return ( - video_generation_cost( - model=model, - duration_seconds=duration_seconds, - custom_llm_provider=custom_llm_provider, - model_info=_video_model_info, - video_resolution=video_resolution, - ) - * video_count + return video_generation_cost( + model=model, + duration_seconds=duration_seconds, + custom_llm_provider=custom_llm_provider, + model_info=_video_model_info, + video_resolution=video_resolution, + ) * video_count + _video_input_image_cost( + requested_model or model, + custom_llm_provider, + _video_model_info, + getattr(completion_response, "usage", None), ) # Fallback to default video cost calculation if no duration available return default_video_cost_calculator( @@ -2168,6 +2171,27 @@ def response_cost_calculator( raise e +def _video_input_image_cost( + model: str, + custom_llm_provider: str | None, + model_info: ModelInfo | None, + usage: object, +) -> float: + match usage: + case {"billable_input_image_count": int(billable_input_images)} if billable_input_images > 0: + deployment_rate: Final = model_info.get("input_cost_per_image") if model_info is not None else None + image_rate: Final = ( + deployment_rate + if deployment_rate is not None + else litellm.get_model_info(model=model, custom_llm_provider=custom_llm_provider).get( + "input_cost_per_image" + ) + ) + return billable_input_images * image_rate if isinstance(image_rate, (int, float)) else 0.0 + case _: + return 0.0 + + _LOGGED_LITELLM_PARAMS: Final = TypeAdapter(Mapping[str, object]) diff --git a/litellm/llms/minimax/videos/__init__.py b/litellm/llms/minimax/videos/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/litellm/llms/minimax/videos/transformation.py b/litellm/llms/minimax/videos/transformation.py new file mode 100644 index 00000000000..7d458cb8877 --- /dev/null +++ b/litellm/llms/minimax/videos/transformation.py @@ -0,0 +1,856 @@ +""" +MiniMax V2 video task API: create, poll, list, download and delete. Regeneration (/v2/video_regeneration) +only upscales a finished 768P task to 2K and ignores the prompt, so it is not exposed as an OpenAI remix. +""" + +import base64 +import re +import time +from collections.abc import Mapping, Sequence +from io import BufferedReader, BytesIO +from math import gcd +from types import MappingProxyType +from typing import TYPE_CHECKING, Final, Literal, TypeVar + +import httpx +from httpx._types import RequestFiles +from pydantic import BaseModel, Field, TypeAdapter, ValidationError + +import litellm +from litellm.exceptions import BadRequestError, UnsupportedParamsError +from litellm.images.utils import ImageEditRequestUtils +from litellm.litellm_core_utils.url_utils import ( + async_safe_get, + encode_url_path_segment, + safe_get, +) +from litellm.llms.base_llm.chat.transformation import BaseLLMException +from litellm.llms.base_llm.videos.transformation import BaseVideoConfig +from litellm.llms.custom_httpx.http_handler import ( + AsyncHTTPHandler, + HTTPHandler, + _get_httpx_client, # pyright: ignore[reportPrivateUsage, reportUnknownVariableType] # house cached-client factory has no public alias and its stub leaves params untyped + get_async_httpx_client, # pyright: ignore[reportUnknownVariableType] # factory stub leaves params untyped +) +from litellm.secret_managers.main import get_secret_str +from litellm.types.router import GenericLiteLLMParams +from litellm.types.videos.main import VideoCreateOptionalRequestParams, VideoObject +from litellm.types.videos.utils import ( + decode_video_id_with_provider, + encode_video_id_with_provider, + extract_original_video_id, +) +from litellm.utils import get_model_info + +if TYPE_CHECKING: + from litellm.litellm_core_utils.litellm_logging import Logging + + +class MinimaxVideoError(BaseLLMException): + pass + + +class _TaskError(BaseModel, frozen=True): + code: str | None = None + message: str | None = None + + +class _TaskUsage(BaseModel, frozen=True): + total_seconds: int | None = None + input_seconds: int | None = None + output_seconds: int | None = None + input_image_count: int | None = None + input_audio_seconds: int | None = None + + +class _TaskContent(BaseModel, frozen=True): + url: str | None = None + prompt: str | None = None + + +class _ContentItem(BaseModel, frozen=True): + type: str = "" + text: str | None = None + role: str | None = None + + +class _MediaUrl(BaseModel, frozen=True, extra="forbid"): + url: str + + +class _CallerMediaItem(BaseModel, frozen=True, extra="forbid"): + type: Literal["image_url", "video_url", "audio_url"] + image_url: _MediaUrl | None = None + video_url: _MediaUrl | None = None + audio_url: _MediaUrl | None = None + role: Literal["first_frame", "last_frame", "reference_image", "reference_video", "reference_audio"] | None = None + + +class _MiniMaxTask(BaseModel, frozen=True): + id: str = Field(min_length=1) + model: str | None = None + status: str + error: _TaskError | None = None + created_at: int | None = None + updated_at: int | None = None + content: _TaskContent | None = None + resolution: str | None = None + duration: int | None = None + usage: _TaskUsage | None = None + ratio: str | None = None + task_type: str | None = None + modality: str | None = None + + +class _TaskIdResponse(BaseModel, frozen=True): + task_id: str = Field(min_length=1) + + +class _TaskResponse(BaseModel, frozen=True): + task: _MiniMaxTask + + +class _ListResponse(BaseModel, frozen=True): + items: Sequence[_MiniMaxTask] | None = None + total: int | None = None + + +class _DeleteResponse(BaseModel, frozen=True): + task_id: str = Field(min_length=1) + status: str + + +MINIMAX_VIDEO_DEFAULT_API_BASE: Final = "https://api.minimax.io" +MINIMAX_VIDEO_DEFAULT_RESOLUTION: Final = "768P" +MINIMAX_VIDEO_DEFAULT_DURATION_SECONDS: Final = 5 +MINIMAX_TEXT_TO_VIDEO_DEFAULT_RATIO: Final = "16:9" + +_EMPTY_PARAMS: Final[dict[str, object]] = {} # mutable-ok: BaseVideoConfig contract empty params + +_RESPONSE_ADAPTER: Final = TypeAdapter(dict[str, object]) +_TASK_ID_RESPONSE_ADAPTER: Final = TypeAdapter(_TaskIdResponse) +_TASK_RESPONSE_ADAPTER: Final = TypeAdapter(_TaskResponse) +_LIST_RESPONSE_ADAPTER: Final = TypeAdapter(_ListResponse) +_DELETE_RESPONSE_ADAPTER: Final = TypeAdapter(_DeleteResponse) +_CONTENT_ITEMS_ADAPTER: Final = TypeAdapter(list[_ContentItem]) +_CALLER_MEDIA_ADAPTER: Final = TypeAdapter(list[_CallerMediaItem]) +_FILE_TUPLE_ADAPTER: Final = TypeAdapter(tuple[object, ...]) +_DROP_KEYS_ADAPTER: Final = TypeAdapter(frozenset[str]) +_PARAMETERS_ADAPTER: Final = TypeAdapter(dict[str, object]) + +_STATUS_MAP: Final = MappingProxyType( + { + "queued": "queued", + "running": "in_progress", + "succeeded": "completed", + "failed": "failed", + "cancelled": "cancelled", + } +) + +_DROP_FROM_CREATE_BODY: Final = frozenset( + { + "model", + "prompt", + "user", + "extra_headers", + "extra_query", + "extra_body", + "drop_params", + "additional_drop_params", + } +) + +_CONTENT_VARIANT: Final = "video" + +_CREATE_BODY_KEYS: Final = ( + "resolution", + "duration", + "ratio", + "callback_url", + "aigc_watermark", + "extra", +) + +_CREATE_REQUEST_PARAMS: Final = frozenset({*_CREATE_BODY_KEYS, "content", "input_reference"}) + +_TASK_NOT_FOUND_MESSAGE: Final = "record not found" + +_ParsedT: Final = TypeVar("_ParsedT") + + +def _minimax_error(status_code: int, message: str) -> MinimaxVideoError: + """ + The video handlers rebuild provider errors from ``response.text``, so the message has to ride on the + response as well or it reaches the caller empty. + """ + request: Final = httpx.Request(method="GET", url=MINIMAX_VIDEO_DEFAULT_API_BASE) + return MinimaxVideoError( + status_code=status_code, + message=message, + request=request, + response=httpx.Response(status_code=status_code, text=message, request=request), + ) + + +def _parse_response(adapter: TypeAdapter[_ParsedT], raw_response: httpx.Response) -> _ParsedT: + try: + return adapter.validate_python(raw_response.json()) + except ValueError as e: + raise _minimax_error(502, f"Unexpected MiniMax video response: {raw_response.text}") from e + + +def _parse_task_response(raw_response: httpx.Response) -> _MiniMaxTask: + return _parse_response(_TASK_RESPONSE_ADAPTER, raw_response).task + + +def _parse_task_id_response(raw_response: httpx.Response) -> str: + return _parse_response(_TASK_ID_RESPONSE_ADAPTER, raw_response).task_id + + +def _parse_delete_response(raw_response: httpx.Response) -> tuple[str, str]: + deleted: Final = _parse_response(_DELETE_RESPONSE_ADAPTER, raw_response) + return deleted.task_id, deleted.status + + +MINIMAX_SURFACE_SUFFIXES: Final = ("/v1", "/v2", "/anthropic") + + +def _normalized_api_base(api_base: str) -> str: + """ + A MiniMax key covers the chat surfaces (``/v1``, ``/anthropic``) and video (``/v2``), so strip whichever + surface suffix a shared api_base carries back to the host. + """ + trimmed: Final = api_base.rstrip("/") + matched: Final = next((suffix for suffix in MINIMAX_SURFACE_SUFFIXES if trimmed.endswith(suffix)), None) + return trimmed[: -len(matched)] if matched else trimmed + + +def _invalid_param(param: str, value: object, expected: str, model: str) -> BadRequestError: + return BadRequestError( + message=f"Invalid {param} {value!r} for MiniMax video generation: expected {expected}.", + model=model, + llm_provider="minimax", + ) + + +_SIZE_OR_RATIO: Final = re.compile(r"(\d+)[x:](\d+)") + + +def _ratio_from_size(size: object, model: str) -> str: + """OpenAI ``size`` is ``WIDTHxHEIGHT``; MiniMax takes the reduced ``W:H`` ratio, which is also accepted as is.""" + matched: Final = _SIZE_OR_RATIO.fullmatch(size) if isinstance(size, str) else None + width: Final = int(matched.group(1)) if matched else 0 + height: Final = int(matched.group(2)) if matched else 0 + if width <= 0 or height <= 0: + raise _invalid_param("size", size, "WIDTHxHEIGHT or W:H with positive integers, e.g. 1280x720", model) + divisor: Final = gcd(width, height) + return f"{width // divisor}:{height // divisor}" + + +def _whole_seconds(seconds: object) -> int: + if isinstance(seconds, int) and not isinstance(seconds, bool): + return seconds + if isinstance(seconds, str) and seconds.isdigit(): + return int(seconds) + return 0 + + +def _duration_param(seconds: object, model: str) -> int: + parsed: Final = _whole_seconds(seconds) + if parsed <= 0: + raise _invalid_param("seconds", seconds, "a positive whole number of seconds", model) + return parsed + + +def _read_all_bytes(file_obj: object) -> bytes: + if isinstance(file_obj, (BytesIO, BufferedReader)): + current_position: Final = file_obj.tell() + file_obj.seek(0) + content: Final = file_obj.read() + file_obj.seek(current_position) + return content + if isinstance(file_obj, bytes): + return file_obj + if isinstance(file_obj, bytearray): + return bytes(file_obj) + read: Final = getattr(file_obj, "read", None) + if callable(read): + data: Final = read() + if isinstance(data, bytes): + return data + raise ValueError("input_reference must be a URL string, bytes, a file object, or a (filename, file) tuple") + + +def _file_tuple_parts(file_tuple: tuple[object, ...]) -> tuple[object, str | None]: + match file_tuple: + case (_, file_content, str() as declared_type, *_) if declared_type: + return file_content, declared_type + case (_, file_content, *_): + return file_content, None + case _: + raise ValueError("input_reference tuples must be (filename, file) or (filename, file, content_type)") + + +def _image_url(image: object) -> str: + if isinstance(image, str): + return image + file_content, declared_type = ( + _file_tuple_parts(_FILE_TUPLE_ADAPTER.validate_python(image)) if isinstance(image, tuple) else (image, None) + ) + content_type: Final = declared_type or ImageEditRequestUtils.get_image_content_type(file_content) + encoded: Final = base64.b64encode(_read_all_bytes(file_content)).decode("utf-8") + return f"data:{content_type};base64,{encoded}" + + +def _first_frame_content_item( + image: object, +) -> dict[str, object]: # mutable-ok: content items are JSON request-body fragments + return { + "type": "image_url", + "image_url": {"url": _image_url(image)}, + "role": "first_frame", + } + + +def _content_items(content: object) -> tuple[_ContentItem, ...]: + if not isinstance(content, Sequence) or isinstance(content, (str, bytes)): + return () + try: + return tuple(_CONTENT_ITEMS_ADAPTER.validate_python(content)) + except ValidationError: + return () + + +def _is_text_only_content(content: object) -> bool: + if not isinstance(content, Sequence) or isinstance(content, (str, bytes)) or not content: + return False + try: + items: Final = _CONTENT_ITEMS_ADAPTER.validate_python(content) + except ValidationError: + return False + return all(item.type == "text" for item in items) + + +def _video_object_from_task(task: _MiniMaxTask) -> VideoObject: + status: Final = _STATUS_MAP.get(task.status) + if status is None: + raise _minimax_error(502, f"MiniMax returned unknown video task status {task.status!r} for task {task.id}") + usage_dump: Final = task.usage.model_dump(exclude_none=True) if task.usage is not None else None + return VideoObject( + id=task.id, + object="video", + status=status, + created_at=task.created_at, + completed_at=task.updated_at if status == "completed" else None, + error=task.error.model_dump(exclude_none=True) if task.error is not None else None, + seconds=str(task.duration) if task.duration is not None else None, + model=task.model, + usage=usage_dump or None, + ) + + +def _polled_model_id(logging_obj: object) -> str | None: + litellm_params: Final[object] = getattr(logging_obj, "litellm_params", None) + match litellm_params: + case {"video_id": str(video_id)}: + return decode_video_id_with_provider(video_id).get("model_id") or None + case _: + return None + + +def _routed_model_id(logging_obj: object) -> str | None: + """ + A list has no id to read a model back from, so a task MiniMax leaves `model` off falls back to the group the + router was asked for. The router stamps the group into litellm_metadata, and metadata carries a copy only when + the caller sent none. + """ + litellm_params: Final[object] = getattr(logging_obj, "litellm_params", None) + try: + params: Final = _PARAMETERS_ADAPTER.validate_python(litellm_params) + except ValidationError: + return None + stamped: Final = (_model_group_from_metadata(params.get(key)) for key in ("litellm_metadata", "metadata")) + return next((group for group in stamped if group is not None), None) + + +def _model_group_from_metadata(metadata: object) -> str | None: + try: + fields: Final = _PARAMETERS_ADAPTER.validate_python(metadata) + except ValidationError: + return None + group: Final = fields.get("model_group") + return group if isinstance(group, str) and group else None + + +def _additional_drop_keys(params: Mapping[str, object]) -> frozenset[str]: + try: + return _DROP_KEYS_ADAPTER.validate_python(params.get("additional_drop_params") or ()) + except ValidationError: + return frozenset() + + +def _parameters_fields(value: object, model: str) -> Mapping[str, object]: + try: + return MappingProxyType(_RESPONSE_ADAPTER.validate_python(value)) + except ValidationError as e: + raise _invalid_param("parameters", value, "an object of MiniMax request fields", model) from e + + +def _billable_input_image_count(model: str, input_image_count: int) -> int: + """MiniMax bills input images beyond a per-model free allowance on top of output seconds.""" + try: + info: Final = get_model_info(model=model, custom_llm_provider="minimax") + except Exception: # noqa: BLE001 # get_model_info raises plain Exception for an unmapped model + return 0 + provider_specific: Final = info.get("provider_specific_entry") + free_images: Final = ( + provider_specific.get("minimax_free_input_images") if isinstance(provider_specific, Mapping) else None + ) + if not isinstance(free_images, int) or isinstance(free_images, bool): + return 0 + return max(0, input_image_count - free_images) + + +_TIER_COST_PREFIX: Final = "output_cost_per_second_" + + +def _priced_resolutions(model: str) -> frozenset[str]: + try: + info: Final = get_model_info(model=model, custom_llm_provider="minimax") + except Exception: # noqa: BLE001 # get_model_info raises plain Exception for an unmapped model + return frozenset() + return frozenset( + key.removeprefix(_TIER_COST_PREFIX) + for key, cost in info.items() + if key.startswith(_TIER_COST_PREFIX) and cost is not None + ) + + +def _unpriced_resolution_drop(model: str, resolution: object, litellm_params: GenericLiteLLMParams) -> frozenset[str]: + priced: Final = _priced_resolutions(model) + if not priced or not isinstance(resolution, str) or resolution.strip().lower() in priced: + return frozenset() + if litellm_params.drop_params is True or litellm.drop_params is True: + return frozenset({"resolution"}) + raise UnsupportedParamsError( + message=( + f"MiniMax {model} has no price for resolution {resolution!r} in litellm's cost map, so it would bill at " + f"another tier's rate. Use one of {', '.join(sorted(tier.upper() for tier in priced))}, or set " + "drop_params=True to send MiniMax's default resolution instead." + ), + model=model, + llm_provider="minimax", + ) + + +def _video_url_from_task(task: _MiniMaxTask) -> str: + """A download before the video is ready is the caller polling too early, so it answers 400, which the + router neither retries nor counts toward a deployment cooldown the way it counts a 404.""" + if task.content is not None and task.content.url: + return task.content.url + + if task.status in ("queued", "running"): + raise _minimax_error( + 400, f"Video is still processing (status: {task.status}). Poll the video until it is completed." + ) + if task.error is not None: + raise _minimax_error(400, f"Video generation failed: {task.error.message or 'unknown error'}") + raise _minimax_error(400, f"Video has no downloadable content (status: {task.status}).") + + +def _remix_unsupported() -> UnsupportedParamsError: + return UnsupportedParamsError( + message=( + "Video remix is not supported by MiniMax. Its regeneration endpoint only upscales a finished 768P " + "MiniMax-H3 task to 2K and ignores the prompt; send a new video_generation() request with the edited " + "prompt instead." + ), + llm_provider="minimax", + ) + + +class MinimaxVideoConfig(BaseVideoConfig): + def get_supported_openai_params(self, model: str) -> list[str]: # mutable-ok: BaseVideoConfig contract returns list + return [ + "model", + "prompt", + "input_reference", + "seconds", + "size", + "resolution", + "user", + "extra_headers", + "duration", + "ratio", + "content", + "callback_url", + "aigc_watermark", + "extra", + "parameters", + ] + + def map_openai_params( + self, + video_create_optional_params: VideoCreateOptionalRequestParams, + model: str, + drop_params: bool, + ) -> dict[str, object]: # mutable-ok: BaseVideoConfig contract + mapped_params: Final[dict[str, object]] = {} # mutable-ok: BaseVideoConfig contract; extra_body merges into it + dropped_keys: Final = _DROP_FROM_CREATE_BODY | _additional_drop_keys(video_create_optional_params) + for key, value in video_create_optional_params.items(): + if value is None or key in dropped_keys: + continue + if key == "seconds": + mapped_params["duration"] = _duration_param(value, model) + elif key == "size": + mapped_params.setdefault("ratio", _ratio_from_size(value, model)) + elif key == "parameters": + mapped_params.update(_parameters_fields(value, model)) + else: + mapped_params[key] = value + unsupported: Final = sorted(key for key in mapped_params if key not in _CREATE_REQUEST_PARAMS) + if unsupported and not drop_params: + raise UnsupportedParamsError( + message=( + f"MiniMax video generation does not support {', '.join(map(repr, unsupported))}. " + "Set litellm.drop_params=True to drop it, or remove it from the request." + ), + model=model, + llm_provider="minimax", + ) + return {key: value for key, value in mapped_params.items() if key in _CREATE_REQUEST_PARAMS} + + def validate_environment( + self, + headers: dict[str, str], # mutable-ok: BaseVideoConfig contract; handler expects a mutable headers dict + model: str, + api_key: str | None = None, + litellm_params: GenericLiteLLMParams | None = None, + ) -> dict[str, str]: # mutable-ok: BaseVideoConfig contract + resolved_api_key: Final = ( + api_key + or (litellm_params.api_key if litellm_params is not None and litellm_params.api_key else None) + or get_secret_str("MINIMAX_API_KEY") + or litellm.api_key + ) + + if resolved_api_key is None: + raise ValueError( + "MiniMax API key is required. Set MINIMAX_API_KEY environment variable or pass api_key parameter." + ) + + auth_headers: Final[dict[str, str]] = { # mutable-ok: httpx request headers are a mutable dict + "Authorization": f"Bearer {resolved_api_key}", + "Content-Type": "application/json", + } + headers.update(auth_headers) + return headers + + def get_complete_url( + self, + model: str, + api_base: str | None, + litellm_params: dict[str, object], # mutable-ok: BaseVideoConfig contract + ) -> str: + resolved_api_base: Final = api_base or get_secret_str("MINIMAX_API_BASE") or MINIMAX_VIDEO_DEFAULT_API_BASE + return _normalized_api_base(resolved_api_base) + + def transform_video_create_request( + self, + model: str, + prompt: str, + api_base: str, + video_create_optional_request_params: dict[str, object], # mutable-ok: BaseVideoConfig contract + litellm_params: GenericLiteLLMParams, + headers: dict[str, str], # mutable-ok: BaseVideoConfig contract + ) -> tuple[dict[str, object], RequestFiles, str]: # mutable-ok: BaseVideoConfig contract + content: Final = self._content_param(video_create_optional_request_params, prompt) + if any(item.type == "video_url" for item in _content_items(content)): + raise UnsupportedParamsError( + message=( + "Reference video input is not supported through litellm: MiniMax bills its duration, which is only " + "known after the task is created and billed. Use image or audio references instead." + ), + model=model, + llm_provider="minimax", + ) + request_data: Final[dict[str, object]] = { # mutable-ok: request body dict, JSON-serialized by the handler + "model": model, + "content": content, + } + additional_drops: Final = _additional_drop_keys(litellm_params.model_dump()) + dropped_keys: Final = ( + additional_drops + if "resolution" in additional_drops + else additional_drops + | _unpriced_resolution_drop(model, video_create_optional_request_params.get("resolution"), litellm_params) + ) + for key in _CREATE_BODY_KEYS: + if key not in dropped_keys and video_create_optional_request_params.get(key) is not None: + request_data[key] = video_create_optional_request_params[key] + + request_data.setdefault("resolution", MINIMAX_VIDEO_DEFAULT_RESOLUTION) + request_data["duration"] = _duration_param( + request_data.get("duration", MINIMAX_VIDEO_DEFAULT_DURATION_SECONDS), model + ) + if "ratio" not in request_data and _is_text_only_content(content): + request_data["ratio"] = MINIMAX_TEXT_TO_VIDEO_DEFAULT_RATIO + + return request_data, (), f"{api_base}/v2/video_generation" + + @staticmethod + def _content_param(video_create_optional_request_params: Mapping[str, object], prompt: str) -> object: + """ + ``prompt`` is what guardrails scanned, so it is always the one text item MiniMax takes; a caller's + ``content`` array only contributes media, never text that would bypass that check. + """ + input_reference: Final = video_create_optional_request_params.get("input_reference") + first_frame_items: Final = () if input_reference is None else (_first_frame_content_item(input_reference),) + explicit_content: Final = video_create_optional_request_params.get("content") + if explicit_content is None: + return [{"type": "text", "text": prompt}, *first_frame_items] + try: + media: Final = _CALLER_MEDIA_ADAPTER.validate_python(explicit_content) + except ValidationError as e: + raise UnsupportedParamsError( + message=( + "content must be a list of MiniMax image_url, video_url or audio_url items; pass the text of " + f"the request as prompt. {e.error_count()} invalid item field(s)." + ), + llm_provider="minimax", + ) from e + return [ + {"type": "text", "text": prompt}, + *(item.model_dump(exclude_none=True) for item in media), + *first_frame_items, + ] + + def transform_video_create_response( + self, + model: str, + raw_response: httpx.Response, + logging_obj: "Logging", + custom_llm_provider: str | None = None, + request_data: dict[str, object] | None = None, # mutable-ok: BaseVideoConfig contract + ) -> VideoObject: + task_id: Final = _parse_task_id_response(raw_response) + request_mapping: Final[Mapping[str, object]] = request_data if request_data is not None else _EMPTY_PARAMS + duration: Final = request_mapping.get("duration") + resolution: Final = request_mapping.get("resolution") + input_image_count: Final = sum( + 1 for item in _content_items(request_mapping.get("content")) if item.type == "image_url" + ) + + video_obj: Final = VideoObject( + id=task_id, + object="video", + status="queued", + created_at=int(time.time()), + model=model, + seconds=str(duration) if duration is not None else None, + ) + if custom_llm_provider and video_obj.id: + video_obj.id = encode_video_id_with_provider(video_obj.id, custom_llm_provider, model) + + usage: Final[dict[str, object]] = {} # mutable-ok: VideoObject.usage is a mutable dict field + if isinstance(duration, (int, float)): + usage["duration_seconds"] = float(duration) + if isinstance(resolution, str): + usage["video_resolution"] = resolution.strip().lower() + if input_image_count: + usage["input_image_count"] = input_image_count + billable_input_images: Final = _billable_input_image_count(model, input_image_count) + if billable_input_images: + usage["billable_input_image_count"] = billable_input_images + video_obj.usage = usage + + return video_obj + + def transform_video_status_retrieve_request( + self, + video_id: str, + api_base: str, + litellm_params: GenericLiteLLMParams, + headers: dict[str, str], # mutable-ok: BaseVideoConfig contract + ) -> tuple[str, dict[str, object]]: # mutable-ok: BaseVideoConfig contract + original_task_id: Final = extract_original_video_id(video_id) + encoded_task_id: Final = encode_url_path_segment(original_task_id, field_name="video_id") + return f"{api_base}/v2/query/video_generation/{encoded_task_id}", _EMPTY_PARAMS + + def transform_video_status_retrieve_response( + self, + raw_response: httpx.Response, + logging_obj: "Logging", + custom_llm_provider: str | None = None, + client: HTTPHandler | None = None, + ) -> VideoObject: + task: Final = _parse_task_response(raw_response) + video_obj: Final = _video_object_from_task(task) + if custom_llm_provider and video_obj.id: + video_obj.id = encode_video_id_with_provider( + video_obj.id, custom_llm_provider, _polled_model_id(logging_obj) or task.model + ) + return video_obj + + def transform_video_content_request( + self, + video_id: str, + api_base: str, + litellm_params: GenericLiteLLMParams, + headers: dict[str, str], # mutable-ok: BaseVideoConfig contract + variant: str | None = None, + ) -> tuple[str, dict[str, object]]: # mutable-ok: BaseVideoConfig contract + if variant is not None and variant != _CONTENT_VARIANT: + raise UnsupportedParamsError( + message=f"MiniMax only serves the video itself; variant {variant!r} is not available.", + llm_provider="minimax", + ) + original_task_id: Final = extract_original_video_id(video_id) + encoded_task_id: Final = encode_url_path_segment(original_task_id, field_name="video_id") + return f"{api_base}/v2/query/video_generation/{encoded_task_id}", _EMPTY_PARAMS + + def transform_video_content_response( + self, + raw_response: httpx.Response, + logging_obj: "Logging", + client: HTTPHandler | None = None, + ) -> bytes: + task: Final = _parse_task_response(raw_response) + video_url: Final = _video_url_from_task(task) + + httpx_client: Final[HTTPHandler] = client if client is not None else _get_httpx_client() + video_response: Final = safe_get(httpx_client, video_url) + video_response.raise_for_status() + + return video_response.content + + async def async_transform_video_content_response( + self, + raw_response: httpx.Response, + logging_obj: "Logging", + client: AsyncHTTPHandler | None = None, + ) -> bytes: + task: Final = _parse_task_response(raw_response) + video_url: Final = _video_url_from_task(task) + + async_httpx_client: Final[AsyncHTTPHandler] = ( + client if client is not None else get_async_httpx_client(llm_provider=litellm.LlmProviders.MINIMAX) + ) + video_response: Final = await async_safe_get(async_httpx_client, video_url) + video_response.raise_for_status() + + return video_response.content + + def transform_video_remix_request( + self, + video_id: str, + prompt: str, + api_base: str, + litellm_params: GenericLiteLLMParams, + headers: dict[str, str], # mutable-ok: BaseVideoConfig contract + extra_body: dict[str, object] | None = None, # mutable-ok: BaseVideoConfig contract + ) -> tuple[str, dict[str, object]]: # mutable-ok: BaseVideoConfig contract + raise _remix_unsupported() + + def transform_video_remix_response( + self, + raw_response: httpx.Response, + logging_obj: "Logging", + custom_llm_provider: str | None = None, + ) -> VideoObject: + raise _remix_unsupported() + + def transform_video_list_request( + self, + api_base: str, + litellm_params: GenericLiteLLMParams, + headers: dict[str, str], # mutable-ok: BaseVideoConfig contract + after: str | None = None, + limit: int | None = None, + order: str | None = None, + extra_query: dict[str, object] | None = None, # mutable-ok: BaseVideoConfig contract + ) -> tuple[str, dict[str, object]]: # mutable-ok: BaseVideoConfig contract + if after is not None: + raise UnsupportedParamsError( + message=( + "MiniMax video list does not support cursor pagination via 'after'. " + "Pass extra_query={'page_num': N} to request a later page." + ), + llm_provider="minimax", + ) + if order is not None and order != "desc": + raise UnsupportedParamsError( + message="MiniMax video list only returns newest first; order must be 'desc' or omitted.", + llm_provider="minimax", + ) + params: Final[dict[str, object]] = {} # mutable-ok: query params dict consumed by the http handler + if limit is not None: + params["page_size"] = str(limit) + if extra_query: + params.update(extra_query) + return f"{api_base}/v2/query/video_generation", params + + def transform_video_list_response( # pyright: ignore[reportIncompatibleMethodOverride] # base declares dict[str, str] but the payload is a heterogeneous list body + self, + raw_response: httpx.Response, + logging_obj: "Logging", + custom_llm_provider: str | None = None, + ) -> dict[str, object]: # mutable-ok: OpenAI list body served as JSON by the proxy + list_payload: Final = _LIST_RESPONSE_ADAPTER.validate_python(raw_response.json()) + total: Final = list_payload.total + + data: Final[list[dict[str, object]]] = [] # mutable-ok: OpenAI list body served as JSON by the proxy + for task in list_payload.items or (): + video_obj = _video_object_from_task(task) + if custom_llm_provider and video_obj.id: + model_id = video_obj.model or _routed_model_id(logging_obj) + video_obj.id = encode_video_id_with_provider(video_obj.id, custom_llm_provider, model_id) + data.append(video_obj.model_dump()) + + list_response: Final[dict[str, object]] = { # mutable-ok: OpenAI list body served as JSON by the proxy + "object": "list", + "data": data, + "total": total if isinstance(total, int) and not isinstance(total, bool) else len(data), + "has_more": False, + } + if data: + list_response["first_id"] = data[0]["id"] + list_response["last_id"] = data[-1]["id"] + return list_response + + def transform_video_delete_request( + self, + video_id: str, + api_base: str, + litellm_params: GenericLiteLLMParams, + headers: dict[str, str], # mutable-ok: BaseVideoConfig contract + ) -> tuple[str, dict[str, object]]: # mutable-ok: BaseVideoConfig contract + original_task_id: Final = extract_original_video_id(video_id) + encoded_task_id: Final = encode_url_path_segment(original_task_id, field_name="video_id") + return f"{api_base}/v2/video_generation/{encoded_task_id}", _EMPTY_PARAMS + + def transform_video_delete_response( + self, + raw_response: httpx.Response, + logging_obj: "Logging", + ) -> VideoObject: + task_id, status = _parse_delete_response(raw_response) + return VideoObject( + id=task_id, + object="video", + status=status, + ) + + def get_error_class( + self, + error_message: str, + status_code: int, + headers: dict[str, str] | httpx.Headers, # mutable-ok: BaseVideoConfig contract + ) -> BaseLLMException: + """MiniMax answers an unknown task id with a 500, which would be retried and cool the deployment down.""" + return MinimaxVideoError( + status_code=400 if _TASK_NOT_FOUND_MESSAGE in error_message else status_code, + message=error_message, + headers=headers, + ) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f4fffa665f0..1cdad96a076 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -40273,6 +40273,58 @@ "max_input_tokens": 1000000, "max_output_tokens": 128000 }, + "minimax/MiniMax-H3": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "output_cost_per_second_2k": 0.13, + "input_cost_per_image": 0.04, + "provider_specific_entry": { + "minimax_free_input_images": 5 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, + "minimax/MiniMax-H3-Max": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "input_cost_per_image": 0.074, + "provider_specific_entry": { + "minimax_free_input_images": 2 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, "mistral.devstral-2-123b": { "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-07, diff --git a/litellm/utils.py b/litellm/utils.py index 0b9b0d79138..b74f97772fa 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -9908,6 +9908,10 @@ class ProviderConfigManager: from litellm.llms.hosted_vllm.videos import get_hosted_vllm_video_config return get_hosted_vllm_video_config(model) + elif LlmProviders.MINIMAX == provider: + from litellm.llms.minimax.videos.transformation import MinimaxVideoConfig + + return MinimaxVideoConfig() elif LlmProviders.EDENAI == provider: return litellm.EdenAIVideoConfig() return None diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f4fffa665f0..1cdad96a076 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -40273,6 +40273,58 @@ "max_input_tokens": 1000000, "max_output_tokens": 128000 }, + "minimax/MiniMax-H3": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "output_cost_per_second_2k": 0.13, + "input_cost_per_image": 0.04, + "provider_specific_entry": { + "minimax_free_input_images": 5 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, + "minimax/MiniMax-H3-Max": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "input_cost_per_image": 0.074, + "provider_specific_entry": { + "minimax_free_input_images": 2 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, "mistral.devstral-2-123b": { "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-07, diff --git a/tests/unit/llms/minimax/videos/__init__.py b/tests/unit/llms/minimax/videos/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/unit/llms/minimax/videos/test_minimax_video_transformation.py b/tests/unit/llms/minimax/videos/test_minimax_video_transformation.py new file mode 100644 index 00000000000..1405964134c --- /dev/null +++ b/tests/unit/llms/minimax/videos/test_minimax_video_transformation.py @@ -0,0 +1,1318 @@ +""" +Tests for MiniMax-H3 video generation transformation. +""" + +import base64 +import io +import json +import time +from typing import Final +from unittest.mock import Mock + +import httpx +import pytest + +import litellm +from litellm.exceptions import BadRequestError, UnsupportedParamsError +from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler +from litellm.llms.minimax.videos.transformation import ( + MINIMAX_VIDEO_DEFAULT_RESOLUTION, + MinimaxVideoConfig, + MinimaxVideoError, + _MiniMaxTask, + _TaskError, + _video_url_from_task, +) +from litellm.types.router import GenericLiteLLMParams +from litellm.types.videos.utils import ( + decode_video_id_with_provider, + encode_video_id_with_provider, +) +from litellm.videos.main import avideo_content, avideo_generation, avideo_status + +PNG_BYTES = base64.b64decode( + "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==" +) + +API_BASE = "https://api.minimax.io" + + +def _mock_response(payload: dict) -> Mock: + mock_response = Mock(spec=httpx.Response) + mock_response.json.return_value = payload + return mock_response + + +def _query_response(task: dict) -> Mock: + return _mock_response({"task": task}) + + +class TestMinimaxVideoCreateRequest: + def test_text_to_video_defaults(self): + """A prompt-only request must build the content array and apply + MiniMax's required resolution/duration/ratio when the caller omits them.""" + data, files, url = MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="A cinematic shot of a lighthouse at dusk", + api_base=API_BASE, + video_create_optional_request_params={}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert url == f"{API_BASE}/v2/video_generation" + assert files == () + assert data["model"] == "MiniMax-H3" + assert data["content"] == [{"type": "text", "text": "A cinematic shot of a lighthouse at dusk"}] + assert data["resolution"] == "768P" + assert data["duration"] == 5 + assert data["ratio"] == "16:9" + + def test_explicit_params_beat_defaults(self): + data, _, _ = MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3-Max", + prompt="prompt", + api_base=API_BASE, + video_create_optional_request_params={"resolution": "480P", "duration": 9, "ratio": "9:16"}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert data["model"] == "MiniMax-H3-Max" + assert data["resolution"] == "480P" + assert data["duration"] == 9 + assert data["ratio"] == "9:16" + + def test_map_openai_params_converts_seconds_and_size(self): + """OpenAI ``seconds``/``size`` must become MiniMax ``duration``/``ratio`` + (1280x720 reduces to 16:9), not be forwarded verbatim.""" + mapped = MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"seconds": "5", "size": "1280x720", "resolution": "2K"}, + model="MiniMax-H3", + drop_params=False, + ) + + assert mapped["duration"] == 5 + assert mapped["ratio"] == "16:9" + assert mapped["resolution"] == "2K" + assert "seconds" not in mapped + assert "size" not in mapped + + def test_map_openai_params_drops_fields_minimax_never_takes(self): + mapped = MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"user": "u1", "prompt": "p"}, + model="MiniMax-H3", + drop_params=False, + ) + + assert mapped == {} + + @pytest.mark.parametrize( + "param,value", + [ + ("characters", [{"id": "c"}]), + ("image", {"gcsUri": "gs://b/i.png"}), + ("seed", 7), + ("negative_prompt", "blurry"), + ("n", 2), + ("quality", "high"), + ], + ) + def test_unsupported_param_is_rejected_unless_drop_params(self, param, value): + """Silently dropping a param the caller asked for hides that it had no + effect; only drop_params opts into that.""" + config = MinimaxVideoConfig() + + with pytest.raises(UnsupportedParamsError, match="drop_params") as raised: + config.map_openai_params(video_create_optional_params={param: value}, model="MiniMax-H3", drop_params=False) + assert raised.value.status_code == 400 + + assert ( + config.map_openai_params(video_create_optional_params={param: value}, model="MiniMax-H3", drop_params=True) + == {} + ) + + @pytest.mark.parametrize("size", ["0x0", "1280x0", "0x720", "0:9", "16:0", "wide", "1280*720", "1280x720x3", ""]) + def test_invalid_size_is_a_bad_request(self, size): + """A zero side would divide by zero in the ratio reduction; anything + unparseable used to vanish and silently fall back to 16:9.""" + with pytest.raises(BadRequestError, match="size") as raised: + MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"size": size}, model="MiniMax-H3", drop_params=False + ) + + assert raised.value.status_code == 400 + + def test_ratio_size_passes_through_reduced(self): + mapped = MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"size": "32:18"}, model="MiniMax-H3", drop_params=False + ) + + assert mapped["ratio"] == "16:9" + + @pytest.mark.parametrize("seconds", ["0", "-5", "abc", "5.5", "", True, 0, -3, 5.0]) + def test_invalid_seconds_is_a_bad_request(self, seconds): + """An unparseable duration used to fall back to the 5 s default, so + the caller got and paid for a video of a length they never asked for.""" + with pytest.raises(BadRequestError, match="seconds") as raised: + MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"seconds": seconds}, model="MiniMax-H3", drop_params=False + ) + + assert raised.value.status_code == 400 + + @pytest.mark.parametrize("duration", ["ten", 0, -1, True]) + def test_invalid_duration_override_is_a_bad_request(self, duration): + """duration can also arrive through extra_body or parameters, past the + seconds mapping; it is what gets billed, so it is checked again.""" + with pytest.raises(BadRequestError, match="seconds"): + MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="p", + api_base=API_BASE, + video_create_optional_request_params={"duration": duration}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + def test_map_openai_params_explicit_ratio_wins_over_size(self): + mapped = MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"size": "1280x720", "ratio": "4:3"}, + model="MiniMax-H3", + drop_params=False, + ) + + assert mapped["ratio"] == "4:3" + + def test_map_openai_params_merges_parameters_block(self): + mapped = MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"parameters": {"callback_url": "https://cb.example/hook", "ratio": "1:1"}}, + model="MiniMax-H3", + drop_params=False, + ) + + assert mapped == {"callback_url": "https://cb.example/hook", "ratio": "1:1"} + + def test_non_object_parameters_is_a_bad_request(self): + with pytest.raises(BadRequestError, match="parameters") as raised: + MinimaxVideoConfig().map_openai_params( + video_create_optional_params={"parameters": "callback_url=x"}, + model="MiniMax-H3", + drop_params=False, + ) + + assert raised.value.status_code == 400 + + def test_image_reference_file_becomes_first_frame_data_uri(self): + """A file input_reference must arrive as a first_frame content item + carrying a base64 data URI, and text-only ratio defaults must not apply.""" + data, _, _ = MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="Pull focus to the people in the background", + api_base=API_BASE, + video_create_optional_request_params={"input_reference": io.BytesIO(PNG_BYTES)}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + image_item = data["content"][1] + assert image_item["type"] == "image_url" + assert image_item["role"] == "first_frame" + assert image_item["image_url"]["url"].startswith("data:image/png;base64,") + encoded = image_item["image_url"]["url"].split(",", 1)[1] + assert base64.b64decode(encoded) == PNG_BYTES + assert "ratio" not in data + + @pytest.mark.parametrize( + ("file_tuple", "expected_type"), + [ + (("frame.png", PNG_BYTES), "image/png"), + (("frame.png", io.BytesIO(PNG_BYTES), "image/png"), "image/png"), + (("frame.webp", PNG_BYTES, "image/webp", {}), "image/webp"), + ], + ) + def test_file_tuple_reference_sends_the_file_bytes(self, file_tuple, expected_type): + data, _, _ = MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="Pull focus to the people in the background", + api_base=API_BASE, + video_create_optional_request_params={"input_reference": file_tuple}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + url = data["content"][1]["image_url"]["url"] + assert url.startswith(f"data:{expected_type};base64,") + assert base64.b64decode(url.split(",", 1)[1]) == PNG_BYTES + + def test_first_frame_reference_is_kept_alongside_explicit_media(self): + media = [ + {"type": "audio_url", "audio_url": {"url": "https://cdn.example.com/ref.mp3"}, "role": "reference_audio"}, + ] + data, _, _ = MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="Character speaking", + api_base=API_BASE, + video_create_optional_request_params={ + "content": media, + "input_reference": "https://cdn.example.com/frame.png", + }, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert data["content"] == [ + {"type": "text", "text": "Character speaking"}, + *media, + {"type": "image_url", "image_url": {"url": "https://cdn.example.com/frame.png"}, "role": "first_frame"}, + ] + + def test_image_reference_url_passthrough(self): + data, _, _ = MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="Add more steam to the ramen bowl", + api_base=API_BASE, + video_create_optional_request_params={"input_reference": "https://cdn.example.com/frame.png"}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert data["content"][1] == { + "type": "image_url", + "image_url": {"url": "https://cdn.example.com/frame.png"}, + "role": "first_frame", + } + + def test_explicit_media_content_follows_the_prompt(self): + """Multimodal-reference (r2va) callers supply the media items; they pass + through after the prompt and suppress the text-only ratio default.""" + media = [ + {"type": "image_url", "image_url": {"url": "https://cdn.example.com/ref.png"}, "role": "reference_image"}, + {"type": "audio_url", "audio_url": {"url": "https://cdn.example.com/ref.mp3"}, "role": "reference_audio"}, + ] + data, _, _ = MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="Character speaking", + api_base=API_BASE, + video_create_optional_request_params={"content": media}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert data["content"] == [{"type": "text", "text": "Character speaking"}, *media] + assert "ratio" not in data + + @pytest.mark.parametrize( + "content", + [ + [{"type": "text", "text": "unscanned text"}, {"type": "image_url"}], + [{"type": "image_url", "image_url": {"url": "https://x/a.png"}, "text": "unscanned text"}], + [{"type": "image_url", "image_url": {"url": "https://x/a.png", "text": "unscanned text"}}], + [{"type": "text", "text": "unscanned text"}, "not an item"], + "unscanned text", + ], + ) + def test_malformed_content_cannot_smuggle_unscanned_text(self, content): + """A text item hidden behind a malformed sibling, or text on a media + item, must be rejected rather than let through by a lenient parse.""" + with pytest.raises(UnsupportedParamsError) as raised: + MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="a calm lake", + api_base=API_BASE, + video_create_optional_request_params={"content": content}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert raised.value.status_code == 400 + + def test_text_inside_content_is_rejected_so_guardrails_cannot_be_bypassed(self): + """Guardrails scan prompt; a text item smuggled into content would reach + MiniMax unscanned while a harmless prompt passed the check.""" + with pytest.raises(UnsupportedParamsError, match="as prompt") as raised: + MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="a calm lake", + api_base=API_BASE, + video_create_optional_request_params={"content": [{"type": "text", "text": "unscanned text"}]}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert raised.value.status_code == 400 + + @pytest.mark.parametrize( + "configured_api_base", + ( + "https://api.minimax.cn/v1/", + "https://api.minimax.cn/v1", + "https://api.minimax.cn/anthropic", + "https://api.minimax.cn/anthropic/", + "https://api.minimax.cn", + "https://api.minimax.cn/", + "https://api.minimax.cn/v2", + ), + ) + def test_any_published_surface_base_reaches_video(self, configured_api_base): + """A MiniMax key works across that host's API surfaces, so an existing + chat credential must reach video whichever base it was configured with: + MiniMax publishes .../v1 (OpenAI-compatible) and .../anthropic + (Anthropic Messages) alongside the /v2 video API, and users also + configure the bare host.""" + config = MinimaxVideoConfig() + api_base = config.get_complete_url(model="MiniMax-H3", api_base=configured_api_base, litellm_params={}) + + _, _, url = config.transform_video_create_request( + model="MiniMax-H3", + prompt="p", + api_base=api_base, + video_create_optional_request_params={}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert url == "https://api.minimax.cn/v2/video_generation" + + @pytest.mark.parametrize( + ("configured_api_base", "expected"), + ( + ("https://anthropic.example.com/v1", "https://anthropic.example.com"), + ("https://api.minimax.cn/v1/proxy", "https://api.minimax.cn/v1/proxy"), + ("https://gateway.internal/anthropic/shim", "https://gateway.internal/anthropic/shim"), + ), + ) + def test_surface_suffix_is_only_stripped_from_the_end(self, configured_api_base, expected): + """Only a trailing surface segment marks the protocol. One appearing + anywhere else is part of the address: cutting it out of the middle sends + the request to a different path than the operator configured.""" + config = MinimaxVideoConfig() + + assert config.get_complete_url(model="MiniMax-H3", api_base=configured_api_base, litellm_params={}) == expected + + def test_get_complete_url_defaults_to_international_host(self): + assert MinimaxVideoConfig().get_complete_url(model="MiniMax-H3", api_base=None, litellm_params={}) == ( + "https://api.minimax.io" + ) + + +class TestMinimaxVideoCreateResponse: + def test_task_id_is_encoded_with_provider_and_model(self): + """The create response only carries task_id; litellm must wrap it so + later status/content/remix calls can route back to minimax.""" + video_obj = MinimaxVideoConfig().transform_video_create_response( + model="MiniMax-H3", + raw_response=_mock_response({"task_id": "424010985738629"}), + logging_obj=None, + custom_llm_provider="minimax", + request_data={"model": "MiniMax-H3", "content": [], "resolution": "2K", "duration": 5, "ratio": "16:9"}, + ) + + assert video_obj.status == "queued" + assert video_obj.model == "MiniMax-H3" + assert video_obj.seconds == "5" + decoded = decode_video_id_with_provider(video_obj.id) + assert decoded["custom_llm_provider"] == "minimax" + assert decoded["model_id"] == "MiniMax-H3" + assert decoded["video_id"] == "424010985738629" + + def test_usage_carries_cost_inputs(self): + video_obj = MinimaxVideoConfig().transform_video_create_response( + model="MiniMax-H3", + raw_response=_mock_response({"task_id": "t1"}), + logging_obj=None, + custom_llm_provider="minimax", + request_data={"resolution": "768P", "duration": 4}, + ) + + assert video_obj.usage["duration_seconds"] == 4.0 + assert video_obj.usage["video_resolution"] == "768p" + assert "input_image_count" not in video_obj.usage + + def test_create_response_carries_its_creation_time(self): + before: Final = int(time.time()) + video_obj = MinimaxVideoConfig().transform_video_create_response( + model="MiniMax-H3", + raw_response=_mock_response({"task_id": "t1"}), + logging_obj=None, + custom_llm_provider="minimax", + request_data={"duration": 4}, + ) + + assert before <= video_obj.created_at <= int(time.time()) + + +class TestMinimaxVideoStatusUsage: + def test_finished_task_reports_no_token_counts(self): + """Regression: MiniMax's token counts rode into every status poll's usage, + so each free poll added ~130k tokens to the deployment's TPM and logged a + $0 billable-request warning.""" + video_obj = MinimaxVideoConfig().transform_video_status_retrieve_response( + raw_response=_query_response( + { + "id": "t1", + "model": "MiniMax-H3", + "status": "succeeded", + "content": {"url": "https://cdn.example.com/output.mp4"}, + "duration": 4, + "usage": { + "total_seconds": 4, + "output_seconds": 4, + "total_tokens": 130196, + "prompt_tokens": 12, + "completion_tokens": 130184, + }, + } + ), + logging_obj=None, + custom_llm_provider="minimax", + ) + + assert video_obj.usage["output_seconds"] == 4 + assert not any(key.endswith("tokens") for key in video_obj.usage) + + +class TestMinimaxVideoStatus: + def test_succeeded_task_mapping(self): + video_obj = MinimaxVideoConfig().transform_video_status_retrieve_response( + raw_response=_query_response( + { + "id": "424010985738629", + "model": "MiniMax-H3", + "status": "succeeded", + "created_at": 1785125529, + "updated_at": 1785125946, + "content": {"url": "https://cdn.example.com/output.mp4"}, + "resolution": "2K", + "duration": 5, + "usage": {"total_seconds": 5, "input_seconds": 0, "output_seconds": 5, "input_image_count": 1}, + "ratio": "16:9", + "task_type": "generation", + "modality": "video", + } + ), + logging_obj=None, + custom_llm_provider="minimax", + ) + + assert video_obj.status == "completed" + assert video_obj.created_at == 1785125529 + assert video_obj.completed_at == 1785125946 + assert video_obj.seconds == "5" + assert video_obj.model == "MiniMax-H3" + assert video_obj.usage["output_seconds"] == 5 + decoded = decode_video_id_with_provider(video_obj.id) + assert decoded["custom_llm_provider"] == "minimax" + assert decoded["model_id"] == "MiniMax-H3" + + def test_running_task_maps_to_in_progress_without_completion(self): + video_obj = MinimaxVideoConfig().transform_video_status_retrieve_response( + raw_response=_query_response({"id": "t1", "model": "MiniMax-H3", "status": "running", "created_at": 1}), + logging_obj=None, + custom_llm_provider="minimax", + ) + + assert video_obj.status == "in_progress" + assert video_obj.completed_at is None + assert video_obj.usage is None + + def test_failed_task_maps_error(self): + video_obj = MinimaxVideoConfig().transform_video_status_retrieve_response( + raw_response=_query_response( + { + "id": "t1", + "status": "failed", + "error": {"code": "1026", "message": "video description contains sensitive content"}, + "created_at": 1, + } + ), + logging_obj=None, + custom_llm_provider="minimax", + ) + + assert video_obj.status == "failed" + assert video_obj.error == {"code": "1026", "message": "video description contains sensitive content"} + + def test_request_decodes_task_id_from_wrapped_video_id(self): + encoded_video_id = encode_video_id_with_provider("424010985738629", "minimax", "MiniMax-H3") + url, data = MinimaxVideoConfig().transform_video_status_retrieve_request( + video_id=encoded_video_id, + api_base=API_BASE, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert url == f"{API_BASE}/v2/query/video_generation/424010985738629" + assert data == {} + + def test_content_request_hits_query_endpoint(self): + encoded_video_id = encode_video_id_with_provider("424010985738629", "minimax", "MiniMax-H3") + url, data = MinimaxVideoConfig().transform_video_content_request( + video_id=encoded_video_id, + api_base=API_BASE, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert url == f"{API_BASE}/v2/query/video_generation/424010985738629" + + def test_video_url_from_task_pending_and_failed_are_client_errors(self): + """A not-ready or failed task is the caller's state, so it must be a + 4xx; a bare ValueError surfaced as a 500 that the router retried.""" + with pytest.raises(MinimaxVideoError, match="still processing") as pending: + _video_url_from_task(_MiniMaxTask(id="t1", status="running")) + with pytest.raises(MinimaxVideoError, match="sensitive content") as failed: + _video_url_from_task(_MiniMaxTask(id="t1", status="failed", error=_TaskError(message="sensitive content"))) + + assert pending.value.status_code == 400 + assert failed.value.status_code == 400 + + def test_not_ready_message_survives_the_handler_error_path(self): + """The video handlers rebuild provider errors from response.text, so + the message must ride on the response or it reaches the caller empty.""" + from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler + + with pytest.raises(MinimaxVideoError) as pending: + _video_url_from_task(_MiniMaxTask(id="t1", status="queued")) + with pytest.raises(MinimaxVideoError) as rebuilt: + BaseLLMHTTPHandler()._handle_error(e=pending.value, provider_config=MinimaxVideoConfig()) + + assert rebuilt.value.status_code == 400 + assert "still processing" in rebuilt.value.message + + def test_unknown_status_fails_loud_instead_of_reporting_queued(self): + """Defaulting an unmapped status to queued would have callers poll a + task that will never progress.""" + with pytest.raises(MinimaxVideoError, match="expired") as raised: + MinimaxVideoConfig().transform_video_status_retrieve_response( + raw_response=_query_response({"id": "t1", "status": "expired"}), + logging_obj=None, + custom_llm_provider="minimax", + ) + + assert raised.value.status_code == 502 + + @pytest.mark.parametrize( + "payload", + [{}, {"task_id": ""}, {"task_id": None}, {"base_resp": {"status_code": 1004, "status_msg": "auth failed"}}], + ) + def test_create_without_a_task_id_fails_closed(self, payload): + """Without a task id there is nothing to poll or download, so a + queued object with an empty id must not be returned (or billed).""" + with pytest.raises(MinimaxVideoError) as raised: + MinimaxVideoConfig().transform_video_create_response( + model="MiniMax-H3", + raw_response=_mock_response(payload), + logging_obj=None, + custom_llm_provider="minimax", + request_data={"resolution": "768P", "duration": 5}, + ) + + assert raised.value.status_code == 502 + + @pytest.mark.parametrize("payload", [{}, {"task": None}, {"task": {"status": "running"}}, {"task": {"id": ""}}]) + def test_status_without_a_task_fails_closed(self, payload): + with pytest.raises(MinimaxVideoError) as raised: + MinimaxVideoConfig().transform_video_status_retrieve_response( + raw_response=_query_response(payload["task"]) if "task" in payload else _mock_response(payload), + logging_obj=None, + custom_llm_provider="minimax", + ) + + assert raised.value.status_code == 502 + + def test_delete_without_a_task_id_fails_closed(self): + with pytest.raises(MinimaxVideoError): + MinimaxVideoConfig().transform_video_delete_response( + raw_response=_mock_response({"status": "cancelled"}), + logging_obj=None, + ) + + +class TestMinimaxVideoContentDownload: + """The download URL comes out of MiniMax's response, so it is fetched + through safe_get like any other URL litellm did not choose itself.""" + + @pytest.mark.parametrize("url", ["http://169.254.169.254/latest/meta-data/", "http://127.0.0.1:8080/x.mp4"]) + def test_sync_download_refuses_internal_addresses(self, url): + from litellm.litellm_core_utils.url_utils import SSRFError + + with pytest.raises(SSRFError): + MinimaxVideoConfig().transform_video_content_response( + raw_response=_query_response({"id": "t1", "status": "succeeded", "content": {"url": url}}), + logging_obj=None, + ) + + @pytest.mark.asyncio + async def test_async_download_refuses_internal_addresses(self): + from litellm.litellm_core_utils.url_utils import SSRFError + + with pytest.raises(SSRFError): + await MinimaxVideoConfig().async_transform_video_content_response( + raw_response=_query_response( + {"id": "t1", "status": "succeeded", "content": {"url": "http://169.254.169.254/x.mp4"}} + ), + logging_obj=None, + ) + + def test_sync_download_returns_the_bytes_from_the_task_url(self, monkeypatch): + from litellm.llms.minimax.videos import transformation + + client = Mock() + client.get.return_value = Mock(content=b"mp4-bytes", raise_for_status=Mock()) + monkeypatch.setattr(litellm, "user_url_validation", False) + monkeypatch.setattr(transformation, "_get_httpx_client", lambda *args, **kwargs: client) + + content = MinimaxVideoConfig().transform_video_content_response( + raw_response=_query_response( + {"id": "t1", "status": "succeeded", "content": {"url": "https://cdn.example.com/v.mp4"}} + ), + logging_obj=None, + ) + + assert content == b"mp4-bytes" + assert client.get.call_args.args[0] == "https://cdn.example.com/v.mp4" + + @pytest.mark.asyncio + async def test_async_download_returns_the_bytes_from_the_task_url(self, monkeypatch): + from litellm.llms.minimax.videos import transformation + + response = Mock(content=b"mp4-bytes", raise_for_status=Mock()) + + async def get(url, **kwargs): + return response + + client = Mock() + client.get = get + monkeypatch.setattr(litellm, "user_url_validation", False) + monkeypatch.setattr(transformation, "get_async_httpx_client", lambda **kwargs: client) + + content = await MinimaxVideoConfig().async_transform_video_content_response( + raw_response=_query_response( + {"id": "t1", "status": "succeeded", "content": {"url": "https://cdn.example.com/v.mp4"}} + ), + logging_obj=None, + ) + + assert content == b"mp4-bytes" + + def test_download_of_a_finished_task_without_a_url_is_a_client_error(self): + with pytest.raises(MinimaxVideoError, match="no downloadable content") as raised: + MinimaxVideoConfig().transform_video_content_response( + raw_response=_query_response({"id": "t1", "status": "succeeded"}), + logging_obj=None, + ) + + assert raised.value.status_code == 400 + + @pytest.mark.asyncio + async def test_downloading_a_running_task_is_a_client_error_not_a_server_error(self): + """Regression: the caller-visible status used to be a synthesized 500, so the + proxy retried the same poll twice and counted the caller's own early download + against the model's error rate. A 404 is no better, since the router cools a + deployment down on 404.""" + encoded = encode_video_id_with_provider("424010985738629", "minimax", "MiniMax-H3") + + def respond(request: httpx.Request) -> httpx.Response: + return httpx.Response(200, json={"task": {"id": "424010985738629", "status": "running"}}) + + async with httpx.AsyncClient(transport=httpx.MockTransport(respond)) as http_client: + handler: Final = AsyncHTTPHandler() + await handler.close() + handler.client = http_client + with pytest.raises(litellm.BadRequestError, match="still processing") as raised: + await avideo_content(video_id=encoded, api_key="sk-test", api_base=API_BASE, client=handler) + + assert raised.value.status_code == 400 + + @pytest.mark.asyncio + async def test_unknown_task_id_is_a_client_error_not_a_retried_server_error(self): + """MiniMax answers an id it does not know with HTTP 500, which the router + retried and counted against the deployment.""" + encoded = encode_video_id_with_provider("123456789", "minimax", "MiniMax-H3") + + def respond(request: httpx.Request) -> httpx.Response: + return httpx.Response( + 500, + json={ + "type": "error", + "error": {"type": "server_error", "message": "record not found (1000)", "http_code": "500"}, + }, + ) + + async with httpx.AsyncClient(transport=httpx.MockTransport(respond)) as http_client: + handler: Final = AsyncHTTPHandler() + await handler.close() + handler.client = http_client + with pytest.raises(litellm.BadRequestError, match="record not found") as raised: + await avideo_status(video_id=encoded, api_key="sk-test", api_base=API_BASE, client=handler) + + assert raised.value.status_code == 400 + + @pytest.mark.asyncio + async def test_status_returns_the_polled_id_when_minimax_omits_the_model(self): + encoded = encode_video_id_with_provider("123456789", "minimax", "MiniMax-H3") + + def respond(request: httpx.Request) -> httpx.Response: + return httpx.Response( + 200, + json={"task": {"id": "123456789", "status": "failed", "error": {"code": "1026", "message": "x"}}}, + ) + + async with httpx.AsyncClient(transport=httpx.MockTransport(respond)) as http_client: + handler: Final = AsyncHTTPHandler() + await handler.close() + handler.client = http_client + video_obj = await avideo_status(video_id=encoded, api_key="sk-test", api_base=API_BASE, client=handler) + + assert video_obj.id == encoded + + @pytest.mark.asyncio + async def test_a_variant_minimax_cannot_serve_is_a_client_error_instead_of_the_full_video(self): + encoded = encode_video_id_with_provider("123456789", "minimax", "MiniMax-H3") + sent: Final[list[httpx.Request]] = [] + + def respond(request: httpx.Request) -> httpx.Response: + sent.append(request) + return httpx.Response(200, json={"task": {"id": "123456789", "status": "succeeded"}}) + + async with httpx.AsyncClient(transport=httpx.MockTransport(respond)) as http_client: + handler: Final = AsyncHTTPHandler() + await handler.close() + handler.client = http_client + with pytest.raises(litellm.BadRequestError, match="thumbnail") as raised: + await avideo_content( + video_id=encoded, variant="thumbnail", api_key="sk-test", api_base=API_BASE, client=handler + ) + + assert raised.value.status_code == 400 + assert sent == [] + + +class TestMinimaxVideoList: + def test_request_maps_limit_and_extra_query(self): + url, params = MinimaxVideoConfig().transform_video_list_request( + api_base=API_BASE, + litellm_params=GenericLiteLLMParams(), + headers={}, + limit=4, + extra_query={"filter.status": "succeeded", "page_num": 2}, + ) + + assert url == f"{API_BASE}/v2/query/video_generation" + assert params == {"page_size": "4", "filter.status": "succeeded", "page_num": 2} + + def test_after_cursor_is_rejected_instead_of_repeating_the_first_page(self): + with pytest.raises(UnsupportedParamsError, match="page_num") as raised: + MinimaxVideoConfig().transform_video_list_request( + api_base=API_BASE, + litellm_params=GenericLiteLLMParams(), + headers={}, + after="video_abc", + ) + + assert raised.value.status_code == 400 + + def test_ascending_order_is_rejected(self): + with pytest.raises(UnsupportedParamsError, match="newest first") as raised: + MinimaxVideoConfig().transform_video_list_request( + api_base=API_BASE, + litellm_params=GenericLiteLLMParams(), + headers={}, + order="asc", + ) + + assert raised.value.status_code == 400 + + def test_descending_order_is_what_minimax_already_returns(self): + _, params = MinimaxVideoConfig().transform_video_list_request( + api_base=API_BASE, + litellm_params=GenericLiteLLMParams(), + headers={}, + order="desc", + ) + + assert params == {} + + def test_response_adopts_openai_list_shape_with_encoded_ids(self): + response = MinimaxVideoConfig().transform_video_list_response( + raw_response=_mock_response( + { + "items": [ + {"id": "424635601932571", "model": "MiniMax-H3", "status": "succeeded", "duration": 5}, + {"id": "424635601932588", "model": "MiniMax-H3", "status": "running"}, + ], + "total": 476, + } + ), + logging_obj=None, + custom_llm_provider="minimax", + ) + + assert response["object"] == "list" + assert response["total"] == 476 + assert response["has_more"] is False, "MiniMax has no cursor, so an OpenAI client paging by after loops" + assert [item["status"] for item in response["data"]] == ["completed", "in_progress"] + first_decoded = decode_video_id_with_provider(response["first_id"]) + last_decoded = decode_video_id_with_provider(response["last_id"]) + assert first_decoded["video_id"] == "424635601932571" + assert last_decoded["video_id"] == "424635601932588" + assert first_decoded["custom_llm_provider"] == "minimax" + + def test_a_listed_task_without_a_model_carries_the_routed_group(self): + """The caller polls the ids a list hands back, and the proxy resolves a poll by the model in the id, so a + task MiniMax leaves `model` off would come back as an id that no longer resolves.""" + response = MinimaxVideoConfig().transform_video_list_response( + raw_response=_mock_response( + { + "items": [ + {"id": "424635601932571", "model": "MiniMax-H3", "status": "succeeded"}, + {"id": "424635601932588", "status": "running"}, + ], + "total": 2, + } + ), + logging_obj=Mock(litellm_params={"litellm_metadata": {"model_group": "minimax-video"}}), + custom_llm_provider="minimax", + ) + + with_model = decode_video_id_with_provider(response["data"][0]["id"]) + without_model = decode_video_id_with_provider(response["data"][1]["id"]) + assert with_model["model_id"] == "MiniMax-H3" + assert without_model["model_id"] == "minimax-video" + assert without_model["video_id"] == "424635601932588" + + +class TestMinimaxVideoRemix: + @pytest.mark.asyncio + async def test_remix_is_a_client_error_instead_of_a_retryable_500(self, monkeypatch: pytest.MonkeyPatch): + """MiniMax regeneration only upscales to 2K and ignores any prompt, so + remix is refused with a 400 the router does not retry.""" + monkeypatch.setenv("MINIMAX_API_KEY", "test-key") + encoded_video_id: Final = encode_video_id_with_provider("424010985738629", "minimax", "MiniMax-H3") + + with pytest.raises(litellm.BadRequestError, match="remix is not supported by MiniMax") as raised: + await litellm.avideo_remix( + video_id=encoded_video_id, + prompt="a different ending", + custom_llm_provider="minimax", + ) + + assert raised.value.status_code == 400 + + def test_remix_response_is_rejected(self): + with pytest.raises(UnsupportedParamsError, match="remix is not supported by MiniMax") as raised: + MinimaxVideoConfig().transform_video_remix_response( + raw_response=_mock_response({}), + logging_obj=None, + ) + + assert raised.value.status_code == 400 + + +class TestMinimaxVideoDelete: + def test_delete_request_and_cancelled_response(self): + encoded_video_id = encode_video_id_with_provider("424010985738629", "minimax", "MiniMax-H3") + url, data = MinimaxVideoConfig().transform_video_delete_request( + video_id=encoded_video_id, + api_base=API_BASE, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert url == f"{API_BASE}/v2/video_generation/424010985738629" + assert data == {} + + video_obj = MinimaxVideoConfig().transform_video_delete_response( + raw_response=_mock_response({"task_id": "424010985738629", "action": "cancelled", "status": "cancelled"}), + logging_obj=None, + ) + assert video_obj.status == "cancelled" + assert video_obj.id == "424010985738629" + + +class TestMinimaxVideoEnvironment: + def test_explicit_api_key_wins_over_litellm_params(self): + headers = MinimaxVideoConfig().validate_environment( + headers={}, + model="MiniMax-H3", + api_key="explicit-key", + litellm_params=GenericLiteLLMParams(api_key="deployment-key"), + ) + + assert headers["Authorization"] == "Bearer explicit-key" + assert headers["Content-Type"] == "application/json" + + def test_litellm_params_key_used_when_no_explicit_key(self): + headers = MinimaxVideoConfig().validate_environment( + headers={}, + model="MiniMax-H3", + litellm_params=GenericLiteLLMParams(api_key="deployment-key"), + ) + + assert headers["Authorization"] == "Bearer deployment-key" + + def test_missing_api_key_raises(self, monkeypatch): + monkeypatch.delenv("MINIMAX_API_KEY", raising=False) + monkeypatch.setattr("litellm.api_key", None) + + with pytest.raises(ValueError, match="MINIMAX_API_KEY"): + MinimaxVideoConfig().validate_environment( + headers={}, + model="MiniMax-H3", + litellm_params=GenericLiteLLMParams(), + ) + + def test_env_var_api_key_used(self, monkeypatch): + monkeypatch.setenv("MINIMAX_API_KEY", "env-key") + monkeypatch.setattr("litellm.api_key", None) + + headers = MinimaxVideoConfig().validate_environment( + headers={}, + model="MiniMax-H3", + litellm_params=GenericLiteLLMParams(), + ) + + assert headers["Authorization"] == "Bearer env-key" + + def test_minimax_env_key_wins_over_the_global_litellm_key(self, monkeypatch): + monkeypatch.setenv("MINIMAX_API_KEY", "env-key") + monkeypatch.setattr("litellm.api_key", "global-key") + + headers = MinimaxVideoConfig().validate_environment( + headers={}, + model="MiniMax-H3", + litellm_params=GenericLiteLLMParams(), + ) + + assert headers["Authorization"] == "Bearer env-key" + + def test_global_litellm_key_is_the_last_fallback(self, monkeypatch): + monkeypatch.delenv("MINIMAX_API_KEY", raising=False) + monkeypatch.setattr("litellm.api_key", "global-key") + + headers = MinimaxVideoConfig().validate_environment( + headers={}, + model="MiniMax-H3", + litellm_params=GenericLiteLLMParams(), + ) + + assert headers["Authorization"] == "Bearer global-key" + + +class TestMinimaxVideoEndToEndRequest: + """ + Drive the real avideo_generation() entrypoint rather than the transform. + + map_openai_params runs first and only its output reaches + transform_video_create_request, so a param the mapper drops never makes + it into the body even though the transform alone handles it. + """ + + @staticmethod + async def _wire_body(**kwargs) -> dict: + sent: Final[list[httpx.Request]] = [] + + def respond(request: httpx.Request) -> httpx.Response: + sent.append(request) + return httpx.Response(200, json={"task_id": "t1"}) + + async with httpx.AsyncClient(transport=httpx.MockTransport(respond)) as http_client: + handler: Final = AsyncHTTPHandler() + await handler.close() + handler.client = http_client + await avideo_generation(api_key="sk-test", api_base=API_BASE, client=handler, **kwargs) + + (request,) = sent + return json.loads(request.content) + + @pytest.mark.asyncio + async def test_input_reference_survives_param_mapping_into_the_body(self): + """Regression: map_openai_params dropped input_reference, so an + image-to-video call silently degraded to text-to-video.""" + body = await self._wire_body( + model="minimax/MiniMax-H3", + prompt="make it move", + input_reference="https://cdn.example/first.png", + ) + + assert body["content"] == [ + {"type": "text", "text": "make it move"}, + {"type": "image_url", "image_url": {"url": "https://cdn.example/first.png"}, "role": "first_frame"}, + ] + assert "input_reference" not in body + assert "ratio" not in body + + @pytest.mark.asyncio + async def test_file_input_reference_reaches_the_body_as_a_data_uri(self): + body = await self._wire_body( + model="minimax/MiniMax-H3", + prompt="make it move", + input_reference=io.BytesIO(PNG_BYTES), + ) + + image_item = body["content"][1] + assert image_item["role"] == "first_frame" + assert image_item["image_url"]["url"] == f"data:image/png;base64,{base64.b64encode(PNG_BYTES).decode()}" + + @pytest.mark.asyncio + async def test_deployment_drop_settings_are_honored_and_never_sent(self): + body = await self._wire_body( + model="minimax/MiniMax-H3", + prompt="p", + ratio="1:1", + aigc_watermark=True, + drop_params=False, + additional_drop_params=["aigc_watermark"], + ) + + assert body["ratio"] == "1:1" + assert "aigc_watermark" not in body + assert "drop_params" not in body + assert "additional_drop_params" not in body + + @pytest.mark.asyncio + async def test_a_dropped_field_is_not_sent_when_it_arrives_inside_parameters(self): + body = await self._wire_body( + model="minimax/MiniMax-H3", + prompt="p", + parameters={"aigc_watermark": True, "ratio": "1:1"}, + additional_drop_params=["aigc_watermark"], + ) + + assert body["ratio"] == "1:1" + assert "aigc_watermark" not in body + + @pytest.mark.asyncio + async def test_a_dropped_field_is_not_sent_when_it_arrives_in_extra_body(self): + body = await self._wire_body( + model="minimax/MiniMax-H3", + prompt="p", + extra_body={"aigc_watermark": True, "resolution": "2K", "ratio": "1:1"}, + additional_drop_params=["aigc_watermark", "resolution"], + ) + + assert body["ratio"] == "1:1" + assert "aigc_watermark" not in body + assert body["resolution"] == MINIMAX_VIDEO_DEFAULT_RESOLUTION + + @pytest.mark.asyncio + async def test_a_param_minimax_cannot_honor_is_rejected_before_the_billed_call(self): + """Regression: seed reached the mapper, never the body, and the video was + still created and billed as if the caller had not asked for it.""" + sent: Final[list[httpx.Request]] = [] + + def respond(request: httpx.Request) -> httpx.Response: + sent.append(request) + return httpx.Response(200, json={"task_id": "t1"}) + + async with httpx.AsyncClient(transport=httpx.MockTransport(respond)) as http_client: + handler: Final = AsyncHTTPHandler() + await handler.close() + handler.client = http_client + with pytest.raises(litellm.BadRequestError, match="seed") as raised: + await avideo_generation( + model="minimax/MiniMax-H3", prompt="p", seed=7, api_key="sk-test", api_base=API_BASE, client=handler + ) + + assert raised.value.status_code == 400 + assert sent == [] + + +@pytest.mark.usefixtures("local_model_cost_map") +class TestMinimaxVideoPricing: + @pytest.mark.parametrize( + "model,resolutions", + [("MiniMax-H3", ("768p", "2k")), ("MiniMax-H3-Max", ("480p", "768p"))], + ) + def test_every_supported_tier_bills_its_own_rate(self, model, resolutions): + """A tier with no rate of its own falls back to the base rate, so a 2K + video would silently bill at the 768P price.""" + from litellm import get_model_info + from litellm.llms.openai.cost_calculation import video_generation_cost + + info = get_model_info(model=model, custom_llm_provider="minimax") + + for resolution in resolutions: + tier_rate = info[f"output_cost_per_second_{resolution}"] + assert tier_rate > 0 + cost = video_generation_cost( + model=model, duration_seconds=5.0, custom_llm_provider="minimax", video_resolution=resolution + ) + assert cost == pytest.approx(tier_rate * 5.0) + + @pytest.mark.asyncio + @pytest.mark.parametrize( + "resolution_kwargs", + [{"resolution": "480P"}, {"parameters": {"resolution": "480P"}}, {"extra_body": {"resolution": "480p"}}], + ) + async def test_a_resolution_without_a_price_is_rejected_before_the_billed_call(self, resolution_kwargs): + sent: Final[list[httpx.Request]] = [] + + def respond(request: httpx.Request) -> httpx.Response: + sent.append(request) + return httpx.Response(200, json={"task_id": "t1"}) + + async with httpx.AsyncClient(transport=httpx.MockTransport(respond)) as http_client: + handler: Final = AsyncHTTPHandler() + await handler.close() + handler.client = http_client + with pytest.raises(litellm.BadRequestError, match="480") as raised: + await avideo_generation( + model="minimax/MiniMax-H3", + prompt="p", + api_key="sk-test", + api_base=API_BASE, + client=handler, + **resolution_kwargs, + ) + + assert raised.value.status_code == 400 + assert sent == [] + + @pytest.mark.asyncio + async def test_drop_params_sends_the_default_resolution_instead_of_one_without_a_price(self): + body = await TestMinimaxVideoEndToEndRequest._wire_body( + model="minimax/MiniMax-H3", prompt="p", resolution="480P", drop_params=True + ) + + assert body["resolution"] == MINIMAX_VIDEO_DEFAULT_RESOLUTION + + @pytest.mark.asyncio + @pytest.mark.parametrize( + "resolution_kwargs", + [{"resolution": "480P"}, {"parameters": {"resolution": "480P"}}, {"extra_body": {"resolution": "480p"}}], + ) + async def test_a_deployment_dropping_resolution_sends_the_default_instead_of_rejecting_one_without_a_price( + self, resolution_kwargs + ): + body = await TestMinimaxVideoEndToEndRequest._wire_body( + model="minimax/MiniMax-H3", prompt="p", additional_drop_params=["resolution"], **resolution_kwargs + ) + + assert body["resolution"] == MINIMAX_VIDEO_DEFAULT_RESOLUTION + + @pytest.mark.asyncio + @pytest.mark.parametrize("model,resolution", [("MiniMax-H3", "2K"), ("MiniMax-H3-Max", "480P")]) + async def test_a_priced_resolution_is_sent_as_asked(self, model, resolution): + body = await TestMinimaxVideoEndToEndRequest._wire_body( + model=f"minimax/{model}", prompt="p", resolution=resolution + ) + + assert body["resolution"] == resolution + + def test_higher_resolution_never_bills_less(self): + from litellm import get_model_info + + h3 = get_model_info(model="MiniMax-H3", custom_llm_provider="minimax") + h3_max = get_model_info(model="MiniMax-H3-Max", custom_llm_provider="minimax") + + assert h3["output_cost_per_second_2k"] > h3["output_cost_per_second_768p"] + assert h3_max["output_cost_per_second_768p"] > h3_max["output_cost_per_second_480p"] + + +@pytest.mark.usefixtures("local_model_cost_map") +class TestMinimaxVideoInputBilling: + @staticmethod + def _create_cost(model: str, image_count: int, router_model_id: str | None = None) -> float: + import litellm + + content = [{"type": "text", "text": "p"}] + [ + {"type": "image_url", "image_url": {"url": f"https://x/{i}.png"}, "role": "reference_image"} + for i in range(image_count) + ] + video_obj = MinimaxVideoConfig().transform_video_create_response( + model=model, + raw_response=_mock_response({"task_id": "t1"}), + logging_obj=None, + custom_llm_provider="minimax", + request_data={"model": model, "content": content, "duration": 5, "resolution": "768P"}, + ) + return litellm.completion_cost( + completion_response=video_obj, + model=f"minimax/{model}", + call_type="create_video", + custom_llm_provider="minimax", + custom_pricing=router_model_id is not None, + router_model_id=router_model_id, + ) + + @pytest.mark.parametrize("model", ["MiniMax-H3", "MiniMax-H3-Max"]) + def test_custom_deployment_pricing_bills_images_like_the_cost_map(self, model, monkeypatch): + """Regression: a deployment with its own prices billed only output seconds, + dropping the per-image charge even when it set input_cost_per_image.""" + from litellm import get_model_info + + info = get_model_info(model=model, custom_llm_provider="minimax") + deployment_id = f"deployment-{model}" + monkeypatch.setitem( + litellm.model_cost, + deployment_id, + { + "litellm_provider": "minimax", + "mode": "video_generation", + "output_cost_per_second": info["output_cost_per_second_768p"], + "input_cost_per_image": info["input_cost_per_image"], + }, + ) + image_count = info["provider_specific_entry"]["minimax_free_input_images"] + 2 + + custom_cost = self._create_cost(model, image_count, router_model_id=deployment_id) + + assert custom_cost == pytest.approx(self._create_cost(model, image_count)) + assert custom_cost > self._create_cost(model, 0, router_model_id=deployment_id) + + @pytest.mark.parametrize("model", ["MiniMax-H3", "MiniMax-H3-Max"]) + def test_a_deployment_pricing_only_seconds_bills_images_at_the_cost_map_rate(self, model, monkeypatch): + from litellm import get_model_info + + info = get_model_info(model=model, custom_llm_provider="minimax") + deployment_id = f"seconds-only-{model}" + seconds_rate = info["output_cost_per_second_768p"] * 2 + monkeypatch.setitem( + litellm.model_cost, + deployment_id, + {"litellm_provider": "minimax", "mode": "video_generation", "output_cost_per_second": seconds_rate}, + ) + extra_images = 2 + image_count = info["provider_specific_entry"]["minimax_free_input_images"] + extra_images + + custom_cost = self._create_cost(model, image_count, router_model_id=deployment_id) + + assert custom_cost == pytest.approx(seconds_rate * 5 + extra_images * info["input_cost_per_image"]) + + @pytest.mark.parametrize("model", ["MiniMax-H3", "MiniMax-H3-Max"]) + def test_images_beyond_the_free_allowance_are_billed_per_image(self, model): + """MiniMax charges for input images past a per-model free allowance; + billing only output seconds under-recorded those requests.""" + from litellm import get_model_info + + info = get_model_info(model=model, custom_llm_provider="minimax") + free_images = info["provider_specific_entry"]["minimax_free_input_images"] + image_rate = info["input_cost_per_image"] + output_only = self._create_cost(model, image_count=0) + + assert self._create_cost(model, image_count=free_images) == pytest.approx(output_only) + assert self._create_cost(model, image_count=free_images + 3) == pytest.approx(output_only + 3 * image_rate) + assert output_only == pytest.approx(info["output_cost_per_second_768p"] * 5) + + @pytest.mark.parametrize( + "content", + [ + [{"type": "video_url", "video_url": {"url": "https://x/ref.mp4"}, "role": "reference_video"}], + ], + ) + def test_reference_video_is_rejected_because_its_length_cannot_be_billed(self, content): + """MiniMax bills reference-video seconds, which are only reported after + the create call that litellm bills.""" + with pytest.raises(UnsupportedParamsError, match="Reference video") as raised: + MinimaxVideoConfig().transform_video_create_request( + model="MiniMax-H3", + prompt="p", + api_base=API_BASE, + video_create_optional_request_params={"content": content}, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert raised.value.status_code == 400