mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-28 06:23:07 +00:00
chore(cost-map): accept the mirrored map's new keys in the schema
Adds search_free_requests, token_count_model (with litellm_provider enum bedrock/bedrock_mantle), token_count_framing and token_count_tokenizer to ci_cd/generate_model_prices_schema.py using main's definitions, and regenerates model_prices_and_context_window.schema.json. Schema keys are CI-only; the line already fetches main's map at runtime.
This commit is contained in:
Mrinal Chanshetty
parent
105a342e77
commit
dc314e7f6a
2 changed files with 286 additions and 39 deletions
|
|
@ -19,6 +19,7 @@ NONNEG_NUMBER: JsonSchema = {"type": "number", "minimum": 0}
|
|||
NONNEG_INTEGER: JsonSchema = {"type": "integer", "minimum": 0}
|
||||
BOOLEAN: JsonSchema = {"type": "boolean"}
|
||||
STRING: JsonSchema = {"type": "string"}
|
||||
NON_BLANK_STRING: Final[JsonSchema] = {"type": "string", "pattern": r"\S"}
|
||||
TIME_WINDOW: Final[JsonSchema] = {"type": "string", "pattern": r"^([01]\d|2[0-3]):[0-5]\d-([01]\d|2[0-3]):[0-5]\d$"}
|
||||
WEEKDAY_PATTERN: Final = (
|
||||
r"(?i)^(mon|monday|tue|tues|tuesday|wed|wednesday|thu|thur|thurs|thursday|fri|friday|sat|saturday|sun|sunday)$"
|
||||
|
|
@ -61,6 +62,28 @@ OFF_PEAK_WINDOW: Final[JsonSchema] = {
|
|||
}
|
||||
|
||||
OBJECT_KEYS: dict[str, JsonSchema] = {
|
||||
"search_free_requests": {
|
||||
"type": "object",
|
||||
"description": "Free Google Search grounding requests per period, shared across models in the same shared_group.",
|
||||
"required": ["count", "period", "shared_group"],
|
||||
"additionalProperties": False,
|
||||
"properties": {
|
||||
"count": {"type": "integer", "minimum": 0},
|
||||
"period": {"type": "string", "enum": ["day", "month"]},
|
||||
"shared_group": {"type": "string", "pattern": "\\S"},
|
||||
},
|
||||
},
|
||||
"token_count_model": {
|
||||
"type": "object",
|
||||
"required": ["model"],
|
||||
"additionalProperties": False,
|
||||
"properties": {
|
||||
"model": NON_BLANK_STRING,
|
||||
"region": NON_BLANK_STRING,
|
||||
"litellm_provider": {"type": "string", "enum": ["bedrock", "bedrock_mantle"]},
|
||||
},
|
||||
"description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in.",
|
||||
},
|
||||
"off_peak_pricing": {
|
||||
"type": "object",
|
||||
"description": "Rates that replace the same-named base fields while the request falls inside the stated UTC windows.",
|
||||
|
|
@ -169,6 +192,10 @@ ARRAY_KEYS: dict[str, JsonSchema] = {
|
|||
}
|
||||
|
||||
INTEGER_KEYS: dict[str, JsonSchema] = {
|
||||
"token_count_framing": {
|
||||
**NONNEG_INTEGER,
|
||||
"description": "Tokens added once per request to a local count estimate, for the provider's chat framing.",
|
||||
},
|
||||
"max_tokens": {
|
||||
**NONNEG_INTEGER,
|
||||
"description": "Legacy field: max output tokens if the provider specifies it, else max input tokens.",
|
||||
|
|
@ -263,6 +290,11 @@ def string_key_schemas(modes: tuple) -> dict[str, JsonSchema]:
|
|||
"format": "date",
|
||||
"pattern": "^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$",
|
||||
},
|
||||
"token_count_tokenizer": {
|
||||
"type": "string",
|
||||
"description": "Local tokenizer used to count tokens for this model.",
|
||||
"enum": ["kimi_k3"],
|
||||
},
|
||||
"web_search_billing_unit": {
|
||||
"type": "string",
|
||||
"description": "Whether web search is billed per query or per prompt.",
|
||||
|
|
|
|||
|
|
@ -83,10 +83,6 @@
|
|||
"minimum": 0,
|
||||
"description": "USD per token written to the provider's prompt cache."
|
||||
},
|
||||
"cache_creation_input_token_cost_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_creation_input_token_cost_above_100k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -97,11 +93,6 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_128k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_1hr": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -122,12 +113,17 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_256k_tokens": {
|
||||
"cache_creation_input_token_cost_above_272k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_272k_tokens": {
|
||||
"cache_creation_input_token_cost_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_272k_tokens_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
|
|
@ -142,6 +138,19 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_272k_tokens_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_input_token_cost_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_creation_input_token_cost_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_creation_input_token_cost_flex": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -152,19 +161,23 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"cache_creation_input_token_cost_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_audio_token_cost": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_image_token_cost": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "USD per prompt token served from the provider's prompt cache."
|
||||
},
|
||||
"cache_read_input_token_cost_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost_above_100k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -175,12 +188,12 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_input_token_cost_above_128k_tokens": {
|
||||
"cache_read_input_token_cost_above_200k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_input_token_cost_above_200k_tokens": {
|
||||
"cache_read_input_token_cost_above_200k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
|
|
@ -190,12 +203,17 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"cache_read_input_token_cost_above_256k_tokens": {
|
||||
"cache_read_input_token_cost_above_272k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_input_token_cost_above_272k_tokens": {
|
||||
"cache_read_input_token_cost_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_input_token_cost_above_272k_tokens_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
|
|
@ -210,11 +228,28 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"cache_read_input_token_cost_above_272k_tokens_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_input_token_cost_above_512k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_input_token_cost_balanced": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost_flex": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -225,6 +260,10 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"cache_read_input_token_cost_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"citation_cost_per_token": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
|
|
@ -236,6 +275,10 @@
|
|||
"comment": {
|
||||
"type": "string"
|
||||
},
|
||||
"cost_per_second": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"default_reasoning_effort": {
|
||||
"type": "string",
|
||||
"description": "Reasoning effort the provider applies when the request omits reasoning_effort. Gates whether a non-default temperature or the top_p/logprobs sampling params are accepted, which hold only when the effort resolves to 'none'.",
|
||||
|
|
@ -254,6 +297,10 @@
|
|||
"format": "date",
|
||||
"pattern": "^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$"
|
||||
},
|
||||
"explicit_cache_read_input_token_cost": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"gemini_audio_only_live": {
|
||||
"type": "boolean"
|
||||
},
|
||||
|
|
@ -337,6 +384,10 @@
|
|||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_text_message": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -362,17 +413,27 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"input_cost_per_token_above_200k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"input_cost_per_token_above_200k_tokens_priority": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"input_cost_per_token_above_256k_tokens": {
|
||||
"input_cost_per_token_above_272k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"input_cost_per_token_above_272k_tokens": {
|
||||
"input_cost_per_token_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"input_cost_per_token_above_272k_tokens_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
|
|
@ -387,36 +448,33 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"input_cost_per_token_above_272k_tokens_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"input_cost_per_token_above_512k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"input_cost_per_token_balanced": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "USD per prompt token via the provider's batch API."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_token_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token_cache_hit": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token_flex": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -427,6 +485,10 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"input_cost_per_token_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_video_per_second": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
|
|
@ -491,6 +553,7 @@
|
|||
"completion",
|
||||
"embedding",
|
||||
"evaluation",
|
||||
"extraction",
|
||||
"guardrail",
|
||||
"image_edit",
|
||||
"image_generation",
|
||||
|
|
@ -641,10 +704,42 @@
|
|||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_0.5K": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_1024": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_1536": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_1K": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_2K": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_4K": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_512": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_token": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_image_token_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_pixel": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
|
|
@ -662,6 +757,10 @@
|
|||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_second_2k": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_second_480p": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
|
|
@ -674,6 +773,10 @@
|
|||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_second_768p": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_token": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -699,17 +802,27 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"output_cost_per_token_above_200k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"output_cost_per_token_above_200k_tokens_priority": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"output_cost_per_token_above_256k_tokens": {
|
||||
"output_cost_per_token_above_272k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"output_cost_per_token_above_272k_tokens": {
|
||||
"output_cost_per_token_above_272k_tokens_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"output_cost_per_token_above_272k_tokens_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
|
|
@ -724,16 +837,29 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"output_cost_per_token_above_272k_tokens_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"output_cost_per_token_above_512k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"output_cost_per_token_balanced": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_token_batches": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"description": "USD per generated token via the provider's batch API."
|
||||
},
|
||||
"output_cost_per_token_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_token_flex": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -744,6 +870,10 @@
|
|||
"minimum": 0,
|
||||
"description": "Priority service-tier rate for the same-named base field."
|
||||
},
|
||||
"output_cost_per_token_ultrafast": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"output_cost_per_video_per_second": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
|
|
@ -825,6 +955,33 @@
|
|||
},
|
||||
"additionalProperties": false
|
||||
},
|
||||
"search_free_requests": {
|
||||
"type": "object",
|
||||
"description": "Free Google Search grounding requests per period, shared across models in the same shared_group.",
|
||||
"required": [
|
||||
"count",
|
||||
"period",
|
||||
"shared_group"
|
||||
],
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"count": {
|
||||
"type": "integer",
|
||||
"minimum": 0
|
||||
},
|
||||
"period": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"day",
|
||||
"month"
|
||||
]
|
||||
},
|
||||
"shared_group": {
|
||||
"type": "string",
|
||||
"pattern": "\\S"
|
||||
}
|
||||
}
|
||||
},
|
||||
"source": {
|
||||
"type": "string",
|
||||
"description": "URL of the provider pricing/model page this entry was taken from."
|
||||
|
|
@ -899,6 +1056,24 @@
|
|||
"supports_audio_output": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_bedrock_converse_tool_result_images": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_bedrock_native_structured_output": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_bedrock_runtime_chat_completions_inline_reasoning": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_bedrock_runtime_chat_completions_response_format": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_bedrock_runtime_chat_completions_tools_with_reasoning": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_box_questions": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_computer_use": {
|
||||
"type": "boolean"
|
||||
},
|
||||
|
|
@ -971,6 +1146,9 @@
|
|||
"supports_reasoning": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_regex_lookaround": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"supports_response_schema": {
|
||||
"type": "boolean"
|
||||
},
|
||||
|
|
@ -1064,6 +1242,43 @@
|
|||
"additionalProperties": false
|
||||
}
|
||||
},
|
||||
"token_count_framing": {
|
||||
"type": "integer",
|
||||
"minimum": 0,
|
||||
"description": "Tokens added once per request to a local count estimate, for the provider's chat framing."
|
||||
},
|
||||
"token_count_model": {
|
||||
"type": "object",
|
||||
"required": [
|
||||
"model"
|
||||
],
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"model": {
|
||||
"type": "string",
|
||||
"pattern": "\\S"
|
||||
},
|
||||
"region": {
|
||||
"type": "string",
|
||||
"pattern": "\\S"
|
||||
},
|
||||
"litellm_provider": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"bedrock",
|
||||
"bedrock_mantle"
|
||||
]
|
||||
}
|
||||
},
|
||||
"description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in."
|
||||
},
|
||||
"token_count_tokenizer": {
|
||||
"type": "string",
|
||||
"description": "Local tokenizer used to count tokens for this model.",
|
||||
"enum": [
|
||||
"kimi_k3"
|
||||
]
|
||||
},
|
||||
"tpm": {
|
||||
"type": "integer",
|
||||
"minimum": 0,
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue