scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-29 06:33:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 267

chore(cost-map): accept the mirrored map's search_free_requests and token_count_model.litellm_provider in the schema

Browse source
This commit is contained in:
Mrinal Chanshetty 2026-10-20 17:47:02 -07:00
parent 9c28744ad5
commit b8e89a881b
2 changed files with 183 additions and 32 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
ci_cd/generate_model_prices_schema.py
View file

@ -62,6 +62,17 @@ 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"},
},
},
"off_peak_pricing": {
"type": "object",
"description": "Rates that replace the same-named base fields while the request falls inside the stated UTC windows.",
@ -111,8 +122,9 @@ OBJECT_KEYS: dict[str, JsonSchema] = {
"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, and the AWS region its count API runs in.",
"description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in.",
},
}

201
model_prices_and_context_window.schema.json
View file

@ -93,11 +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,
@ -118,11 +113,6 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_creation_input_token_cost_above_256k_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": {
"type": "number",
"minimum": 0,
@ -133,6 +123,11 @@
"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."
},
"cache_creation_input_token_cost_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
@ -143,7 +138,7 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_creation_input_token_cost_above_32k_tokens": {
"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."
@ -152,6 +147,10 @@
"type": "number",
"minimum": 0
},
"cache_creation_input_token_cost_decisions": {
"type": "number",
"minimum": 0
},
"cache_creation_input_token_cost_flex": {
"type": "number",
"minimum": 0,
@ -162,6 +161,10 @@
"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
@ -185,12 +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."
@ -200,11 +203,6 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_read_input_token_cost_above_256k_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": {
"type": "number",
"minimum": 0,
@ -215,6 +213,11 @@
"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."
},
"cache_read_input_token_cost_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
@ -225,7 +228,7 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_read_input_token_cost_above_32k_tokens": {
"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."
@ -235,10 +238,18 @@
"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,
@ -249,6 +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
@ -260,6 +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'.",
@ -278,6 +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"
},
@ -361,6 +384,10 @@
"type": "number",
"minimum": 0
},
"input_cost_per_text_message": {
"type": "number",
"minimum": 0
},
"input_cost_per_token": {
"type": "number",
"minimum": 0,
@ -386,16 +413,16 @@
"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": {
"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": {
"type": "number",
"minimum": 0,
@ -406,6 +433,11 @@
"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."
},
"input_cost_per_token_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
@ -416,7 +448,7 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"input_cost_per_token_above_32k_tokens": {
"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."
@ -426,6 +458,10 @@
"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,
@ -435,6 +471,10 @@
"type": "number",
"minimum": 0
},
"input_cost_per_token_decisions": {
"type": "number",
"minimum": 0
},
"input_cost_per_token_flex": {
"type": "number",
"minimum": 0,
@ -445,6 +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
@ -509,6 +553,7 @@
"completion",
"embedding",
"evaluation",
"extraction",
"guardrail",
"image_edit",
"image_generation",
@ -691,6 +736,10 @@
"type": "number",
"minimum": 0
},
"output_cost_per_image_token_batches": {
"type": "number",
"minimum": 0
},
"output_cost_per_pixel": {
"type": "number",
"minimum": 0
@ -753,16 +802,16 @@
"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": {
"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": {
"type": "number",
"minimum": 0,
@ -773,6 +822,11 @@
"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."
},
"output_cost_per_token_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
@ -783,7 +837,7 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"output_cost_per_token_above_32k_tokens": {
"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."
@ -793,11 +847,19 @@
"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,
@ -808,6 +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
@ -889,6 +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."
@ -963,6 +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"
},
@ -1035,6 +1146,9 @@
"supports_reasoning": {
"type": "boolean"
},
"supports_regex_lookaround": {
"type": "boolean"
},
"supports_response_schema": {
"type": "boolean"
},
@ -1133,6 +1247,31 @@
"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": "Tokenizer litellm counts this model's requests with when the provider cannot count them.",