mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-02 07:13:02 +00:00
chore(cost-map): accept the mirrored map's search_free_requests and token_count_model.litellm_provider in the schema
This commit is contained in:
Mrinal Chanshetty
parent
ebf92c9a45
commit
f44d4a70c0
1 changed files with 103 additions and 55 deletions
|
|
@ -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,
|
||||
|
|
@ -118,16 +113,6 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_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."
|
||||
},
|
||||
"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,
|
||||
|
|
@ -138,6 +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,
|
||||
|
|
@ -153,15 +143,14 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_creation_input_token_cost_above_32k_tokens": {
|
||||
"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,
|
||||
|
|
@ -199,11 +188,6 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_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_read_input_token_cost_above_200k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -219,11 +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,
|
||||
|
|
@ -234,6 +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,
|
||||
|
|
@ -249,11 +233,6 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"cache_read_input_token_cost_above_32k_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_512k_tokens": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -267,6 +246,10 @@
|
|||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"cache_read_input_token_cost_flex": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -314,6 +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"
|
||||
},
|
||||
|
|
@ -397,6 +384,10 @@
|
|||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_text_message": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -432,11 +423,6 @@
|
|||
"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,
|
||||
|
|
@ -447,6 +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,
|
||||
|
|
@ -462,11 +453,6 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"input_cost_per_token_above_32k_tokens": {
|
||||
"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,
|
||||
|
|
@ -485,6 +471,10 @@
|
|||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token_decisions": {
|
||||
"type": "number",
|
||||
"minimum": 0
|
||||
},
|
||||
"input_cost_per_token_flex": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
|
|
@ -563,6 +553,7 @@
|
|||
"completion",
|
||||
"embedding",
|
||||
"evaluation",
|
||||
"extraction",
|
||||
"guardrail",
|
||||
"image_edit",
|
||||
"image_generation",
|
||||
|
|
@ -821,11 +812,6 @@
|
|||
"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,
|
||||
|
|
@ -836,6 +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,
|
||||
|
|
@ -851,11 +842,6 @@
|
|||
"minimum": 0,
|
||||
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
||||
},
|
||||
"output_cost_per_token_above_32k_tokens": {
|
||||
"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,
|
||||
|
|
@ -870,6 +856,10 @@
|
|||
"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,
|
||||
|
|
@ -965,6 +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."
|
||||
|
|
@ -1039,6 +1056,12 @@
|
|||
"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"
|
||||
},
|
||||
|
|
@ -1224,6 +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.",
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue