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

test(cost): mirror the main catalog schema on 1.103

Browse source
This commit is contained in:
Joshua Valluru 2026-10-20 22:12:49 -07:00
parent 3c74e62aab
commit 40cc69c4b9
1 changed files with 294 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

304
model_prices_and_context_window.schema.json
View file

@ -83,7 +83,12 @@
"minimum": 0,
"description": "USD per token written to the provider's prompt cache."
},
"cache_creation_input_token_cost_above_128k_tokens": {
"cache_creation_input_token_cost_above_100k_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_100k_tokens_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
@ -93,6 +98,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_creation_input_token_cost_above_1hr_above_100k_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_above_200k_tokens": {
"type": "number",
"minimum": 0,
@ -103,12 +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."
@ -123,6 +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,
@ -133,16 +161,29 @@
"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_above_128k_tokens": {
"cache_read_input_token_cost_above_100k_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_100k_tokens_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
@ -152,17 +193,27 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"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."
},
"cache_read_input_token_cost_above_200k_tokens_priority": {
"type": "number",
"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."
@ -177,11 +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,
@ -192,6 +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
@ -203,6 +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'.",
@ -221,6 +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"
},
@ -304,11 +384,25 @@
"type": "number",
"minimum": 0
},
"input_cost_per_text_message": {
"type": "number",
"minimum": 0
},
"input_cost_per_token": {
"type": "number",
"minimum": 0,
"description": "USD per prompt token."
},
"input_cost_per_token_above_100k_tokens": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"input_cost_per_token_above_100k_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_128k_tokens": {
"type": "number",
"minimum": 0,
@ -319,17 +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."
@ -344,11 +448,20 @@
"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,
@ -358,6 +471,10 @@
"type": "number",
"minimum": 0
},
"input_cost_per_token_decisions": {
"type": "number",
"minimum": 0
},
"input_cost_per_token_flex": {
"type": "number",
"minimum": 0,
@ -368,6 +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
@ -432,6 +553,7 @@
"completion",
"embedding",
"evaluation",
"extraction",
"guardrail",
"image_edit",
"image_generation",
@ -582,10 +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
@ -603,6 +757,10 @@
"type": "number",
"minimum": 0
},
"output_cost_per_second_2k": {
"type": "number",
"minimum": 0
},
"output_cost_per_second_480p": {
"type": "number",
"minimum": 0
@ -615,11 +773,25 @@
"type": "number",
"minimum": 0
},
"output_cost_per_second_768p": {
"type": "number",
"minimum": 0
},
"output_cost_per_token": {
"type": "number",
"minimum": 0,
"description": "USD per generated token."
},
"output_cost_per_token_above_100k_tokens": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"output_cost_per_token_above_100k_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_128k_tokens": {
"type": "number",
"minimum": 0,
@ -630,17 +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."
@ -655,16 +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,
@ -675,6 +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
@ -756,6 +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."
@ -815,6 +1041,9 @@
"supports_adaptive_thinking": {
"type": "boolean"
},
"supports_anthropic_compaction": {
"type": "boolean"
},
"supports_anthropic_thinking_payload": {
"type": "boolean"
},
@ -827,9 +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"
},
@ -902,6 +1146,9 @@
"supports_reasoning": {
"type": "boolean"
},
"supports_regex_lookaround": {
"type": "boolean"
},
"supports_response_schema": {
"type": "boolean"
},
@ -995,6 +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": "Tokenizer litellm counts this model's requests with when the provider cannot count them.",
"enum": [
"kimi_k3"
]
},
"tpm": {
"type": "integer",
"minimum": 0,