mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-24 00:52:24 +00:00
deba473821
* fix(cost): bill batch prompts above 272K at OpenAI's long-context batch tier * fix(cost): mirror batch long-context keys on custom pricing params Register the two *_above_272k_tokens_batches keys on CustomPricingLiteLLMParams so a per-deployment override stays out of the shared backend key, add them to the inline model-info schema and alias-count tests, and build LiteLLM_Params and GenericLiteLLMParams through model_validate at the two dict-splat call sites so basedpyright's reportArgumentType budget ratchets down instead of blocking the new fields. * fix(cost): add the gpt-5.5-pro batch long-context tier and ignore malformed batch tier keys * fix(cost): bill cached batch tokens at OpenAI's cached batch rate Adds cache_read_input_token_cost_batches and cache_read_input_token_cost_above_272k_tokens_batches for the tiered OpenAI entries at half the standard cached rate, bills cached batch tokens at that rate per output line, and parses string-valued batch rates in deployment-level model_info. * fix(cost): bill batch cache writes at the batch cache-write rate and carry published batch rates for one-sided deployments OpenAI's Batch table prices cache writes for gpt-6-astra, gpt-5.6, gpt-5.6-sol, gpt-5.6-terra and gpt-5.6-luna at half the standard cache-write rate, so the cost map gains cache_creation_input_token_cost_batches and its above_272k tier for those entries and batch cost pulls written tokens out of the input bucket at that rate; models without the key keep billing writes at the batch input rate. A deployment declaring only one side of its batch pricing now carries every published batch rate of the other side (tier, cached, cache write), its own keys win, and a lone tier, cached or cache-write batch key counts as declared pricing instead of being ignored. * fix(cost): select the batch long-context tier from any batch tier key A deployment that declares its own flat standard input rate keeps every published batch rate of the output direction, including the 272K output tier, but the tier was only ever selected when an input tier key was also present. Detect the crossed tier from any of the four batch tier keys so the carried output, cache-read, and cache-write tiers bill at their tier rate above 272K tokens. * chore(proxy): keep the OpenAPI snapshot as CI generates it * fix(cost): pick each batch price component's tier from its own keys The batch rate picker crossed one threshold for every component, so a deployment declaring only an output tier also moved its input, cached, and cache-write rates to that cutoff. Each component now crosses its own *_above_<N>k_tokens_batches keys and falls back to its flat key. The JSON schema is regenerated with the generator as it is on main: cost-map-guard renders the PR's cost map with the base branch's generator, so the descriptions for the new batch cache keys move to a follow-up. * chore(proxy): restore the lazy OpenAPI snapshot to what CI's Python 3.12 generates The merge commit carried a snapshot regenerated on a Python 3.14 venv, which dedents docstrings at compile time, so one description line differed from the file CI regenerates on 3.12 and the schema.d.ts sync check went red. The snapshot is byte-identical to main again
1080 lines
36 KiB
JSON
1080 lines
36 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"title": "LiteLLM model_prices_and_context_window.json",
|
|
"description": "Schema for LiteLLM's model price and context window registry (https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json). Every top-level key except 'sample_spec' and 'fallback_generalizations' is a model id, optionally prefixed with its provider (e.g. 'azure/gpt-5.4'), mapping to a model entry. All costs are USD per unit. New optional fields are added regularly, so consumers should ignore unknown fields rather than reject them.",
|
|
"type": "object",
|
|
"properties": {
|
|
"sample_spec": {
|
|
"type": "object",
|
|
"description": "Documentation placeholder illustrating the entry shape; not a real model and not schema-conformant (several values are prose)."
|
|
},
|
|
"fallback_generalizations": {
|
|
"type": "object",
|
|
"description": "Regex rules that generalize unknown model ids to known families; not a model entry.",
|
|
"properties": {
|
|
"rules": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"name": {
|
|
"type": "string"
|
|
},
|
|
"pattern": {
|
|
"type": "string"
|
|
},
|
|
"description": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"name",
|
|
"pattern"
|
|
],
|
|
"additionalProperties": true
|
|
}
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
}
|
|
},
|
|
"additionalProperties": {
|
|
"$ref": "#/$defs/modelEntry"
|
|
},
|
|
"$defs": {
|
|
"modelEntry": {
|
|
"type": "object",
|
|
"description": "Pricing, limits, and capability flags for one model. Fields other than litellm_provider are optional; boolean capability flags are simply omitted when unknown or false.",
|
|
"required": [
|
|
"litellm_provider"
|
|
],
|
|
"properties": {
|
|
"annotation_cost_per_page": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"annotation_cost_per_page_batches": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"audio_transcription_config": {
|
|
"type": "string"
|
|
},
|
|
"bedrock_converse_supports_strict_tools": {
|
|
"type": "boolean"
|
|
},
|
|
"bedrock_output_config_effort_ceiling": {
|
|
"type": "string",
|
|
"description": "Highest reasoning effort the Bedrock output_config accepts for this model.",
|
|
"enum": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"max",
|
|
"xhigh"
|
|
]
|
|
},
|
|
"cache_creation_input_audio_token_cost": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"cache_creation_input_token_cost": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "USD per token written to the provider's prompt cache."
|
|
},
|
|
"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,
|
|
"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,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"cache_creation_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_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,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"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_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"cache_creation_input_token_cost_above_272k_tokens_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"cache_creation_input_token_cost_batches": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"cache_creation_input_token_cost_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"cache_creation_input_token_cost_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"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": {
|
|
"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,
|
|
"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": {
|
|
"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,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"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_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"cache_read_input_token_cost_above_272k_tokens_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"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_batches": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"cache_read_input_token_cost_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"cache_read_input_token_cost_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"citation_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"code_interpreter_cost_per_session": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"comment": {
|
|
"type": "string"
|
|
},
|
|
"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'.",
|
|
"enum": [
|
|
"none",
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
},
|
|
"deprecation_date": {
|
|
"type": "string",
|
|
"description": "Date the provider deprecates the model, YYYY-MM-DD.",
|
|
"format": "date",
|
|
"pattern": "^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$"
|
|
},
|
|
"gemini_audio_only_live": {
|
|
"type": "boolean"
|
|
},
|
|
"gemini_native_audio": {
|
|
"type": "boolean"
|
|
},
|
|
"google_maps_grounding_cost_per_query": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "USD per Grounding with Google Maps request; billed per query or per prompt per web_search_billing_unit."
|
|
},
|
|
"guardrail_cost_per_unit": {
|
|
"type": "object",
|
|
"description": "USD cost per billable guardrail unit, keyed by the provider's usage counter name (e.g. Bedrock's contentPolicyUnits).",
|
|
"additionalProperties": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"input_cost_per_audio_per_second": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_audio_per_second_above_128k_tokens": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"input_cost_per_audio_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_audio_token_batches": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_audio_token_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"input_cost_per_character": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_character_above_128k_tokens": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"input_cost_per_image": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_image_above_128k_tokens": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"input_cost_per_image_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_image_token_batches": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_pixel": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_query": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_request": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_second": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "USD per prompt token."
|
|
},
|
|
"input_cost_per_token_above_128k_tokens": {
|
|
"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": {
|
|
"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,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"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_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"input_cost_per_token_above_272k_tokens_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"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_batches": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "USD per prompt token via the provider's batch API."
|
|
},
|
|
"input_cost_per_token_cache_hit": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_token_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"input_cost_per_token_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"input_cost_per_video_per_second": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_video_per_second_above_128k_tokens": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"input_cost_per_video_per_second_above_15s_interval": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"input_cost_per_video_per_second_above_8s_interval": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"input_cost_per_video_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_video_token_batches": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_dbu_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"litellm_provider": {
|
|
"type": "string",
|
|
"description": "LiteLLM provider slug; one of https://docs.litellm.ai/docs/providers."
|
|
},
|
|
"max_input_tokens": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Maximum prompt/context tokens the model accepts."
|
|
},
|
|
"max_output_tokens": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Maximum tokens the model can generate in one response."
|
|
},
|
|
"max_tokens": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Legacy field: max output tokens if the provider specifies it, else max input tokens."
|
|
},
|
|
"metadata": {
|
|
"type": "object",
|
|
"description": "Free-form notes about the entry (e.g. pricing derivation)."
|
|
},
|
|
"mode": {
|
|
"type": "string",
|
|
"description": "Primary API surface / task type of the model.",
|
|
"enum": [
|
|
"audio_speech",
|
|
"audio_transcription",
|
|
"chat",
|
|
"completion",
|
|
"embedding",
|
|
"evaluation",
|
|
"guardrail",
|
|
"image_edit",
|
|
"image_generation",
|
|
"moderation",
|
|
"ocr",
|
|
"realtime",
|
|
"rerank",
|
|
"responses",
|
|
"search",
|
|
"vector_store",
|
|
"video_generation"
|
|
]
|
|
},
|
|
"ocr_cost_per_credit": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"ocr_cost_per_page": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"ocr_cost_per_page_batches": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"off_peak_pricing": {
|
|
"type": "object",
|
|
"description": "Rates that replace the same-named base fields while the request falls inside the stated UTC windows.",
|
|
"properties": {
|
|
"hours_utc": {
|
|
"description": "UTC \"HH:MM-HH:MM\" window, or a list of them; a window may wrap past midnight.",
|
|
"oneOf": [
|
|
{
|
|
"type": "string",
|
|
"pattern": "^([01]\\d|2[0-3]):[0-5]\\d-([01]\\d|2[0-3]):[0-5]\\d$"
|
|
},
|
|
{
|
|
"type": "array",
|
|
"items": {
|
|
"type": "string",
|
|
"pattern": "^([01]\\d|2[0-3]):[0-5]\\d-([01]\\d|2[0-3]):[0-5]\\d$"
|
|
},
|
|
"minItems": 1
|
|
}
|
|
]
|
|
},
|
|
"windows": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"hours_utc": {
|
|
"description": "UTC \"HH:MM-HH:MM\" window, or a list of them; a window may wrap past midnight.",
|
|
"oneOf": [
|
|
{
|
|
"type": "string",
|
|
"pattern": "^([01]\\d|2[0-3]):[0-5]\\d-([01]\\d|2[0-3]):[0-5]\\d$"
|
|
},
|
|
{
|
|
"type": "array",
|
|
"items": {
|
|
"type": "string",
|
|
"pattern": "^([01]\\d|2[0-3]):[0-5]\\d-([01]\\d|2[0-3]):[0-5]\\d$"
|
|
},
|
|
"minItems": 1
|
|
}
|
|
]
|
|
},
|
|
"weekdays": {
|
|
"type": "array",
|
|
"description": "ISO-8601 weekday numbers (1 = Monday .. 7 = Sunday) or English day names the window applies on.",
|
|
"items": {
|
|
"oneOf": [
|
|
{
|
|
"type": "integer",
|
|
"minimum": 1,
|
|
"maximum": 7
|
|
},
|
|
{
|
|
"type": "string",
|
|
"pattern": "(?i)^(mon|monday|tue|tues|tuesday|wed|wednesday|thu|thur|thurs|thursday|fri|friday|sat|saturday|sun|sunday)$"
|
|
}
|
|
]
|
|
},
|
|
"minItems": 1
|
|
}
|
|
},
|
|
"required": [
|
|
"hours_utc"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
"minItems": 1
|
|
},
|
|
"weekday_timezone": {
|
|
"type": "string",
|
|
"description": "IANA zone the weekdays of each window are read on; defaults to UTC."
|
|
},
|
|
"input_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_reasoning_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"cache_read_input_token_cost": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"cache_creation_input_token_cost": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"anyOf": [
|
|
{
|
|
"required": [
|
|
"hours_utc"
|
|
]
|
|
},
|
|
{
|
|
"required": [
|
|
"windows"
|
|
]
|
|
}
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
"output_cost_per_audio_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_character": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_character_above_128k_tokens": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"output_cost_per_image": {
|
|
"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_512": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_image_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_pixel": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_reasoning_token": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "USD per reasoning/thinking token, when billed separately."
|
|
},
|
|
"output_cost_per_second": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_second_1080p": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_second_2k": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_second_480p": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_second_4k": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_second_720p": {
|
|
"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_128k_tokens": {
|
|
"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": {
|
|
"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,
|
|
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
|
|
},
|
|
"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_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"output_cost_per_token_above_272k_tokens_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"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_batches": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "USD per generated token via the provider's batch API."
|
|
},
|
|
"output_cost_per_token_flex": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Flex service-tier rate for the same-named base field."
|
|
},
|
|
"output_cost_per_token_priority": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"description": "Priority service-tier rate for the same-named base field."
|
|
},
|
|
"output_cost_per_video_per_second": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_video_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_dbu_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_vector_size": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Embedding dimension for embedding models."
|
|
},
|
|
"prompt_cache_min_tokens": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Smallest prefix the provider will actually cache; absent means the provider default applies."
|
|
},
|
|
"provider_specific_entry": {
|
|
"type": "object",
|
|
"description": "Provider-internal routing hints (e.g. bedrock_invocation_schema)."
|
|
},
|
|
"reasoning_effort_levels": {
|
|
"type": "array",
|
|
"description": "Exact reasoning_effort levels this deployment accepts; wins over supports_* flags.",
|
|
"items": {
|
|
"type": "string",
|
|
"enum": [
|
|
"none",
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
},
|
|
"regional_endpoint_uplift_multiplier": {
|
|
"type": "number",
|
|
"minimum": 1,
|
|
"description": "Multiplier applied to all token costs when served from a non-global Vertex AI endpoint (e.g. 1.10 = +10%)."
|
|
},
|
|
"regional_processing_uplift_multiplier_eu": {
|
|
"type": "number",
|
|
"minimum": 1,
|
|
"description": "Multiplier applied to all token costs for EU data residency (e.g. 1.10 = +10%)."
|
|
},
|
|
"regional_processing_uplift_multiplier_us": {
|
|
"type": "number",
|
|
"minimum": 1,
|
|
"description": "Multiplier applied to all token costs for US data residency (e.g. 1.10 = +10%)."
|
|
},
|
|
"rpm": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Provider default requests-per-minute limit."
|
|
},
|
|
"search_context_cost_per_query": {
|
|
"type": "object",
|
|
"description": "USD cost per web search query, keyed by search context size.",
|
|
"properties": {
|
|
"search_context_size_low": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"search_context_size_medium": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"search_context_size_high": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"description": "URL of the provider pricing/model page this entry was taken from."
|
|
},
|
|
"supported_audio_formats": {
|
|
"type": "array",
|
|
"description": "Audio container formats the model can return.",
|
|
"items": {
|
|
"type": "string",
|
|
"enum": [
|
|
"mp3",
|
|
"wav"
|
|
]
|
|
}
|
|
},
|
|
"supported_endpoints": {
|
|
"type": "array",
|
|
"description": "OpenAI-style API routes this model can be called through, e.g. /v1/chat/completions.",
|
|
"items": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"supported_modalities": {
|
|
"type": "array",
|
|
"description": "Input modalities the model accepts.",
|
|
"items": {
|
|
"type": "string",
|
|
"enum": [
|
|
"text",
|
|
"image",
|
|
"audio",
|
|
"video"
|
|
]
|
|
}
|
|
},
|
|
"supported_output_modalities": {
|
|
"type": "array",
|
|
"description": "Output modalities the model can produce.",
|
|
"items": {
|
|
"type": "string",
|
|
"enum": [
|
|
"text",
|
|
"image",
|
|
"audio",
|
|
"video",
|
|
"code"
|
|
]
|
|
}
|
|
},
|
|
"supported_regions": {
|
|
"type": "array",
|
|
"description": "Cloud regions the model is available in ('global' or region ids).",
|
|
"items": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"supports_adaptive_thinking": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_anthropic_compaction": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_anthropic_thinking_payload": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_assistant_prefill": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_audio_input": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_audio_output": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_computer_use": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_embedding_image_input": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_fast_mode": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_forced_tool_use": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_function_calling": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_image_input": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_image_size": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_legacy_thinking": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_low_reasoning_effort": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_max_reasoning_effort": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_mid_conversation_system": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_minimal_reasoning_effort": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_multimodal": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_native_streaming": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_native_structured_output": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_none_reasoning_effort": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_nova_canvas_image_edit": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_output_config": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_parallel_function_calling": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_parallel_tool_use_config": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_pdf_input": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_prompt_cache_breakpoint": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_prompt_caching": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_reasoning": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_response_schema": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_sampling_params": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_speed": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_system_messages": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_thinking_cache_preservation": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_tool_choice": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_tool_search": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_url_context": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_video_input": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_vision": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_web_search": {
|
|
"type": "boolean"
|
|
},
|
|
"supports_xhigh_reasoning_effort": {
|
|
"type": "boolean"
|
|
},
|
|
"thinking_always_on": {
|
|
"type": "boolean"
|
|
},
|
|
"tiered_pricing": {
|
|
"type": "array",
|
|
"description": "Context-length or result-count tiered rates; each tier's costs apply within its range.",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"range": {
|
|
"type": "array",
|
|
"description": "[min, max] prompt-token span this tier applies to.",
|
|
"items": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"minItems": 2,
|
|
"maxItems": 2
|
|
},
|
|
"max_results_range": {
|
|
"type": "array",
|
|
"description": "[min, max] result-count span this tier applies to (search models).",
|
|
"items": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"minItems": 2,
|
|
"maxItems": 2
|
|
},
|
|
"input_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"output_cost_per_reasoning_token": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"cache_read_input_token_cost": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"cache_creation_input_token_cost": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
},
|
|
"input_cost_per_query": {
|
|
"type": "number",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
}
|
|
},
|
|
"tpm": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Provider default tokens-per-minute limit."
|
|
},
|
|
"use_openai_responses_path": {
|
|
"type": "boolean"
|
|
},
|
|
"uses_embed_content": {
|
|
"type": "boolean"
|
|
},
|
|
"vertex_ai_audio_api": {
|
|
"type": "string",
|
|
"enum": [
|
|
"lyria_predict",
|
|
"lyria_interactions"
|
|
]
|
|
},
|
|
"web_search_billing_unit": {
|
|
"type": "string",
|
|
"description": "Whether web search is billed per query or per prompt.",
|
|
"enum": [
|
|
"per_query",
|
|
"per_prompt"
|
|
]
|
|
}
|
|
},
|
|
"additionalProperties": true
|
|
}
|
|
}
|
|
}
|