From c515f80f8260580f6fd5e07688535f77e4cdf6f2 Mon Sep 17 00:00:00 2001 From: Mateo Wang <277851410+mateo-berri@users.noreply.github.com> Date: Wed, 21 Oct 2026 01:46:03 +0000 Subject: [PATCH] ci(cost map): delete the model prices JSON schema file (#47079) * chore(cost map): delete the unused model prices JSON schema Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * ci(cost map): remove interim schema sync compatibility Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .circleci/scripts/classify_changes.sh | 2 +- ci_cd/cost_map_guard.py | 6 +- model_prices_and_context_window.schema.json | 1312 ------------------- tests/unit/test_circleci_path_filter.py | 1 - tests/unit/test_cost_map_guard.py | 7 - 5 files changed, 3 insertions(+), 1325 deletions(-) delete mode 100644 model_prices_and_context_window.schema.json diff --git a/.circleci/scripts/classify_changes.sh b/.circleci/scripts/classify_changes.sh index d2ab3478397..a33695d0dbe 100755 --- a/.circleci/scripts/classify_changes.sh +++ b/.circleci/scripts/classify_changes.sh @@ -33,7 +33,7 @@ while IFS= read -r file || [ -n "$file" ]; do *) has_backend=true ;; esac case "$file" in - model_prices_and_context_window.json | litellm/model_prices_and_context_window_backup.json | model_prices_and_context_window.schema.json) + model_prices_and_context_window.json | litellm/model_prices_and_context_window_backup.json) has_cost_map=true ;; tests/unit/proxy/*) : ;; *) outside_cost_map_set=true ;; diff --git a/ci_cd/cost_map_guard.py b/ci_cd/cost_map_guard.py index 932da84e5d7..c1aeaabc5d2 100644 --- a/ci_cd/cost_map_guard.py +++ b/ci_cd/cost_map_guard.py @@ -4,8 +4,7 @@ Every pull request whose diff against its merge base touches one of the two cost checks: the files parse and the backup copy matches the root file. A pull request that leaves both untouched skips them, since merging it keeps the base branch's copies and its head tree only carries whatever state the branch was cut from. Pull requests from the cost map sync bot (branches named litellm_cost_map_sync_*) always -get the file checks and additionally may only touch those two files or the legacy schema -path and may only add or update models. +get the file checks and additionally may only touch those two files and may only add or update models. """ from __future__ import annotations @@ -21,7 +20,6 @@ from typing import Final COST_MAP_PATH: Final = "model_prices_and_context_window.json" BACKUP_PATH: Final = "litellm/model_prices_and_context_window_backup.json" -LEGACY_SCHEMA_PATH: Final = "model_prices_and_context_window.schema.json" GUARDED_PATHS: Final = (COST_MAP_PATH, BACKUP_PATH) BOT_BRANCH_PREFIX: Final = "litellm_cost_map_sync_" SPECIAL_ROOT_KEYS: Final = frozenset({"sample_spec", "fallback_generalizations"}) @@ -110,7 +108,7 @@ def _bot_failures(base: Snapshot, head_map: CostMap, changed_files: Sequence[str *( f"bot PRs may only change the cost map files, not {path}" for path in changed_files - if path not in GUARDED_PATHS and path != LEGACY_SCHEMA_PATH + if path not in GUARDED_PATHS ), *(f"bot PRs may not remove models: {key}" for key in base_map if key not in head_map), *(f"bot PRs may not remove fields: {ref}" for ref in removed_fields), diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json deleted file mode 100644 index d4dfeb25429..00000000000 --- a/model_prices_and_context_window.schema.json +++ /dev/null @@ -1,1312 +0,0 @@ -{ - "$schema": "https://json-schema.org/draft/2020-12/schema", - "title": "LiteLLM model_prices_and_context_window.json", - "description": "Schema for LiteLLM's model price and context window registry (https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json). Every top-level key except 'sample_spec' and 'fallback_generalizations' is a model id, optionally prefixed with its provider (e.g. 'azure/gpt-5.4'), mapping to a model entry. All costs are USD per unit. New optional fields are added regularly, so consumers should ignore unknown fields rather than reject them.", - "type": "object", - "properties": { - "sample_spec": { - "type": "object", - "description": "Documentation placeholder illustrating the entry shape; not a real model and not schema-conformant (several values are prose)." - }, - "fallback_generalizations": { - "type": "object", - "description": "Regex rules that generalize unknown model ids to known families; not a model entry.", - "properties": { - "rules": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "pattern": { - "type": "string" - }, - "description": { - "type": "string" - } - }, - "required": [ - "name", - "pattern" - ], - "additionalProperties": true - } - } - }, - "additionalProperties": false - } - }, - "additionalProperties": { - "$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_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." - }, - "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_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, - "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_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_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, - "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_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, - "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_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_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." - }, - "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_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_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_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, - "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_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, - "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." - }, - "cache_read_input_token_cost_ultrafast": { - "type": "number", - "minimum": 0 - }, - "citation_cost_per_token": { - "type": "number", - "minimum": 0 - }, - "code_interpreter_cost_per_session": { - "type": "number", - "minimum": 0 - }, - "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'.", - "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])$" - }, - "explicit_cache_read_input_token_cost": { - "type": "number", - "minimum": 0 - }, - "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_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, - "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_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_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_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, - "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_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." - }, - "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, - "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_token_ultrafast": { - "type": "number", - "minimum": 0 - }, - "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", - "extraction", - "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_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 - }, - "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_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, - "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_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_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_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, - "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_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, - "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_token_ultrafast": { - "type": "number", - "minimum": 0 - }, - "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 - }, - "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." - }, - "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_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" - }, - "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_regex_lookaround": { - "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 - } - }, - "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, - "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 - } - } -} diff --git a/tests/unit/test_circleci_path_filter.py b/tests/unit/test_circleci_path_filter.py index f94b2fa863a..c44560b96f1 100644 --- a/tests/unit/test_circleci_path_filter.py +++ b/tests/unit/test_circleci_path_filter.py @@ -96,7 +96,6 @@ CI = [".github/workflows/test-unit.yml"] ("ui", BACKEND + CLIENT, "run"), ("cost-map-only", ["model_prices_and_context_window.json"], "run"), ("cost-map-only", ["litellm/model_prices_and_context_window_backup.json"], "run"), - ("cost-map-only", ["model_prices_and_context_window.schema.json"], "run"), ( "cost-map-only", ["model_prices_and_context_window.json", "tests/unit/proxy/test_y.py"], diff --git a/tests/unit/test_cost_map_guard.py b/tests/unit/test_cost_map_guard.py index a705597952b..578d5482822 100644 --- a/tests/unit/test_cost_map_guard.py +++ b/tests/unit/test_cost_map_guard.py @@ -186,13 +186,6 @@ def test_bot_may_only_touch_the_cost_map_files() -> None: ) -def test_bot_may_update_cost_map_and_legacy_schema() -> None: - head: Final = _snapshot({**BASE_MAP, "openrouter/c": _entry()}) - changed: Final = (*guard.GUARDED_PATHS, guard.LEGACY_SCHEMA_PATH) - - assert _failures(head, changed_files=changed) == () - - def test_bot_may_not_remove_models() -> None: head = _snapshot({key: value for key, value in BASE_MAP.items() if key != "openrouter/b"}) assert _failures(head, bot=False) == ()