scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109
litellm/model_prices_and_context_window.schema.json
devin-ai-integration[bot] 233db9f285
feat(bedrock): serve gpt-5.6+ chat completions natively by default, with chat_completions/ opt-in for gpt-oss and grok (#44307) 
* feat(bedrock): send grok chat completions through runtime openai path

Unspecified bedrock grok was rewritten to Converse. Chat completions now hit bedrock-runtime /openai/v1/chat/completions, and converse/ still uses Converse

* feat(bedrock): serve gpt-oss and gpt-5.6 chat completions on runtime's native openai path

* fix(bedrock): route gpt-oss response_format to Converse and decide the route once from the raw request

* fix(bedrock): serve region-path and GovCloud gpt-oss ids on native Chat Completions

The cost-map parity tests require every regional variant of a flagged id to carry the same supports_ flags, so the six us-gov gpt-oss entries now carry the native-route flags too. A region path in the model name (bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0) is routing, not a different model: the route is looked up on the id after the path, the path's region picks the endpoint and the SigV4 scope, an explicit aws_region_name still wins, and the body carries the bare id AWS expects

* fix(bedrock): keep params AWS refuses natively off the chat completions route

Drop the params each family 400s or 503s on runtime Chat Completions from the native config's supported list (GPT-5.6 penalties, stop, and logprobs, Grok penalties, gpt-oss logit_bias) so drop_params drops them as Converse did, gate legacy functions on GPT-5.6 the same way as tools, and send an Anthropic-style thinking block to Converse, the only route that forwards it

* fix(bedrock): keep schema-less json_object on Converse for the chat completions models

* fix(bedrock): keep every json_object response_format on Converse for the chat completions models

* fix(rust): declare the bedrock runtime chat completions flags on ModelInfo

* fix(bedrock): opt into the native chat completions route through supported_endpoints

* docs(cost-map): describe the bedrock native chat completions capability flags

* revert: docs(cost-map): describe the bedrock native chat completions capability flags

This reverts commit 4101c0ceb2.

cost-map-guard runs main's schema generator under pull_request_target and compares
its output to the PR's committed schema, so a PR that changes the generator's output
cannot pass that required check until the generator change lands on main first. The
descriptions move to a follow-up that lands the generator change ahead of the schema

* test(bedrock): move the native chat completions tests under tests/unit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): drop reasoning_effort none for grok on the native chat completions route

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): keep converse extension params on the converse route

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): inline http image urls and keep stop on converse for native chat completions

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(bedrock): share the sync remote media inliner

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(image-handling): infer the image mime type when the server sends a generic content type

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): stop sending aws_bedrock_project_id as OpenAI-Project on the runtime chat completions route

* feat(bedrock): make native chat completions an opt-in bedrock/chat_completions/ route

Bare Bedrock OpenAI and Grok model ids stay on Converse as on main. The
bedrock/chat_completions/<model> prefix opts a deployment into bedrock-runtime's
/openai/v1/chat/completions, and a request carrying a Converse-only param
still falls back to Converse. The cost map no longer decides the route.

* fix(bedrock): keep chat_completions/-prefixed deployments on the native Responses surface

* fix(bedrock): keep provider response headers on the runtime chat completions route

* feat(bedrock): serve gpt-5.6 and newer on runtime chat completions by default

Unprefixed bedrock/<gpt-5.6+> models whose cost-map row lists /v1/chat/completions
now route to the native OpenAI-compatible endpoint; converse/ pins Converse and
chat_completions/ still opts gpt-oss and Grok in. Guardrails, application inference
profile ARNs, and tools with reasoning keep falling back to Converse per request.
Hoist the remote-media url comprehension into a single-clause helper.

* fix(bedrock): refuse temperature and top_p natively on GPT 5.6 and newer like Converse does

AWS answers temperature and top_p with a 400 on the native Chat Completions endpoint for the GPT 5.6+ models, the same models whose Converse route already dropped both under drop_params via supports_sampling_params: false. The native config now honors that price-map flag, the gpt-6 and gpt-6.1 rows carry it, and the gpt-6 family joins gpt-5 in refusing frequency_penalty, presence_penalty, logprobs, and top_logprobs before the request reaches AWS.

* fix(bedrock): refuse GPT sampling and logprob params natively only while reasoning is on

On bedrock-runtime's native chat completions endpoint, GPT-5.x and GPT-6.x
accept temperature, top_p, frequency_penalty, presence_penalty, logprobs,
and top_logprobs once reasoning_effort is "none", and refuse them with any
other effort or when the effort is unset. The previous commit refused the
sampling params unconditionally from the cost map's supports_sampling_params
flag, which lost the reasoning-off case and never covered the penalties or
logprobs. The refusal now keys on the model being a GPT id and reasoning
being active, raises a 400 UnsupportedParamsError naming the params unless
drop_params drops them, and lets everything through under "none". Grok and
gpt-oss keep their unconditional family refusals.

* refactor(bedrock): keep the Converse route-prefix strip inside the bedrock llms module

* fix(bedrock): forward a non-string reasoning_effort on the native route instead of crashing

A list or dict reasoning_effort hit a frozenset membership test in
without_refused_reasoning_effort and raised TypeError, which the proxy
surfaced as a 500 APIConnectionError with no upstream call. The value is
now left alone unless it is a string Bedrock's native endpoint refuses,
so AWS answers the malformed value with its own 400 like it does for an int

* fix(bedrock): route overlong GPT version digits to Converse and send native chat completions to the runtime endpoint

A model id with more than 4300 version digits raised ValueError in the route check; the digits are now bounded so such ids fall back to Converse. The native chat completions URL now follows Converse's precedence: aws_bedrock_runtime_endpoint (or AWS_BEDROCK_RUNTIME_ENDPOINT) wins over api_base, so a deployment that sets both keeps sending to the same host

* fix(bedrock): route model_id overrides to Converse and never send an empty bearer natively

A deployment whose litellm_params carry model_id (an application inference profile or provisioned throughput ARN) went to the native Chat Completions route with the base model in the URL and model_id left in the body. It now takes Converse like the bedrock/arn:... model form, which encodes the override into the request URL

A blank api_key on a SigV4 deployment became an Authorization header reading Bearer with nothing after it on the native route, since the OpenAI-like header builder writes any non-None key and the signer keeps a non-AWS4 Authorization header. validate_environment now resolves the key through bedrock_bearer_token, so a blank key is signed with SigV4 the way Converse signs it

* test(bedrock): audit the native GPT chat completions route on the integration rig

Adds the /audit cells for the runtime chat completions route: the scripted Bedrock runtime peer, the happy and fallback wire tests, the sad-path and regex worst-case tests, the chaos burst tests, the Messages adapter tests, and the Responses native-route tests. Tests only, no product diff.

* test(bedrock): harden the runtime chat completions audit cells

The chaos peer's shared counter and process now come from the same spawn context, since a fork-context Value handed to a spawn-context process raises on Linux. The peer-kill test waits for the first six answers to reach the client before killing the peer instead of counting accepted requests. The Responses wire tests look the spend row up under both the ciphertext id the caller received and the issued id behind it, matching the chaos file's rule for the pre-encryption row

* fix(bedrock): refuse or drop a non-string reasoning_effort before the native chat completions call

A reasoning_effort sent as an int, a list, or an object on a GPT 5.6+ deployment the native
route serves now answers 400 from litellm before any wire request, naming the type and the
drop_params way out, and is dropped under drop_params so AWS applies its default effort, the
way Converse dropped it on main. The tip since a0cef91f0b forwarded it for AWS to refuse

* test(bedrock): pin router retries off and give the chaos bursts config deployments on an owned proxy

* test(bedrock): wait for the replacement worker before tearing down the sigkill chaos proxy

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mateo <mateo@berri.ai>
2026-10-02 19:55:54 -07:00

1197 lines
40 KiB
JSON
Raw Blame History

{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "LiteLLM model_prices_and_context_window.json",
"description": "Schema for LiteLLM's model price and context window registry (https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json). Every top-level key except 'sample_spec' and 'fallback_generalizations' is a model id, optionally prefixed with its provider (e.g. 'azure/gpt-5.4'), mapping to a model entry. All costs are USD per unit. New optional fields are added regularly, so consumers should ignore unknown fields rather than reject them.",
"type": "object",
"properties": {
"sample_spec": {
"type": "object",
"description": "Documentation placeholder illustrating the entry shape; not a real model and not schema-conformant (several values are prose)."
},
"fallback_generalizations": {
"type": "object",
"description": "Regex rules that generalize unknown model ids to known families; not a model entry.",
"properties": {
"rules": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"pattern": {
"type": "string"
},
"description": {
"type": "string"
}
},
"required": [
"name",
"pattern"
],
"additionalProperties": true
}
}
},
"additionalProperties": false
}
},
"additionalProperties": {
"$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_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,
"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_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_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_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_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_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": {
"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_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_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,
"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_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])$"
},
"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_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"input_cost_per_token_above_200k_tokens_priority": {
"type": "number",
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"input_cost_per_token_above_256k_tokens": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"input_cost_per_token_above_272k_tokens": {
"type": "number",
"minimum": 0,
"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_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_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,
"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_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",
"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_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_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"output_cost_per_token_above_200k_tokens_priority": {
"type": "number",
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"output_cost_per_token_above_256k_tokens": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"output_cost_per_token_above_272k_tokens": {
"type": "number",
"minimum": 0,
"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_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_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,
"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_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
},
"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_runtime_chat_completions_response_format": {
"type": "boolean"
},
"supports_bedrock_runtime_chat_completions_tools_with_reasoning": {
"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
}
},
"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
}
}
}
Reference in a new issue View git blame Copy permalink