Skip to main content
POST
/
api
/
governance
/
pricing-overrides
Create pricing override
curl --request POST \
  --url http://localhost:8080/api/governance/pricing-overrides \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "scope_kind": "global",
  "match_type": "exact",
  "pattern": "<string>",
  "request_types": [
    "chat_completion"
  ],
  "virtual_key_id": "<string>",
  "provider_id": "<string>",
  "provider_key_id": "<string>",
  "patch": {
    "input_cost_per_token": 1,
    "output_cost_per_token": 1,
    "input_cost_per_token_batches": 1,
    "output_cost_per_token_batches": 1,
    "input_cost_per_token_priority": 1,
    "output_cost_per_token_priority": 1,
    "input_cost_per_character": 1,
    "input_cost_per_token_above_128k_tokens": 1,
    "output_cost_per_token_above_128k_tokens": 1,
    "input_cost_per_token_above_200k_tokens": 1,
    "output_cost_per_token_above_200k_tokens": 1,
    "cache_creation_input_token_cost": 1,
    "cache_read_input_token_cost": 1,
    "cache_creation_input_token_cost_above_200k_tokens": 1,
    "cache_read_input_token_cost_above_200k_tokens": 1,
    "cache_read_input_token_cost_priority": 1,
    "cache_read_input_image_token_cost": 1,
    "cache_creation_input_audio_token_cost": 1,
    "input_cost_per_image": 1,
    "output_cost_per_image": 1,
    "input_cost_per_pixel": 1,
    "output_cost_per_pixel": 1,
    "input_cost_per_image_token": 1,
    "output_cost_per_image_token": 1,
    "output_cost_per_image_low_quality": 1,
    "output_cost_per_image_medium_quality": 1,
    "output_cost_per_image_high_quality": 1,
    "output_cost_per_image_auto_quality": 1,
    "output_cost_per_image_premium_image": 1,
    "output_cost_per_image_above_512_and_512_pixels": 1,
    "output_cost_per_image_above_1024_and_1024_pixels": 1,
    "output_cost_per_image_above_2048_and_2048_pixels": 1,
    "output_cost_per_image_above_4096_and_4096_pixels": 1,
    "input_cost_per_audio_token": 1,
    "output_cost_per_audio_token": 1,
    "input_cost_per_audio_per_second": 1,
    "input_cost_per_second": 1,
    "input_cost_per_video_per_second": 1,
    "output_cost_per_video_per_second": 1,
    "output_cost_per_second": 1,
    "search_context_cost_per_query": 1,
    "code_interpreter_cost_per_session": 1
  }
}
'
{
  "message": "<string>",
  "pricing_override": {
    "id": "<string>",
    "name": "<string>",
    "scope_kind": "global",
    "virtual_key_id": "<string>",
    "provider_id": "<string>",
    "provider_key_id": "<string>",
    "match_type": "exact",
    "pattern": "<string>",
    "request_types": [
      "chat_completion"
    ],
    "pricing_patch": "<string>",
    "patch": {
      "input_cost_per_token": 1,
      "output_cost_per_token": 1,
      "input_cost_per_token_batches": 1,
      "output_cost_per_token_batches": 1,
      "input_cost_per_token_priority": 1,
      "output_cost_per_token_priority": 1,
      "input_cost_per_character": 1,
      "input_cost_per_token_above_128k_tokens": 1,
      "output_cost_per_token_above_128k_tokens": 1,
      "input_cost_per_token_above_200k_tokens": 1,
      "output_cost_per_token_above_200k_tokens": 1,
      "cache_creation_input_token_cost": 1,
      "cache_read_input_token_cost": 1,
      "cache_creation_input_token_cost_above_200k_tokens": 1,
      "cache_read_input_token_cost_above_200k_tokens": 1,
      "cache_read_input_token_cost_priority": 1,
      "cache_read_input_image_token_cost": 1,
      "cache_creation_input_audio_token_cost": 1,
      "input_cost_per_image": 1,
      "output_cost_per_image": 1,
      "input_cost_per_pixel": 1,
      "output_cost_per_pixel": 1,
      "input_cost_per_image_token": 1,
      "output_cost_per_image_token": 1,
      "output_cost_per_image_low_quality": 1,
      "output_cost_per_image_medium_quality": 1,
      "output_cost_per_image_high_quality": 1,
      "output_cost_per_image_auto_quality": 1,
      "output_cost_per_image_premium_image": 1,
      "output_cost_per_image_above_512_and_512_pixels": 1,
      "output_cost_per_image_above_1024_and_1024_pixels": 1,
      "output_cost_per_image_above_2048_and_2048_pixels": 1,
      "output_cost_per_image_above_4096_and_4096_pixels": 1,
      "input_cost_per_audio_token": 1,
      "output_cost_per_audio_token": 1,
      "input_cost_per_audio_per_second": 1,
      "input_cost_per_second": 1,
      "input_cost_per_video_per_second": 1,
      "output_cost_per_video_per_second": 1,
      "output_cost_per_second": 1,
      "search_context_cost_per_query": 1,
      "code_interpreter_cost_per_session": 1
    },
    "config_hash": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z"
  }
}

Body

application/json

Request body for creating a pricing override.

​
name
string
required

Human-readable label

​
scope_kind
enum<string>
required
Available options:
global,
provider,
provider_key,
virtual_key,
virtual_key_provider,
virtual_key_provider_key
​
match_type
enum<string>
required
Available options:
exact,
wildcard
​
pattern
string
required

Model name or wildcard prefix ending with * (e.g. "claude-3*")

​
request_types
enum<string>[]
required

Request types this override applies to. At least one value is required.

Minimum array length: 1

Request type for pricing override filtering. Stream variants are treated identically to their base type — specifying chat_completion covers both streaming and non-streaming chat requests.

Available options:
chat_completion,
text_completion,
responses,
embedding,
rerank,
speech,
transcription,
image_generation,
image_variation,
image_edit,
video_generation,
video_remix
​
virtual_key_id
string

Required for virtual_key* scopes

​
provider_id
string

Required for provider and virtual_key_provider scopes

​
provider_key_id
string

Required for provider_key and virtual_key_provider_key scopes

​
patch
object

Pricing fields to override. Only non-zero/non-null fields are applied. All values are cost per unit in USD.

Response

Pricing override created successfully

​
message
string
​
pricing_override
object

A pricing override that applies custom rates to matching requests.