A valid request URL is required to generate request examples{
"id": "<string>",
"name": "<string>",
"value": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"models": [
"<string>"
],
"blacklisted_models": [
"<string>"
],
"weight": 123,
"aliases": {},
"azure_key_config": {
"endpoint": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"api_version": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"client_id": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"client_secret": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"tenant_id": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"scopes": [
"<string>"
]
},
"vertex_key_config": {
"project_id": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"project_number": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"region": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"auth_credentials": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
}
},
"bedrock_key_config": {
"access_key": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"secret_key": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"session_token": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"region": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"arn": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"batch_s3_config": {
"buckets": [
{
"bucket_name": "<string>",
"prefix": "<string>",
"is_default": true
}
]
}
},
"vllm_key_config": {
"url": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"model_name": "<string>"
},
"ollama_key_config": {
"url": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
}
},
"sgl_key_config": {
"url": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
}
},
"replicate_key_config": {
"use_deployments_endpoint": true
},
"enabled": true,
"use_for_batch_api": true,
"config_hash": "<string>",
"status": "<string>",
"description": "<string>"
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "anthropic",
"model_requested": "<string>",
"request_type": "<string>",
"error_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "anthropic",
"model_requested": "<string>",
"request_type": "<string>",
"error_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "anthropic",
"model_requested": "<string>",
"request_type": "<string>",
"error_type": "<string>"
}
}Update a key for a provider
Updates an existing key. Send the full key object. Redacted values sent back unchanged are automatically preserved (the server merges them with the stored raw values).
A valid request URL is required to generate request examples{
"id": "<string>",
"name": "<string>",
"value": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"models": [
"<string>"
],
"blacklisted_models": [
"<string>"
],
"weight": 123,
"aliases": {},
"azure_key_config": {
"endpoint": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"api_version": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"client_id": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"client_secret": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"tenant_id": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"scopes": [
"<string>"
]
},
"vertex_key_config": {
"project_id": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"project_number": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"region": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"auth_credentials": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
}
},
"bedrock_key_config": {
"access_key": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"secret_key": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"session_token": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"region": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"arn": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"batch_s3_config": {
"buckets": [
{
"bucket_name": "<string>",
"prefix": "<string>",
"is_default": true
}
]
}
},
"vllm_key_config": {
"url": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
},
"model_name": "<string>"
},
"ollama_key_config": {
"url": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
}
},
"sgl_key_config": {
"url": {
"value": "<string>",
"ref": "<string>",
"type": "plain_text"
}
},
"replicate_key_config": {
"use_deployments_endpoint": true
},
"enabled": true,
"use_for_batch_api": true,
"config_hash": "<string>",
"status": "<string>",
"description": "<string>"
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "anthropic",
"model_requested": "<string>",
"request_type": "<string>",
"error_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "anthropic",
"model_requested": "<string>",
"request_type": "<string>",
"error_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "anthropic",
"model_requested": "<string>",
"request_type": "<string>",
"error_type": "<string>"
}
}| Permission | Granted via |
|---|---|
ModelProvider:Update | RBAC role or API key scope |
Authorizations
Management API authentication for /api/* endpoints. Use the Authorization header
with Bearer <token>, where <token> is one of:
- a Bifrost management API key,
- a dashboard session token issued by
POST /api/session/login, - base64 of
<admin-username>:<admin-password>(legacy equivalent ofBasicAuth).
Virtual keys (sk-bf-*) and the x-api-key header are not accepted on management APIs -
the sole exception is GET /api/governance/virtual-keys/quota, which is virtual-key-only.
Authentication alone is not sufficient in Bifrost Enterprise: each operation page shows a
Required Permissions table (Resource:Operation, for example Dashboard:View) above
its Authorizations section, and the caller's RBAC role or management API key scopes must
include what it lists, otherwise the request is rejected with 403 Forbidden.
A local admin — authenticated with the admin password, or any caller on a deployment with dashboard auth disabled — bypasses these checks and can call every management endpoint. See Required permissions for how permissions are derived and which endpoints are exempt.
Body
API key configuration
Unique identifier for the key
Name of the key
API key value (redacted in responses)
Show child attributes
Show child attributes
List of models this key can access (whitelist). ["*"] allows every model. An entry starting with regex: is an RE2 pattern matched case-insensitively against the whole model name; an empty pattern, regex:*, or a pattern that does not compile is rejected with 400. blacklisted_models wins over this list.
List of models this key cannot access (blacklist), which wins over models. ["*"] blocks every model. An entry starting with regex: is an RE2 pattern matched case-insensitively against the whole model name; an empty pattern, regex:*, or a pattern that does not compile is rejected with 400.
Weight for load balancing
Model alias mappings - maps a user-facing model name to a provider-specific identifier (deployment name, inference profile ID, fine-tuned model ID, etc.)
Show child attributes
Show child attributes
Azure-specific key configuration
Show child attributes
Show child attributes
Vertex-specific key configuration
Show child attributes
Show child attributes
AWS Bedrock-specific key configuration
Show child attributes
Show child attributes
VLLM-specific key configuration
Show child attributes
Show child attributes
Ollama-specific key configuration
Show child attributes
Show child attributes
SGLang-specific key configuration
Show child attributes
Show child attributes
Replicate-specific key configuration
Show child attributes
Show child attributes
Whether the key is active (defaults to true)
Whether this key can be used for batch API operations
Hash of config.json version, used for change detection
Status of key (e.g., success, list_models_failed)
Error or status description for the key
Response
Key updated successfully
API key configuration
Unique identifier for the key
Name of the key
API key value (redacted in responses)
Show child attributes
Show child attributes
List of models this key can access (whitelist). ["*"] allows every model. An entry starting with regex: is an RE2 pattern matched case-insensitively against the whole model name; an empty pattern, regex:*, or a pattern that does not compile is rejected with 400. blacklisted_models wins over this list.
List of models this key cannot access (blacklist), which wins over models. ["*"] blocks every model. An entry starting with regex: is an RE2 pattern matched case-insensitively against the whole model name; an empty pattern, regex:*, or a pattern that does not compile is rejected with 400.
Weight for load balancing
Model alias mappings - maps a user-facing model name to a provider-specific identifier (deployment name, inference profile ID, fine-tuned model ID, etc.)
Show child attributes
Show child attributes
Azure-specific key configuration
Show child attributes
Show child attributes
Vertex-specific key configuration
Show child attributes
Show child attributes
AWS Bedrock-specific key configuration
Show child attributes
Show child attributes
VLLM-specific key configuration
Show child attributes
Show child attributes
Ollama-specific key configuration
Show child attributes
Show child attributes
SGLang-specific key configuration
Show child attributes
Show child attributes
Replicate-specific key configuration
Show child attributes
Show child attributes
Whether the key is active (defaults to true)
Whether this key can be used for batch API operations
Hash of config.json version, used for change detection
Status of key (e.g., success, list_models_failed)
Error or status description for the key
Was this page helpful?