OXoxlo
admin

Update Foundry Model

Update an existing foundry model configuration. Only provided fields will be updated.

put/admin/foundry-models/{model_id}

Request

  • Base URL
    https://api.oxlo.ai (the document declares no server; this is the origin it was published from)
  • URL
    https://api.oxlo.ai/admin/foundry-models/{model_id}
  • Auth
    HTTP bearer

Path parameters

model_idstring required

Request body

namestring nullable
target_modelstring nullable
providerstring nullable
query_methodstring nullable
context_lengthinteger nullable
quantizationstring nullable
gpu_requirementstring nullable
tierstring nullable
owned_bystring nullable
coming_soonboolean nullable
tagsstring[] nullable
sizestring nullable
categorystring nullable
descriptionstring nullable
rate_limit_requestsinteger nullable
rate_limit_tokensinteger nullable
rate_limit_window_secondsinteger nullable
fallback_to_next_endpointboolean nullable
testable_in_playgroundboolean nullable
is_activeboolean nullable
query_handlerstring nullable
endpoint_configobject nullable
use_foundry_endpointsboolean nullable

Response

Successful Response

namestring required

Display name for the model

target_modelstring required

Target model name for API calls

providerstring required

Provider: 'azure', 't4'

query_methodstring required

Query method: 'openai_chat', 'rest_flux-2-pro', etc.

context_lengthinteger

Context window length (0 for non-LLM)

quantizationstring nullable

Quantization: 'fp16', 'Q8_0', etc.

gpu_requirementstring nullable

GPU requirement: 'oxlo', 'A100', 'T4'

tierstring

Access tier: 'free', 'pro', 'premium'

owned_bystring

Owner: 'oxlo', 'worker-local'

coming_soonboolean

Whether the model is not yet available

tagsstring[] nullable

Tags for categorization

sizestring nullable

Model size: '70B', 'unknown'

categorystring

Category: 'chat', 'image', 'audio', etc.

descriptionstring nullable

Description for UI/docs

rate_limit_requestsinteger nullable

Rate limit: requests per window

rate_limit_tokensinteger nullable

Rate limit: tokens per window

rate_limit_window_secondsinteger nullable

Rate limit window in seconds

fallback_to_next_endpointboolean

Try next endpoint on rate limit

testable_in_playgroundboolean

Available in playground UI

is_activeboolean

Whether model is active and loaded

query_handlerstring nullable

Handler function name: 'openai_chat', 'flux_image', 'anthropic_messages', 'rest_generic'

endpoint_configobject nullable

Flexible endpoint configuration with endpoints, path, auth_type, timeout, etc.

use_foundry_endpointsboolean

If true, use Foundry endpoint rotation; if false, use endpoint_config.endpoints

idstring required
created_atstring date-time required
updated_atstring date-time required

Changes

No recorded changes to this operation across all 1 revision of this API.