digitalocean-openapi-agent/skills/dedicated-inferences/SKILL.md

name, description

name	description
dedicated-inferences-routes	Handle 13 OpenAPI operation(s) under /v2/dedicated-inferences for the dedicated inferences route group.

dedicated inferences API Routes

Handle 13 OpenAPI operation(s) under /v2/dedicated-inferences for the dedicated inferences route group.

Use the generated operation tools to make real API calls. Do not invent API responses. If a tool reports missing setup, return the exact setup field name to the caller. For write, update, or delete operations, state the intended action before calling the tool.

Operations

get_v2_dedicated_inferences_dedicated_inference_id

• Operation ID: get_v2_dedicated_inferences_dedicated_inference_id
• Route: GET /v2/dedicated-inferences/{dedicated_inference_id}
• Mode: READ
• Summary: get_/v2/dedicated-inferences/{dedicated_inference_id}
• Parameters:
  • dedicated_inference_id in path required

patch_v2_dedicated_inferences_dedicated_inference_id

• Operation ID: patch_v2_dedicated_inferences_dedicated_inference_id
• Route: PATCH /v2/dedicated-inferences/{dedicated_inference_id}
• Mode: WRITE
• Summary: patch_/v2/dedicated-inferences/{dedicated_inference_id}
• Parameters:
  • dedicated_inference_id in path required

delete_v2_dedicated_inferences_dedicated_inference_id

• Operation ID: delete_v2_dedicated_inferences_dedicated_inference_id
• Route: DELETE /v2/dedicated-inferences/{dedicated_inference_id}
• Mode: WRITE
• Summary: delete_/v2/dedicated-inferences/{dedicated_inference_id}
• Parameters:
  • dedicated_inference_id in path required

get_v2_dedicated_inferences

• Operation ID: get_v2_dedicated_inferences
• Route: GET /v2/dedicated-inferences
• Mode: READ
• Summary: get_/v2/dedicated-inferences

post_v2_dedicated_inferences

• Operation ID: post_v2_dedicated_inferences
• Route: POST /v2/dedicated-inferences
• Mode: WRITE
• Summary: post_/v2/dedicated-inferences

get_v2_dedicated_inferences_dedicated_inference_id_accelerators

• Operation ID: get_v2_dedicated_inferences_dedicated_inference_id_accelerators
• Route: GET /v2/dedicated-inferences/{dedicated_inference_id}/accelerators
• Mode: READ
• Summary: get_/v2/dedicated-inferences/{dedicated_inference_id}/accelerators
• Parameters:
  • dedicated_inference_id in path required

get_v2_dedicated_inferences_dedicated_inference_id_accelerators_accelerator_id

• Operation ID: get_v2_dedicated_inferences_dedicated_inference_id_accelerators_accelerator_id
• Route: GET /v2/dedicated-inferences/{dedicated_inference_id}/accelerators/{accelerator_id}
• Mode: READ
• Summary: get_/v2/dedicated-inferences/{dedicated_inference_id}/accelerators/{accelerator_id}
• Parameters:
  • dedicated_inference_id in path required
  • accelerator_id in path required

get_v2_dedicated_inferences_dedicated_inference_id_ca

• Operation ID: get_v2_dedicated_inferences_dedicated_inference_id_ca
• Route: GET /v2/dedicated-inferences/{dedicated_inference_id}/ca
• Mode: READ
• Summary: get_/v2/dedicated-inferences/{dedicated_inference_id}/ca
• Parameters:
  • dedicated_inference_id in path required

get_v2_dedicated_inferences_dedicated_inference_id_tokens

• Operation ID: get_v2_dedicated_inferences_dedicated_inference_id_tokens
• Route: GET /v2/dedicated-inferences/{dedicated_inference_id}/tokens
• Mode: READ
• Summary: get_/v2/dedicated-inferences/{dedicated_inference_id}/tokens
• Parameters:
  • dedicated_inference_id in path required

post_v2_dedicated_inferences_dedicated_inference_id_tokens

• Operation ID: post_v2_dedicated_inferences_dedicated_inference_id_tokens
• Route: POST /v2/dedicated-inferences/{dedicated_inference_id}/tokens
• Mode: WRITE
• Summary: post_/v2/dedicated-inferences/{dedicated_inference_id}/tokens
• Parameters:
  • dedicated_inference_id in path required

delete_v2_dedicated_inferences_dedicated_inference_id_tokens_token_id

• Operation ID: delete_v2_dedicated_inferences_dedicated_inference_id_tokens_token_id
• Route: DELETE /v2/dedicated-inferences/{dedicated_inference_id}/tokens/{token_id}
• Mode: WRITE
• Summary: delete_/v2/dedicated-inferences/{dedicated_inference_id}/tokens/{token_id}
• Parameters:
  • dedicated_inference_id in path required
  • token_id in path required

get_v2_dedicated_inferences_sizes

• Operation ID: get_v2_dedicated_inferences_sizes
• Route: GET /v2/dedicated-inferences/sizes
• Mode: READ
• Summary: get_/v2/dedicated-inferences/sizes

get_v2_dedicated_inferences_gpu_model_config

• Operation ID: get_v2_dedicated_inferences_gpu_model_config
• Route: GET /v2/dedicated-inferences/gpu-model-config
• Mode: READ
• Summary: get_/v2/dedicated-inferences/gpu-model-config