{ "item": [ { "id": "c1a0e001-0001-4001-a001-000000000001", "name": "Chat", "description": { "content": "OpenAI-compatible chat completions on CentML serverless endpoints.", "type": "text/plain" }, "item": [ { "id": "c1a0e001-0001-4001-a001-000000000101", "name": "Creates a model response for the given chat conversation.", "request": { "name": "Creates a model response for the given chat conversation.", "description": { "content": "OpenAI-compatible chat completions. Set stream=true for SSE.", "type": "text/plain" }, "url": { "path": [ "openai", "v1", "chat", "completions" ], "host": [ "{{baseUrl}}" ], "query": [], "variable": [] }, "header": [ { "key": "Content-Type", "value": "application/json" } ], "method": "POST", "auth": null, "body": { "mode": "raw", "raw": "{\n \"model\": \"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What is CentML's value prop?\"\n }\n ],\n \"max_tokens\": 2000,\n \"temperature\": 0.7,\n \"top_p\": 1,\n \"n\": 1,\n \"stream\": false,\n \"frequency_penalty\": 0,\n \"presence_penalty\": 0.5,\n \"stop\": []\n}", "options": { "raw": { "language": "json" } } } }, "response": [], "event": [], "protocolProfileBehavior": { "disableBodyPruning": true } } ], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000002", "name": "Completions", "description": { "content": "OpenAI-compatible text completions on CentML serverless endpoints.", "type": "text/plain" }, "item": [ { "id": "c1a0e001-0001-4001-a001-000000000201", "name": "Creates a completion for the provided prompt.", "request": { "name": "Creates a completion for the provided prompt.", "description": {}, "url": { "path": [ "openai", "v1", "completions" ], "host": [ "{{baseUrl}}" ], "query": [], "variable": [] }, "header": [ { "key": "Content-Type", "value": "application/json" } ], "method": "POST", "auth": null, "body": { "mode": "raw", "raw": "{\n \"model\": \"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8\",\n \"prompt\": \"CentML optimizes\",\n \"max_tokens\": 256,\n \"temperature\": 0.7,\n \"stream\": false\n}", "options": { "raw": { "language": "json" } } } }, "response": [], "event": [], "protocolProfileBehavior": { "disableBodyPruning": true } } ], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000003", "name": "Models", "description": { "content": "List and retrieve models available on CentML serverless endpoints.", "type": "text/plain" }, "item": [ { "id": "c1a0e001-0001-4001-a001-000000000301", "name": "Lists the models available on CentML serverless endpoints.", "request": { "name": "Lists the models available on CentML serverless endpoints.", "description": {}, "url": { "path": [ "openai", "v1", "models" ], "host": [ "{{baseUrl}}" ], "query": [], "variable": [] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000302", "name": "Retrieves a model instance.", "request": { "name": "Retrieves a model instance.", "description": {}, "url": { "path": [ "openai", "v1", "models", ":model" ], "host": [ "{{baseUrl}}" ], "query": [], "variable": [ { "key": "model", "value": "", "description": "The ID of the model to retrieve." } ] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] } ], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000004", "name": "Deployments", "description": { "content": "CentML platform (control-plane) API for managing dedicated deployments.", "type": "text/plain" }, "item": [ { "id": "c1a0e001-0001-4001-a001-000000000401", "name": "Lists all deployments for the account.", "request": { "name": "Lists all deployments for the account.", "description": {}, "url": { "path": [ "deployments" ], "host": [ "{{platformBaseUrl}}" ], "query": [], "variable": [] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000402", "name": "Creates a dedicated inference deployment.", "request": { "name": "Creates a dedicated inference deployment.", "description": {}, "url": { "path": [ "deployments", "inference" ], "host": [ "{{platformBaseUrl}}" ], "query": [], "variable": [] }, "header": [ { "key": "Content-Type", "value": "application/json" } ], "method": "POST", "auth": null, "body": { "mode": "raw", "raw": "{\n \"name\": \"my-inference\",\n \"cluster_id\": 1,\n \"hardware_instance_id\": 1,\n \"model\": \"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8\",\n \"min_replicas\": 1,\n \"max_replicas\": 3\n}", "options": { "raw": { "language": "json" } } } }, "response": [], "event": [], "protocolProfileBehavior": { "disableBodyPruning": true } }, { "id": "c1a0e001-0001-4001-a001-000000000403", "name": "Retrieves an inference deployment by ID.", "request": { "name": "Retrieves an inference deployment by ID.", "description": {}, "url": { "path": [ "deployments", "inference", ":deployment_id" ], "host": [ "{{platformBaseUrl}}" ], "query": [], "variable": [ { "key": "deployment_id", "value": "", "description": "The ID of the deployment to retrieve." } ] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000404", "name": "Gets the status of a deployment.", "request": { "name": "Gets the status of a deployment.", "description": {}, "url": { "path": [ "deployments", "status", ":deployment_id" ], "host": [ "{{platformBaseUrl}}" ], "query": [], "variable": [ { "key": "deployment_id", "value": "" } ] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000405", "name": "Returns logs for a deployment.", "request": { "name": "Returns logs for a deployment.", "description": {}, "url": { "path": [ "deployments", "logs", ":deployment_id" ], "host": [ "{{platformBaseUrl}}" ], "query": [], "variable": [ { "key": "deployment_id", "value": "" } ] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] } ], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000005", "name": "Clusters", "description": { "content": "CentML platform (control-plane) API for clusters and capacity.", "type": "text/plain" }, "item": [ { "id": "c1a0e001-0001-4001-a001-000000000501", "name": "Lists the regional clusters available to the account.", "request": { "name": "Lists the regional clusters available to the account.", "description": {}, "url": { "path": [ "clusters" ], "host": [ "{{platformBaseUrl}}" ], "query": [], "variable": [] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] }, { "id": "c1a0e001-0001-4001-a001-000000000502", "name": "Lists available GPU capacity and hardware instances.", "request": { "name": "Lists available GPU capacity and hardware instances.", "description": {}, "url": { "path": [ "capacity" ], "host": [ "{{platformBaseUrl}}" ], "query": [], "variable": [] }, "header": [], "method": "GET", "auth": null }, "response": [], "event": [] } ], "event": [] } ], "event": [], "variable": [ { "type": "string", "value": "https://api.centml.com", "key": "baseUrl" }, { "type": "string", "value": "https://api.centml.com", "key": "platformBaseUrl" } ], "auth": { "type": "bearer", "bearer": [ { "key": "token", "value": "{{bearerToken}}" } ] }, "info": { "_postman_id": "c1a0e001-0001-4001-a001-000000000000", "name": "CentML API", "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json", "description": { "content": "CentML OpenAI-compatible serverless inference API (https://api.centml.com/openai/v1) and platform control-plane API for deployments and clusters (https://api.centml.com). Bearer API key auth.\n\nContact Support:\n URL: https://docs.centml.ai/resources/requesting_support", "type": "text/plain" } } }