{ "info": { "name": "Predibase API", "description": "Predibase inference (serving) and control-plane API. Inference is OpenAI-compatible plus native generate endpoints under https://serving.app.predibase.com/{tenant}/deployments/v2/llms/{model}; fine-tuning, adapters, deployments, datasets, models, and batch inference under https://api.app.predibase.com/v2. Authenticate with a Predibase API token as a Bearer token.", "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json" }, "auth": { "type": "bearer", "bearer": [ { "key": "token", "value": "{{bearerToken}}", "type": "string" } ] }, "variable": [ { "key": "servingUrl", "value": "https://serving.app.predibase.com/{{tenant}}/deployments/v2/llms/{{model}}" }, { "key": "controlUrl", "value": "https://api.app.predibase.com/v2" }, { "key": "tenant", "value": "TENANT_ID" }, { "key": "model", "value": "DEPLOYMENT_NAME" } ], "item": [ { "name": "Inference", "item": [ { "name": "OpenAI-compatible chat completion.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{servingUrl}}/v1/chat/completions", "host": [ "{{servingUrl}}" ], "path": [ "v1", "chat", "completions" ] }, "body": { "mode": "raw", "raw": "{\n \"model\": \"\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}],\n \"max_tokens\": 100,\n \"stream\": false\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "OpenAI-compatible text completion.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{servingUrl}}/v1/completions", "host": [ "{{servingUrl}}" ], "path": [ "v1", "completions" ] }, "body": { "mode": "raw", "raw": "{\n \"model\": \"\",\n \"prompt\": \"How many helicopters can a human eat in one sitting?\",\n \"max_tokens\": 100\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "Native text generation.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{servingUrl}}/generate", "host": [ "{{servingUrl}}" ], "path": [ "generate" ] }, "body": { "mode": "raw", "raw": "{\n \"inputs\": \"What is your name?\",\n \"parameters\": {\n \"max_new_tokens\": 100,\n \"adapter_id\": \"my-repo/1\",\n \"adapter_source\": \"pbase\"\n }\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "Native streaming text generation.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{servingUrl}}/generate_stream", "host": [ "{{servingUrl}}" ], "path": [ "generate_stream" ] }, "body": { "mode": "raw", "raw": "{\n \"inputs\": \"What is your name?\",\n \"parameters\": {\n \"max_new_tokens\": 100\n }\n}", "options": { "raw": { "language": "json" } } } } } ] }, { "name": "Fine-Tuning", "item": [ { "name": "Create a fine-tuning job.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{controlUrl}}/finetuning/jobs", "host": [ "{{controlUrl}}" ], "path": [ "finetuning", "jobs" ] }, "body": { "mode": "raw", "raw": "{\n \"base_model\": \"qwen3-8b\",\n \"dataset\": \"my-dataset\",\n \"repo\": \"my-repo\",\n \"adapter_type\": \"lora\",\n \"task\": \"sft\"\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "List fine-tuning jobs.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/finetuning/jobs", "host": [ "{{controlUrl}}" ], "path": [ "finetuning", "jobs" ] } } }, { "name": "Get a fine-tuning job.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/finetuning/jobs/{{jobId}}", "host": [ "{{controlUrl}}" ], "path": [ "finetuning", "jobs", "{{jobId}}" ] } } }, { "name": "Cancel a fine-tuning job.", "request": { "method": "POST", "header": [], "url": { "raw": "{{controlUrl}}/finetuning/jobs/{{jobId}}/cancel", "host": [ "{{controlUrl}}" ], "path": [ "finetuning", "jobs", "{{jobId}}", "cancel" ] } } } ] }, { "name": "Adapters", "item": [ { "name": "Create an adapter repository.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{controlUrl}}/repos", "host": [ "{{controlUrl}}" ], "path": [ "repos" ] }, "body": { "mode": "raw", "raw": "{\n \"name\": \"my-repo\",\n \"description\": \"My adapter repository\"\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "List adapter repositories.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/repos", "host": [ "{{controlUrl}}" ], "path": [ "repos" ] } } }, { "name": "Get an adapter repository.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/repos/{{repoName}}", "host": [ "{{controlUrl}}" ], "path": [ "repos", "{{repoName}}" ] } } }, { "name": "Delete an adapter repository.", "request": { "method": "DELETE", "header": [], "url": { "raw": "{{controlUrl}}/repos/{{repoName}}", "host": [ "{{controlUrl}}" ], "path": [ "repos", "{{repoName}}" ] } } } ] }, { "name": "Deployments", "item": [ { "name": "Create a dedicated deployment.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{controlUrl}}/deployments", "host": [ "{{controlUrl}}" ], "path": [ "deployments" ] }, "body": { "mode": "raw", "raw": "{\n \"name\": \"my-qwen3-8b\",\n \"base_model\": \"qwen3-8b\",\n \"accelerator\": \"a10_24gb\",\n \"min_replicas\": 0,\n \"max_replicas\": 1\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "List deployments.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/deployments", "host": [ "{{controlUrl}}" ], "path": [ "deployments" ] } } }, { "name": "Get a deployment.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/deployments/{{deploymentName}}", "host": [ "{{controlUrl}}" ], "path": [ "deployments", "{{deploymentName}}" ] } } }, { "name": "Delete a deployment.", "request": { "method": "DELETE", "header": [], "url": { "raw": "{{controlUrl}}/deployments/{{deploymentName}}", "host": [ "{{controlUrl}}" ], "path": [ "deployments", "{{deploymentName}}" ] } } } ] }, { "name": "Datasets", "item": [ { "name": "Connect or upload a dataset.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{controlUrl}}/datasets", "host": [ "{{controlUrl}}" ], "path": [ "datasets" ] }, "body": { "mode": "raw", "raw": "{\n \"name\": \"my-dataset\",\n \"source\": \"file\"\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "List datasets.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/datasets", "host": [ "{{controlUrl}}" ], "path": [ "datasets" ] } } }, { "name": "Get a dataset.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/datasets/{{datasetName}}", "host": [ "{{controlUrl}}" ], "path": [ "datasets", "{{datasetName}}" ] } } } ] }, { "name": "Models", "item": [ { "name": "List supported base models.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/models", "host": [ "{{controlUrl}}" ], "path": [ "models" ] } } } ] }, { "name": "Batch Inference", "item": [ { "name": "Create a batch inference job.", "request": { "method": "POST", "header": [ { "key": "Content-Type", "value": "application/json" } ], "url": { "raw": "{{controlUrl}}/batch-inference/jobs", "host": [ "{{controlUrl}}" ], "path": [ "batch-inference", "jobs" ] }, "body": { "mode": "raw", "raw": "{\n \"base_model\": \"qwen3-8b\",\n \"dataset\": \"my-input-dataset\",\n \"output\": \"my-output\"\n}", "options": { "raw": { "language": "json" } } } } }, { "name": "List batch inference jobs.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/batch-inference/jobs", "host": [ "{{controlUrl}}" ], "path": [ "batch-inference", "jobs" ] } } }, { "name": "Get a batch inference job.", "request": { "method": "GET", "header": [], "url": { "raw": "{{controlUrl}}/batch-inference/jobs/{{jobId}}", "host": [ "{{controlUrl}}" ], "path": [ "batch-inference", "jobs", "{{jobId}}" ] } } } ] } ] }