{ "opencollection": "1.0.0", "info": { "name": "Predibase API", "version": "2.0" }, "request": { "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "items": [ { "info": { "name": "Inference", "type": "folder" }, "items": [ { "info": { "name": "OpenAI-compatible chat completion.", "type": "http" }, "http": { "method": "POST", "url": "https://serving.app.predibase.com/{{tenant}}/deployments/v2/llms/{{model}}/v1/chat/completions", "body": { "type": "json", "data": "{\n \"model\": \"\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}],\n \"max_tokens\": 100,\n \"stream\": false\n}" } }, "docs": "Creates an OpenAI-compatible chat completion against the named deployment. Set model to an adapter ID to serve a fine-tuned LoRA. Set stream to true for SSE." }, { "info": { "name": "OpenAI-compatible text completion.", "type": "http" }, "http": { "method": "POST", "url": "https://serving.app.predibase.com/{{tenant}}/deployments/v2/llms/{{model}}/v1/completions", "body": { "type": "json", "data": "{\n \"model\": \"\",\n \"prompt\": \"How many helicopters can a human eat in one sitting?\",\n \"max_tokens\": 100\n}" } }, "docs": "Creates an OpenAI-compatible text completion against the named deployment." }, { "info": { "name": "Native text generation.", "type": "http" }, "http": { "method": "POST", "url": "https://serving.app.predibase.com/{{tenant}}/deployments/v2/llms/{{model}}/generate", "body": { "type": "json", "data": "{\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}" } }, "docs": "Generates text from a deployed model, optionally applying a LoRA adapter via adapter_id and adapter_source (pbase, hub, or s3)." }, { "info": { "name": "Native streaming text generation.", "type": "http" }, "http": { "method": "POST", "url": "https://serving.app.predibase.com/{{tenant}}/deployments/v2/llms/{{model}}/generate_stream", "body": { "type": "json", "data": "{\n \"inputs\": \"What is your name?\",\n \"parameters\": {\n \"max_new_tokens\": 100\n }\n}" } }, "docs": "Streams generated tokens from a deployed model as Server-Sent Events." } ] }, { "info": { "name": "Fine-Tuning", "type": "folder" }, "items": [ { "info": { "name": "Create a fine-tuning job.", "type": "http" }, "http": { "method": "POST", "url": "https://api.app.predibase.com/v2/finetuning/jobs", "body": { "type": "json", "data": "{\n \"base_model\": \"qwen3-8b\",\n \"dataset\": \"my-dataset\",\n \"repo\": \"my-repo\",\n \"adapter_type\": \"lora\",\n \"task\": \"sft\"\n}" } }, "docs": "Starts a supervised (sft) or reinforcement (grpo) fine-tuning job that trains a LoRA / Turbo LoRA adapter." }, { "info": { "name": "List fine-tuning jobs.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/finetuning/jobs" }, "docs": "Lists fine-tuning jobs." }, { "info": { "name": "Get a fine-tuning job.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/finetuning/jobs/{{jobId}}" }, "docs": "Gets a fine-tuning job." }, { "info": { "name": "Cancel a fine-tuning job.", "type": "http" }, "http": { "method": "POST", "url": "https://api.app.predibase.com/v2/finetuning/jobs/{{jobId}}/cancel" }, "docs": "Cancels a fine-tuning job." } ] }, { "info": { "name": "Adapters", "type": "folder" }, "items": [ { "info": { "name": "Create an adapter repository.", "type": "http" }, "http": { "method": "POST", "url": "https://api.app.predibase.com/v2/repos", "body": { "type": "json", "data": "{\n \"name\": \"my-repo\",\n \"description\": \"My adapter repository\"\n}" } }, "docs": "Creates an adapter repository." }, { "info": { "name": "List adapter repositories.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/repos" }, "docs": "Lists adapter repositories." }, { "info": { "name": "Get an adapter repository.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/repos/{{repoName}}" }, "docs": "Gets an adapter repository and its versions." }, { "info": { "name": "Delete an adapter repository.", "type": "http" }, "http": { "method": "DELETE", "url": "https://api.app.predibase.com/v2/repos/{{repoName}}" }, "docs": "Deletes an adapter repository." } ] }, { "info": { "name": "Deployments", "type": "folder" }, "items": [ { "info": { "name": "Create a dedicated deployment.", "type": "http" }, "http": { "method": "POST", "url": "https://api.app.predibase.com/v2/deployments", "body": { "type": "json", "data": "{\n \"name\": \"my-qwen3-8b\",\n \"base_model\": \"qwen3-8b\",\n \"accelerator\": \"a10_24gb\",\n \"min_replicas\": 0,\n \"max_replicas\": 1\n}" } }, "docs": "Creates a dedicated or private serverless deployment of a base model on a GPU accelerator with LoRA serving enabled." }, { "info": { "name": "List deployments.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/deployments" }, "docs": "Lists deployments." }, { "info": { "name": "Get a deployment.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/deployments/{{deploymentName}}" }, "docs": "Gets a deployment." }, { "info": { "name": "Delete a deployment.", "type": "http" }, "http": { "method": "DELETE", "url": "https://api.app.predibase.com/v2/deployments/{{deploymentName}}" }, "docs": "Deletes a deployment." } ] }, { "info": { "name": "Datasets", "type": "folder" }, "items": [ { "info": { "name": "Connect or upload a dataset.", "type": "http" }, "http": { "method": "POST", "url": "https://api.app.predibase.com/v2/datasets", "body": { "type": "json", "data": "{\n \"name\": \"my-dataset\",\n \"source\": \"file\"\n}" } }, "docs": "Connects or uploads a dataset for use in fine-tuning jobs." }, { "info": { "name": "List datasets.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/datasets" }, "docs": "Lists datasets." }, { "info": { "name": "Get a dataset.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/datasets/{{datasetName}}" }, "docs": "Gets a dataset." } ] }, { "info": { "name": "Models", "type": "folder" }, "items": [ { "info": { "name": "List supported base models.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/models" }, "docs": "Lists open-source base models supported for fine-tuning and serving." } ] }, { "info": { "name": "Batch Inference", "type": "folder" }, "items": [ { "info": { "name": "Create a batch inference job.", "type": "http" }, "http": { "method": "POST", "url": "https://api.app.predibase.com/v2/batch-inference/jobs", "body": { "type": "json", "data": "{\n \"base_model\": \"qwen3-8b\",\n \"dataset\": \"my-input-dataset\",\n \"output\": \"my-output\"\n}" } }, "docs": "Launches an asynchronous batch inference job with optional per-row adapter selection." }, { "info": { "name": "List batch inference jobs.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/batch-inference/jobs" }, "docs": "Lists batch inference jobs." }, { "info": { "name": "Get a batch inference job.", "type": "http" }, "http": { "method": "GET", "url": "https://api.app.predibase.com/v2/batch-inference/jobs/{{jobId}}" }, "docs": "Gets a batch inference job." } ] } ] }