Skip to main content
Glama

Start a Replicate fine-tune / training run

replicate_create_training

Kick off a fine-tuning run on a trainable base model with your dataset and hyperparameters. Returns a training ID for status polling.

Instructions

Kick off a fine-tuning (training) run on a trainable base model — e.g. a Flux LoRA trainer — with your dataset and hyperparameters. Returns immediately with a training ID; poll it with replicate_get_training.

Args:

  • model: BASE trainer "owner/name" (or "owner/name:version" to pin the trainer version inline). e.g. "ostris/flux-dev-lora-trainer".

  • version (optional): trainer version id. Required unless pinned inline on model.

  • destination: "owner/name" the trained weights are pushed to. The destination model must already exist on your account.

  • input: training inputs as a JSON object (dataset URL + hyperparameters). Call replicate_get_model_schema on the trainer to see its exact inputs.

Returns structuredContent: TrainingSummary { id, status, model, version, destination, created_at, completed_at, output_version, error }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputNoTraining inputs as a JSON object (dataset URL + hyperparameters). The exact keys depend on the trainer — call replicate_get_model_schema on the trainer model to see them.
modelYesThe BASE trainer model as "owner/name" (or "owner/name:version" to pin the trainer version inline). Example: "ostris/flux-dev-lora-trainer".
versionNoTrainer version id. Required unless you pinned it inline on `model` as "owner/name:version".
destinationYesWhere the trained weights are pushed, as "owner/name". The destination model must already exist on your account.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=false, openWorldHint=true, idempotentHint=false. The description adds value by explaining the asynchronous behavior (returns immediately with training ID) and the need to poll. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a concise paragraph followed by a bulleted list of arguments. It is front-loaded with the purpose and every sentence is necessary and informative, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description specifies the return type (TrainingSummary) with fields. It covers async behavior, prerequisites, and links to relevant tools for polling and schema introspection, making it fully informative for a training start tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and all parameters have descriptions. The description adds extra context with examples, inline version pinning, and a cross-reference to replicate_get_model_schema for the input object, which goes beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Kick off') and clearly identifies the resource (fine-tuning/training run on a trainable base model). It includes an example and distinguishes from sibling tools like replicate_get_training (polling) and replicate_run_model (inference).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly mentions polling with replicate_get_training and states a prerequisite (destination must exist). However, it does not explicitly say when to use this tool versus alternatives like replicate_run_model, though the context makes it clear it's for training, not inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sena-labs/replicate-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server