Projects and traffic - CoreWeave Docs

A project is the unit you optimize. It owns its data and experiments while giving the application one stable project to select. Each Model Distillation project is backed by exactly one Weights & Biases project, which stores its traces. This page shows you how to create a project, connect your application to the proxy with the project’s OpenAI-Project value, and confirm that the proxy records traces you can use as training data.

Create a project

To create a project, follow these steps:

From Projects, select Create or import a project.
Configure the following fields:
- W&B project: Select Create new to create a Weights & Biases project in the selected entity, or Import existing to connect a Weights & Biases project you already have. Importing doesn’t change the existing project’s data. A Weights & Biases project can back only one Model Distillation project per entity.
- Project alias: Identifies the project in Studio URLs and Management API paths. The UI suggests a name derived from the Weights & Biases project name. Use lowercase letters, digits, and hyphens, up to 64 characters. The project alias can differ from the Weights & Biases project name.
- Initial model: The model that serves version 1 while you collect traces and train alternatives.
Select Create project.

Every new project requires an initial model so it can route traffic as soon as its routing deployment is applied.

API: Create a project (PUT /projects/{alias})

The project alias is the alias path segment. Set project to the Weights & Biases project name and project_mode to create or import. Supply at least one routing target. Creation fails when targets is missing or empty.

curl --request PUT \
  --url "https://forge.coreweave.com/api/distillation/v1/projects/ticket-classifier" \
  --header "Authorization: Bearer $WANDB_API_KEY" \
  --header "Forge-Entity: your-team" \
  --header "Content-Type: application/json" \
  --data '{
    "project": "ticket-classifier",
    "project_mode": "create",
    "targets": [
      {"model_ref": "openai/gpt-5.6-sol", "weight": 1}
    ]
  }'

For the complete schema, see Create a Model Distillation project.

Connect the application

After you create the project, point your application at the proxy, which routes its traffic through the project and records it as traces. Use the following client and request configuration: Replace your-team/ticket-classifier with the OpenAI-Project value that Studio shows in the project header and on the project’s settings page. The value is the entity and the Weights & Biases project name, not the project alias:

client = OpenAI(
    base_url="https://proxy.training.coreweave.com/v1",
    api_key=os.environ["WANDB_API_KEY"],
    project="your-team/ticket-classifier",  # sent as OpenAI-Project
)

response = client.chat.completions.create(
    model="router",  # or "openai/gpt-5.5" to override the model
    messages=messages,
    metadata={"gen_ai.conversation.id": conversation_id},
)

The proxy forwards all normal Chat Completions fields, replaces router with the selected target’s provider model, and applies that target’s stored parameter overrides. Requests without forge.project_version use version 1. To pin another version, add "forge.project_version": "2" to metadata.

Verify useful traces

Before you collect a large dataset, confirm the following:

Successful calls appear in the project’s request chart.
Traffic share matches routing weights.
A stable gen_ai.conversation.id groups each conversation in the W&B Weave Agents view.
Tool definitions, response formats, and multi-turn messages appear in the recorded request.
Failed provider calls are visible for debugging but excluded from training data.

When these checks pass, the project records traces that can serve as training examples.

Send the complete message history on every call. Each trace becomes one self-contained training example representing the assistant response produced for that history.

​Create a project

​Connect the application

​Verify useful traces

Create a project

Connect the application

Verify useful traces