Connect Valar

Valar is an inference provider with OpenAI- and Anthropic-compatible APIs, and ValarCode, a router for coding agents such as Claude Code, Cursor, and Codex. The Valar integration imports your organization's daily spend and token usage into Cloud Intelligence™ so you can analyze it in Cloud Analytics by model and API key.

Prerequisites

• A Valar organization in which you can create API keys.

• A DoiT account with the Billing Profiles Admin permission.

Required credentials

Field	Description	Where to find it
Organization name	A short name for the Valar organization, used to label the connection. Lowercase letters, digits, and hyphens only	Your choice
API key	A Valar API key of either type, Inference or Coding	Valar dashboard > API Keys

Use a dedicated key

Valar does not offer a read-only key: every API key that can read usage can also run inference. Create a key only for this connection, give it an expiry, and replace it in DoiT before it expires. DoiT only reads usage and never sends inference requests.

Connect each organization once

Valar reports usage for the whole organization, whichever workspace owns the key. Connecting the same organization twice duplicates its cost.

Create an API key

1. Sign in to the Valar dashboard and go to API Keys.

2. Select Create key.

3. Choose a key type, enter a descriptive name, for example doit-cloud-intelligence, and choose when the key expires.

4. Select Create and copy the key.

   Caution

   The key is only shown once. Make sure to copy it before leaving the page.

Connect your Valar organization

1. Sign in to Cloud Intelligence, select Data ingestion and integrations > Integrations from the top navigation mega menu.

2. Search for Valar in the integrations catalog.

3. Select Connect + on the integration card.

4. Enter the Organization name and paste the API key.

5. Select Test connection to verify DoiT can read your Valar usage.

6. If the test is successful, select Save to complete the setup.

   If the test fails or you need further assistance, please open an expert inquiry.

Note

Upon initial connection, DoiT imports up to 90 days of historical Valar usage. The import process can take a few hours. You'll receive an email when the data is available in Cloud Analytics.

What is imported

• Inference and ValarCode spend billed by Valar, per day, API key, and model. ValarCode requests are reported under the model that served them, which can differ from the model the coding agent asked for.

• Token usage: input, cached input, and output tokens.

The following are not imported:

• Bring your own key (BYOK) requests. Valar does not bill them; your model provider does. Connect that provider to DoiT to see the spend.

• Workload tags, per-engineer ValarCode usage, and ValarCode savings.

• Taxes, credits, and invoices, which Valar's usage API does not report.

Note

Valar reports spend in whole cents for each model, so a model that cost less than half a cent on a day shows zero cost, and the total in Cloud Analytics can differ from the Valar dashboard by a fraction of a cent per model.

Data refresh

DoiT refreshes your Valar usage every 6 hours. Valar reports usage by UTC day, and a day is imported once it has closed.

Reporting dimensions

Once connected, Valar data maps to the following standard Cloud Analytics dimensions:

Cloud Analytics dimension	Valar value	Example
Provider	Valar	Valar
Billing Account	Organization name	my-org
Project	API key ID	key_0000000000000001
Service	Model inference	Model Inference
SKU	Model that served the requests	moonshotai/Kimi-K3

In addition to standard dimensions, the following labels are available:

Label	Description
Model	The model that served the requests
Model provider	The developer of the model, for example DeepSeek or Moonshot AI, when Valar's model ID identifies it
API key	The name of the API key that made the requests
API key ID	The ID of the API key that made the requests
Organization	The Valar organization the charge belongs to

Usage amounts are measured in tokens. Input tokens (including cached input), cached input tokens, and output tokens are available as the token.usage.input, token.usage.cache_read, and token.usage.output metrics.

Note

Valar costs appear in the GenAI Intelligence dashboard alongside other supported GenAI providers.

Delete your Valar connection

1. Sign in to Cloud Intelligence, select Data ingestion and integrations > Integrations from the top navigation mega menu.

2. Search for Valar in the integrations catalog.

3. Select Manage on the integration card.

4. Select the kebab menu (⋮) at the rightmost end of the organization you want to remove and select Delete.

5. Select Delete to confirm.