Claude Code

Use a Valkyrie-hosted model as Claude Code’s model.

Claude Code speaks the Anthropic Messages protocol, and Valkyrie serves your deployed model over that same protocol. Point Claude Code at your deployment by setting its Anthropic base URL and auth token. The base URL is your API host plus the deployment slug (deployment-{id}) or an alias. Claude Code appends /v1/messages itself.

# By deployment slug (deployment-{id})
export ANTHROPIC_BASE_URL="https://valkyrie-back.azumo.com/deployment-213"
# ...or by alias:
# export ANTHROPIC_BASE_URL="https://valkyrie-back.azumo.com/{account_slug}/{alias}"

export ANTHROPIC_AUTH_TOKEN="vk_dep_your_deployment_key"

claude

Valkyrie exposes /{deployment_slug}/v1/messages and /{deployment_slug}/v1/messages/count_tokens (and the alias equivalents). Use a deployment key (vk_dep_); it’s accepted as ANTHROPIC_AUTH_TOKEN or as the x-api-key header the Anthropic SDKs send. An alias gives you a stable base URL to bake into your shell profile.

A self-hosted open model is not Claude. Behavior, tool-use quality, and context limits depend entirely on the model you deployed. Size the deployment for the workload you expect from a coding agent.

---

Looking to let Claude Code operate Valkyrie (deploy models, read logs, manage jobs) rather than use one as its model? That’s the MCP server, see Set up the MCP server. The two integrations are independent and can be used together.