Claude Code helper-model request to custom base URL
Parent: Mac local LLMs: Agent clients, context and compaction · Published reference · snapshot 2026-10-05
↓ Facts as markdownall context files
ANTHROPIC_DEFAULT_HAIKU_MODEL sets what the haiku alias resolves to and is also the model used for background functionality; pointing it at the local model ID sends helper requests to the same served model.
These notes link each claim to its source. Some citations identify archived research reports that are no longer hosted on this site. A published reference means the content is available; it does not certify independent review or accuracy.Read the editorial policy and follow the sources before relying on a claim.
Facts
- ANTHROPIC_DEFAULT_HAIKU_MODEL sets what the haiku alias resolves to and is also the model used for background functionality; pointing it at the local model ID sends helper requests to the same served model. [source]
- ANTHROPIC_SMALL_FAST_MODEL is the deprecated older name for the same Haiku-class background model. [source]
- Documented background work, even when idle: summarizing previous conversations for claude --resume; the costs page says it uses a small number of tokens. [source]
- With prompt suggestions on, a short request goes to the session's own model after each response and reuses the conversation prompt cache, so it is a main-model request, not a helper-model one. [source]
- CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 turns off auto-updates, telemetry, error reporting, feedback and availability checks; the docs do not list helper-model calls among them. [source]
- ANTHROPIC_SMALL_FAST_MODEL is marked deprecated in the current env-vars page; ANTHROPIC_DEFAULT_HAIKU_MODEL replaces it. [source]
- On a single-slot local server the helper request carries a different prefix (own system prompt, 27 tools) so it can evict the main session's cached prefix; this builds on the existing measurement. [inferred] [source]
- If the haiku alias is left at its default, a server that serves one model ID returns 404 for it (existing LM Studio report). [source]
- Whether a pinned local ID removes the helper request or only redirects it; not measured here. [source]
- Which helper requests (title, summary, command-prefix check) fire per session and whether any can be switched off individually. [source]
- ANTHROPIC_DEFAULT_HAIKU_MODEL sets the haiku alias target and is also used for background functionality [source]
- ANTHROPIC_SMALL_FAST_MODEL is deprecated and names the Haiku-class model for background tasks [source]
- Claude Code runs background jobs that summarize previous conversations for claude --resume, using a small number of tokens even when idle [source]
- Prompt suggestions send a short request to the session's own model and reuse its prompt cache [source]
- CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC disables updates, telemetry, error reporting and feedback traffic [source]
- Under an LLM gateway set through ANTHROPIC_BASE_URL, a listed model ID with no built-in picker row appears as its own row, and ANTHROPIC_DEFAULT_*_MODEL cannot redirect an allowed alias outside availableModels [source]
- Pinning ANTHROPIC_DEFAULT_HAIKU_MODEL to the served local model ID is the documented way to keep helper requests on a model the server has [source]
Children
- No children recorded.