Answer: Call a model from a mod using `$.model.complete` to send your prompt on its own, or `$.model.fork({ prompt })` to send the current conversation with your prompt at the end. Pass `model` and `prompt` to `$.model.complete`, and optionally `system` for instructions. Status: Confirmed Entry: tool/claude-code/agents-and-automation/call-model-from-mod Revision: 2 Digest: sha256:367165c5454fb92f (changes whenever the content changes) Timeline: Created: 2026-11-13T03:05:11Z Last changed: 2026-11-20T12:23:33Z (max breakpoints per request: — → four) Last verified: 2026-11-20T12:23:33Z Next check: 2026-11-21T12:23:33Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of method for standalone prompt | $.model.complete | [1] | 2026-11-20 method for conversation fork | $.model.fork({ prompt }) | [1] | 2026-11-20 required parameters | model | [1] | 2026-11-20 optional system prompt parameter | system | [1] | 2026-11-20 minimum version for block arrays | v2.1.292 | [1] | 2026-11-20 cache TTL | five minutes | [1] | 2026-11-20 max breakpoints per request | four | [1] | 2026-11-20 Sources: [1] Anthropic. "Use the mods API". https://code.claude.com/docs/en/plugins/mods/api.md Role: primary. Accessed: 2026-11-20T12:23:33Z Quote: "`$.model.complete` sends your prompt on its own" (Supports: method for standalone prompt) Quote: "`$.model.fork({ prompt })` sends the current conversation with your prompt at the end" (Supports: method for conversation fork) Quote: "Pass `model` and `prompt` to `$.model.complete`." (Supports: required parameters) Quote: "also pass `system`, which becomes the system prompt" (Supports: optional system prompt parameter) Quote: "Arrays of blocks require Claude Code v2.1.292 or later." (Supports: minimum version for block arrays) Quote: "a cache entry lasts five minutes after its last use" (Supports: cache TTL) Quote: "the API accepts [up to four](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#when-to-use-multiple-breakpoints)" (Supports: max breakpoints per request) Published: 2026-11-20T10:36:06Z Snapshot SHA-256: ca14f630f768366693cc8185a9947d443c402745f351ddfdefa3cbaed2a7883c (captured 2026-11-19T12:18:56Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-19T12:18:57Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:23:33Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:23:33Z Last attempt: 2026-11-20T12:23:33Z Notes and limitations: Extracted automatically from a single official source (section "Call a model"). Related: https://latestn.com/tool/claude-code/agents-and-automation/capture-session-id How do I capture the session ID in Claude Code SDK? https://latestn.com/tool/claude-code/agents-and-automation/change-system-prompt-existing-session How do I change the system prompt of an existing Claude Code session? https://latestn.com/tool/claude-code/agents-and-automation/check-running-agent-work How do I check on work that Claude Code agents are running in the background? https://latestn.com/tool/claude-code/agents-and-automation/auto-format-after-edits How do I make Claude Code auto-format code after it edits files using hooks? https://latestn.com/tool/claude-code/agents-and-automation/available-hook-events What hook events are available in Claude Code? https://latestn.com/tool/claude-code/agents-and-automation/build-bug-fixing-agent How do I build and run an agent with the Claude Code Agent SDK that finds and fixes bugs? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T12:23:33Z | changed | max breakpoints per request: — → four | [1] 2026-11-20T12:23:33Z | changed | cache TTL: — → five minutes | [1] 2026-11-20T12:23:33Z | changed | minimum version for block arrays: — → v2.1.292 | [1] 2026-11-20T12:23:33Z | changed | example max tokens: 20 → — | [1] 2026-11-20T12:23:33Z | changed | example timeout: 15000 → — | [1] 2026-11-20T12:23:33Z | changed | example model value: haiku → — | [1] 2026-11-13T03:05:11Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/agents-and-automation/call-model-from-mod/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/agents-and-automation/call-model-from-mod POST: https://latestn.com/dispute/tool/claude-code/agents-and-automation/call-model-from-mod with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/agents-and-automation/call-model-from-mod?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I call a model from a Claude Code mod with the mods API? Revision 2, last verified 2026-11-20T12:23:33Z. https://latestn.com/tool/claude-code/agents-and-automation/call-model-from-mod (accessed 2026-11-21T10:01:31Z). @misc{LatestN_tool_claude_code_agents_and_automation_call_model_from_mod_r2, title = {How do I call a model from a Claude Code mod with the mods API?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/agents-and-automation/call-model-from-mod}}, note = {Revision 2; digest sha256:367165c5454fb92f; last verified 2026-11-20T12:23:33Z; accessed 2026-11-21T10:01:31Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/agents-and-automation/call-model-from-mod