model
A Claude Code settings key, read out of the shipped bundle. It was in the build from v2.1.138 and was gone by v2.1.284.
Change the model Claude Code starts with
Anthropic's own wording. Read off All settings, captured 2026-10-22.
In the changelogs
47Releases whose published page names model.
-
v2.1.296
set_model can swap the system prompt only if the expected model is running
set_model gains only_if_model_is_current, which replaces the system prompt only if the session confirms it runs the named model
found in this entry's text
-
v2.1.284
Gateway config checks warn about model lists that would reject every request
Gateway checks now warn when availableModels is empty or leaves out the default model, both of which get requests refused
found in this entry's text
-
v2.1.282
Routine-scheduling example uses the current Sonnet model instead of a fixed one
The example in the routine-scheduling skill now fills in whatever model "sonnet" currently points to rather than always naming claude-sonnet-5
found in this entry's text
-
v2.1.281
Agent definitions may have an empty prompt
Agent definitions with an empty
promptare no longer rejectedfound in this entry's text
-
v2.1.281
Command frontmatter overrides helper
Command overrides can now replace a command's description, argument hint, model and allowed tools, and plugin commands are merged into the list
found in this entry's text
-
v2.1.280
MCP servers can now hide tools from the model via
_meta.ui.visibility, live and wiredMCP servers can now hide specific tools from Claude while still showing them to the human in mcp_status
found in this entry's text
-
v2.1.277
Announcement-style context blocks can be repositioned to just before the closing line
Certain system announcements can now be moved to sit right before the closing line at session start
found in this entry's text
-
v2.1.275
Advisor-model API errors get dedicated recognition, including org-entitlement case
Advisor-model API errors are now specifically recognized, including when unavailable for an organization
found in this entry's text
-
v2.1.269
Model-parameter allowlist changed from array to Set
Internal list of allowed API request fields switched from an array to a Set
found in this entry's text
-
v2.1.268
Datadog model-sanitization now runs on any defined model value, not just strings
Datadog telemetry now sanitizes any defined model value, not just string ones, dropping events it can't sanitize
found in this entry's text
-
v2.1.268
Client-side data cache key getter now accepts a model parameter
Client-side data cache can now be keyed per model, not just globally
found in this entry's text
-
v2.1.267
Per-model "maxEffortLevel" cap now enforced client-side across settings
maxEffortLevel now combines a global cap with per-model overrides across all settings files and clamps any explicit effort request
found in this entry's text
-
v2.1.263
Effort nudge confirm dialog supports templated copy and an optional warning banner
The effort nudge dialog can now fill in the model and levels by name and show a warning banner, once enabled.
found in this entry's text
-
v2.1.261
Weekly usage-limit lookup simplified/hardened
Weekly usage-limit lookup logic was simplified and tightened.
found in this entry's text
-
v2.1.260
Remote session now propagates skills/plugins list from worker init
Remote session init now also captures the skills and plugins list, not just commands and model.
found in this entry's text
-
v2.1.260
Per-model 'quizzical shore' hint on thinking blocks, off by default
A hidden hint can appear on thinking blocks per model, off by default.
found in this entry's text
-
v2.1.259
Skill model field description updated
A skill result's model field is documented as the model the turn actually ran on, not the raw frontmatter override.
found in this entry's text
-
v2.1.257
Workflow docs: model-override guidance suppressed when CLAUDE_CODE_SUBAGENT_MODEL_FORCE is set
With the forced subagent model set, the workflow authoring reference drops its model-override guidance.
found in this entry's text
-
v2.1.257
"High demand" model-overload message generalized
The high-demand overload notice now names whichever model is actually overloaded rather than a fixed pair.
found in this entry's text
-
v2.1.257
New
$.session.authorizeplugin hook API surfacePlugins gain $.session.authorize(), which mints an auth handle for the session.
found in this entry's text
-
v2.1.257
New
CLAUDE_CODE_SUBAGENT_MODEL_FORCEenv varA new env var stops per-call model overrides for subagents and workflow agents, forcing them to inherit.
found in this entry's text
-
v2.1.257
AskUserQuestion-style tool prompt gains a leanPrompt parameter
The AskUserQuestion prompt now receives a lean-prompt flag that can suppress a guidance snippet.
found in this entry's text
-
v2.1.257
Automatic migration of
claude-fable-5model alias tofableIf your model setting says claude-fable-5, startup rewrites it to the fable alias automatically.
found in this entry's text
-
v2.1.257
New fallback message when org's pinned default model is unavailable in this build
If your org's pinned default model is missing from this build, the restart notice now says the standard default applies.
found in this entry's text
-
v2.1.251
Subagent
modelfield documents its fallback orderSubagent model field docs now spell out alias, raw id, inherit, and the default fallback.
found in this entry's text
-
v2.1.248
Coordinator workers can be forced onto the session model
An env var forces coordinator workers onto the session's model, ignoring any requested one.
found in this entry's text
-
v2.1.248
claude remote-controlrefuses flags typed before the verbFlags typed before remote-control now error out instead of being silently dropped.
found in this entry's text
-
v2.1.248
Agent tool tells subagents when the model choice is ignored
In coordinator sessions the Agent tool now says when its model choice will be ignored.
found in this entry's text
-
v2.1.246
Plugin interfaces are checked before they are used
A plugin publishing an interface for others now fails loudly if it isn't a proper object of functions.
found in this entry's text
-
v2.1.239
Spend and rate limit notices say when the limit resets
Rate and spend limit notices now name the limit and when it resets.
found in this entry's text
-
v2.1.239
Per-model effort level in settings, behind a gate
You could set an effort level per model in settings, but the lookup is gated off.
found in this entry's text
-
v2.1.239
Remote Control workers can be handed MCP config and a system prompt by the daemon, switched off in this build
Remote Control workers could receive MCP config and prompts from the daemon, but no session does.
found in this entry's text
-
v2.1.235
Cloud/frame SDK messages are validated instead of trusted
Cloud/frame SDK messages are now validated field-by-field instead of trusted
found in this entry's text
-
v2.1.233
/doctor now checks skills for broken frontmatter
/doctor now spots skills whose frontmatter fails to parse and offers to repair it.
found in this entry's text
-
v2.1.232
/context returns structured usage, exposed to the SDK as
context_usageSDK consumers get /context numbers as
context_usageon the assistant message, including an over-limit block.found in this entry's text
-
v2.1.228
The gateway now requires a model in the request body
The self-hosted gateway now rejects requests that omit a model with a 400.
found in this entry's text
-
v2.1.224
Agent versions are sequential integers, not timestamps
Agent versions are documented as counting up from 1, not timestamps.
found in this entry's text
-
v2.1.224
Inference geography can be pinned on a Managed Agents agent
The Claude API docs describe pinning inference geography to us or global on an agent's model.
found in this entry's text
-
v2.1.222
Host-managed provider sessions take model policy from the parent process
Setting CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST makes the parent process dictate your model settings, ignoring your settings file.
found in this entry's text
-
v2.1.221
Local HTTP API rejects non-string model fields
The local HTTP API now returns a clear 400 when model isn't a string, instead of ignoring it.
found in this entry's text
-
v2.1.219
The API skill's model placeholders now resolve to Claude Opus 5, with the previous Opus kept as a separate placeholder
The API skill's model placeholders now render Opus 5, keeping the previous Opus named separately.
found in this entry's text
-
v2.1.187
Usage credits messages — cleaner wording
found in this entry's text
-
v2.1.30
Enhanced Custom Subagent Schema
found in this entry's text
-
v2.0.12
Inline Plugin Commands
found in this entry's text
-
v2.0.10
Model Switching from Plan Mode
found in this entry's text
-
v2.0.2
Removed Rate Limit Display from Model Selection
found in this entry's text
-
v1.0.113
Enhanced Prompt Caching Function Signatures
found in this entry's text
First cited
0No release's published evidence quotes this name. The ledger indexes the Evidence lines of every changelog on this site, so this says nobody here has ever quoted it; it says nothing about how old the name is.
Presence across releases
2Build by build
149One row per release since the first build this name was read out of. Absent means the build was read and the name was not in it, never mined means no bundle for that release was ever archived, and a declared type or a default is only ever what that release's own bundle stated.
Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the settings key does. All settings keys.