Model configuration changedmodel-config
Nearest release: v2.1.321, published under an hour after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 9 Nov 2026 18:57 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 9 Nov 2026 19:07 UTC.
Upstream edited
Recorded here
Lines+46added
Lines−29removed
From line
26
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits93to this page, all time
The whole hunk
from line 26, old and new numbered
/
from line 26
2626| Model alias | Behavior |
2727| - | - |
2828| **`default`** | Special value that clears any model override and reverts to the [runtime default for your account](#default-model-setting). Not itself a model alias |
29| **`best`** | Uses the model the [`fable` alias resolves to](#fable-alias-resolution) where Fable is available to you, otherwise the same model as `opus` |
29| **`best`** | Uses the same model as `opus` |
3030| **`fable`** | Uses the [Fable model for your provider](#fable-alias-resolution) for your hardest and longest-running tasks |
3131| **`sonnet`** | Uses the latest Sonnet model for daily coding tasks |
3232| **`opus`** | Uses the latest Opus model for complex reasoning tasks |
from line 44
4444| Amazon Bedrock, Google Cloud's Agent Platform | Opus 5.5 | Sonnet 4.5 | Haiku 4.5 |
4545| Microsoft Foundry | Opus 4.6 | Sonnet 4.5 | Haiku 4.5 |
4646
47Unless you set `ANTHROPIC_DEFAULT_FABLE_MODEL`, the `fable` alias resolves to Fable 5.1, except in [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway) sessions, where `fable` and `best` resolve to Fable 5.
47Unless you set `ANTHROPIC_DEFAULT_FABLE_MODEL`, the `fable` alias resolves to Fable 5 in [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway) sessions and to Fable 5.2 everywhere else.
4848
49A gateway that isn't configured to serve `claude-fable-5-1` rejects requests for that model. To use Fable 5.1 through a gateway that serves it, select it with `/model claude-fable-5-1`.
49A gateway that isn't configured to serve `claude-fable-5-2` rejects requests for that model. To use Fable 5.2 through a gateway that serves it, select it with `/model claude-fable-5-2`.
5050
5151Where `opus` or `sonnet` resolves to an older model, newer models are available by selecting the full model name explicitly or setting `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`.
5252
from line 60
6060
6161### Work with Fable
6262
63[Claude Fable 5.1](https://platform.claude.com/docs/en/about-claude/models/overview) and Claude Fable 5 are the most capable models in Claude Code, suited to tasks larger than a single sitting. They sustain long autonomous sessions, investigate before acting, and verify their work more often than smaller models. Fable 5.1 is the newer release.
63[Claude Fable models](https://platform.claude.com/docs/en/about-claude/models/overview) are the most capable models in Claude Code, suited to tasks larger than a single sitting. They sustain long autonomous sessions, investigate before acting, and verify their work more often than smaller models.
6464
65Neither Fable model is the account-type default on any plan or provider. Select one explicitly:
65No Fable model is the account-type default on any plan or provider. Select one explicitly:
6666
67* **Fable 5.1**: run `/model fable`, or launch with `claude --model fable`. In [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway) sessions, where the alias resolves to Fable 5, run `/model claude-fable-5-1` instead.
68* **Fable 5**: select it by model ID. On the Anthropic API, run `/model claude-fable-5` or launch with `claude --model claude-fable-5`. On other providers, use your provider's Fable 5 model ID or [pin it](#pin-models-for-third-party-deployments) with `ANTHROPIC_DEFAULT_FABLE_MODEL`.
67* **Fable 5.2**: run `/model fable`, or launch with `claude --model fable`. In [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway) sessions, run `/model claude-fable-5-2` instead.
68* **Fable 5.1 or Fable 5**: select it by model ID. On the Anthropic API, run `/model claude-fable-5-1` or `/model claude-fable-5`, or launch with `claude --model claude-fable-5-1`. On other providers, use your provider's model ID or [pin it](#pin-models-for-third-party-deployments) with `ANTHROPIC_DEFAULT_FABLE_MODEL`.
6969
70If you connect to the Anthropic API directly and your user settings hold `claude-fable-5` or `claude-fable-5[1m]` as the model, for example because you selected Fable in the `/model` picker before v2.1.257, Claude Code changes that saved value to the `fable` or `fable[1m]` alias the first time you run v2.1.257 or later. The startup model line shows `(auto-updated)` once. A `claude-fable-5` value in project, local, or managed settings stays as it is.
70On Pro, Max, Team, and Enterprise plans, a `claude-fable-5-1` model saved in your user settings moves to the `fable` alias:
7171
72* **Pro or Max plan**: the move happens the first time you run v2.1.321 or later. In the terminal, the startup model line can show `(auto-updated)` once.
73* **Team or Enterprise plan**: the move waits for your organization's settings, so it can come at a later startup, or not at all. It applies from the next session, with no `(auto-updated)` line. To check your model, run `/model`.
74
75After the move, sessions start at Fable 5.2's default effort unless you've [set a level](#adjust-effort-level) for it. Console accounts, third-party providers, and project, local, or managed settings keep `claude-fable-5-1`.
76
7277Requests that a Fable model's safety classifiers flag, most often in cybersecurity and biology domains, trigger [automatic model fallback](#automatic-model-fallback).
7378
7479To get the most from Fable:
from line 85
8085
8186> [!NOTE]
8287>
83> Fable 5.1 requires Claude Code v2.1.257 or later. If a request for it from an older version fails, see [Claude Code does not support this model](https://code.claude.com/docs/en/errors.md#claude-code-does-not-support-this-model). Run `claude update` to upgrade. For availability under zero data retention, see [Model availability under ZDR](https://code.claude.com/docs/en/zero-data-retention.md#model-availability-under-zdr).
88> Fable 5.2 requires Claude Code v2.1.321 or later, and Fable 5.1 requires v2.1.257 or later. If a request for one of them from an older version fails, see [Claude Code does not support this model](https://code.claude.com/docs/en/errors.md#claude-code-does-not-support-this-model). Run `claude update` to upgrade. For availability under zero data retention, see [Model availability under ZDR](https://code.claude.com/docs/en/zero-data-retention.md#model-availability-under-zdr).
8489
8590On the Anthropic API, a Fable model appears in the `/model` picker unless [`availableModels`](#restrict-model-selection) or [organization model restrictions](#organization-model-restrictions) exclude it. When your organization can't use Fable at all, for example under [zero data retention](https://code.claude.com/docs/en/zero-data-retention.md#model-availability-under-zdr), the row stays in the picker grayed out, with a note on why.
8691
from line 226
221226
222227## Restrict model selection
223228
224Administrators can use `availableModels` in [managed or policy settings](https://code.claude.com/docs/en/managed-settings.md) to restrict which models users can select. Entries match a model family such as `sonnet`, a version prefix such as `claude-sonnet-4-5`, or a full model ID such as `claude-sonnet-4-5-20250929`. A version prefix also matches later model IDs that extend it with another segment, so `claude-fable-5` permits both Fable 5 and Fable 5.1, while `claude-fable-5-1` permits Fable 5.1 only. To block a model the list permits, or to make each model ID entry permit only the version it names, see [Block specific models or versions](#block-specific-models-or-versions).
229Administrators can use `availableModels` in [managed or policy settings](https://code.claude.com/docs/en/managed-settings.md) to restrict which models users can select. Each entry matches one of these:
225230
231* A model family such as `sonnet`
232* A version prefix such as `claude-sonnet-4-5`. It also matches later model IDs that extend it with another segment. For example, `claude-fable-5` permits Fable 5, Fable 5.1, and Fable 5.2, while `claude-fable-5-1` permits Fable 5.1 only
233* A full model ID such as `claude-sonnet-4-5-20250929`
234
235To block a model the list permits, or to make each model ID entry permit only the version it names, see [Block specific models or versions](#block-specific-models-or-versions).
236
226237On platforms that embed Claude Code and set [`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`](https://code.claude.com/docs/en/env-vars), the host's model configuration takes precedence over managed model settings, while a managed `availableModels` allowlist stays in force unless the host supplies its own; [Exceptions to managed settings precedence](https://code.claude.com/docs/en/settings.md#exceptions-to-managed-settings-precedence) says which keys and variables the host overrides.
227238
228239When `availableModels` is set, the allowlist applies everywhere a user can specify a model:
from line 472
461472
462473When nothing is recorded on your account, managed settings [enforce the allowlist for the Default model](#enforce-the-allowlist-for-the-default-model), and the account-type default is not in `availableModels`, `default` resolves to the enforced Default instead of the account-type default above. When an organization default and enforcement both apply, the organization default replaces the account-type default first and enforcement then applies to it: an allowlisted organization default is kept, while one outside the list resolves to the enforced Default.
463474
464Fable models are not the account-type default on any plan or provider. Choosing one with `/model` saves it as the selected model in your user settings, so later sessions start on it. For the one-time change Claude Code makes to a saved Fable 5 selection in v2.1.257, see [Work with Fable](#work-with-fable).
475> [!NOTE]
476>
477> Fable models are not the account-type default on any plan or provider. Choosing one with `/model` saves it as the selected model in your user settings, so later sessions start on it, apart from the [one-time change to a saved Fable 5.1 pick](#work-with-fable).
465478
466479### `opusplan` model setting
467480
from line 530
517530
518531Fable models, Opus 5.5, Sonnet 5.5, and Opus 5 run with safety classifiers, which most often flag cybersecurity and biology content. For those two categories, the fallback model depends on which model refused:
519532
520* **Fable 5.1, Fable 5, and Opus 5.5**: biology-flagged requests re-run on Opus 5, and cybersecurity-flagged requests re-run on Opus 4.8.
533* **Fable models and Opus 5.5**: biology-flagged requests re-run on Opus 5, and cybersecurity-flagged requests re-run on Opus 4.8.
521534* **Sonnet 5.5**: cybersecurity-flagged requests re-run on Sonnet 5. Biology-flagged requests end with a refusal instead, because Sonnet 5.5 has no biology fallback model.
522535* **Opus 5**: cybersecurity-flagged requests re-run on Opus 4.8. Biology-flagged requests end with a refusal instead, because Opus 5 runs its own biology classifiers with no fallback model.
523536
from line 591
578591
579592On [Amazon Bedrock](https://code.claude.com/docs/en/amazon-bedrock.md), [Google Cloud's Agent Platform](https://code.claude.com/docs/en/google-vertex-ai.md), and [Microsoft Foundry](https://code.claude.com/docs/en/microsoft-foundry.md), model IDs are provider-specific, so automatic fallback only operates when Claude Code can identify each model involved:
580593
581* Claude Code must recognize the current model as a fallback source. Fable 5.1 and Fable 5 are recognized when the model ID contains `claude-fable-5`, matches the value of `ANTHROPIC_DEFAULT_FABLE_MODEL`, or is mapped with [`modelOverrides`](#override-model-ids-per-version). Opus 5.5, Sonnet 5.5, and Opus 5 are recognized by their provider model ID or a [`modelOverrides`](#override-model-ids-per-version) mapping.
594* Claude Code must recognize the current model as a fallback source. Fable models are recognized when the model ID contains `claude-fable-5`, matches the value of `ANTHROPIC_DEFAULT_FABLE_MODEL`, or is mapped with [`modelOverrides`](#override-model-ids-per-version). Opus 5.5, Sonnet 5.5, and Opus 5 are recognized by their provider model ID or a [`modelOverrides`](#override-model-ids-per-version) mapping.
582595* An Opus target must resolve in your deployment, whichever model refused: set `ANTHROPIC_DEFAULT_OPUS_MODEL`, or keep an Opus 4.8 entry in the provider's model list. Without one, fallback stays off for every source model, including Sonnet 5.5, and flagged requests end with a refusal.
583596* The flagged category's fallback model must resolve in your deployment. From a Fable model, Opus 5.5, or Opus 5, if you set `ANTHROPIC_DEFAULT_OPUS_MODEL`, flagged requests re-run on that model for every category that has a fallback; a biology flag on Opus 5 still ends with a refusal. If you don't set it, cybersecurity-flagged requests re-run on the Opus 4.8 entry, and biology-flagged requests from a Fable model or Opus 5.5 on an Opus 5 entry. From Sonnet 5.5, cybersecurity-flagged requests re-run on the model you set in `ANTHROPIC_DEFAULT_SONNET_MODEL`, or on a Sonnet 5 entry in the provider's model list if you don't set it.
584597
from line 605
592605
593606#### Security research and biology workloads
594607
595Workloads in offensive security or biology, including penetration testing, Capture the Flag (CTF) exercises, and biology-adjacent codebases, trigger fallback frequently, often on the first request. For substantive biology work on Fable 5.1, Fable 5, or Opus 5.5, the first flagged request that switches models moves the session to Opus 5, and later biology-flagged requests end in refusals there, because Opus 5 has no biology fallback. On Opus 5 and Sonnet 5.5, you get those refusals from the first flagged request.
608Workloads in offensive security or biology, including penetration testing, Capture the Flag (CTF) exercises, and biology-adjacent codebases, trigger fallback frequently, often on the first request. This is expected routing for these domains, not an account flag. If your organization needs Fable-class capability for this work, ask your Anthropic account team about trusted access programs.
596609
597This is expected routing for these domains, not an account flag. If your organization needs Fable-class capability for this work, ask your Anthropic account team about trusted access programs.
610For substantive biology work on a Fable model or Opus 5.5, the first flagged request that switches models moves the session to Opus 5. Later biology-flagged requests end in refusals there, because Opus 5 has no biology fallback. On Opus 5 and Sonnet 5.5, those refusals start with the first flagged request.
598611
599612### Adjust effort level
600613
from line 617
604617
605618| Model | Levels |
606619| :- | :- |
607| Fable 5.1 and Fable 5 | `low`, `medium`, `high`, `xhigh`, `max` |
620| Fable models | `low`, `medium`, `high`, `xhigh`, `max` |
608621| Opus 5.5, Sonnet 5.5, Haiku 5.5, Opus 5, Sonnet 5, Opus 4.8, and Opus 4.7 | `low`, `medium`, `high`, `xhigh`, `max` |
609622| Opus 4.6 and Sonnet 4.6 | `low`, `medium`, `high`, `max` |
610623
from line 629
6166292. A level you pick in the session, such as with `/effort`, the `/model` picker, or [`applyFlagSettings()`](https://code.claude.com/docs/en/agent-sdk/typescript#applyflagsettings)
6176303. Launching with `--effort`
6186314. Your settings: the level you saved for the model or an [`effortLevel`](https://code.claude.com/docs/en/settings-reference#effortlevel) key, with the precedence between them and across settings files stated at [`modelSettings`](https://code.claude.com/docs/en/settings-reference#modelsettings)
6195. The model's default effort: `high` on every model that supports effort, except that Opus 5.5, Sonnet 5.5, and Haiku 5.5 default to `medium` and Opus 4.7 defaults to `xhigh`. If your organization sets a default effort level for its [organization default model](#organization-default-model), that level is the default when you run that model.
6325. The model's default effort: Fable 5.2, Opus 5.5, Sonnet 5.5, and Haiku 5.5 default to `medium`, and Opus 4.7 defaults to `xhigh`. Other models in the [effort levels table](#adjust-effort-level) default to `high`. If your organization sets a default effort level for its [organization default model](#organization-default-model), that level is the default when you run that model.
620633
621634After an automatic model fallback, see [Effort level after a fallback](#effort-level-after-a-fallback) for the level that applies. For subagents and teammates, see [Effort level of subagents and teammates](#effort-level-of-subagents-and-teammates).
622635
from line 680
667680| Level | When to use it |
668681| :- | :- |
669682| `low` | Quick exchanges where you review each result, such as brainstorming, a first sketch, or a small change like a rename |
670| `medium` | The default on Opus 5.5, Sonnet 5.5, and Haiku 5.5. On Opus 5.5 and Sonnet 5.5, it fits day-to-day engineering work with a clear scope, such as implementing a new feature. On models with a higher default, reduces token usage for cost-sensitive work that can trade off some intelligence |
671| `high` | Work where verification matters or edge cases are likely, such as fixing a bug in an existing codebase. The default on every model except Opus 5.5, Sonnet 5.5, Haiku 5.5, and Opus 4.7 |
683| `medium` | The default on the Fable 5.2, Opus 5.5, Sonnet 5.5, and Haiku 5.5 models. On Opus 5.5 and Sonnet 5.5, it fits day-to-day engineering work with a clear scope, such as implementing a new feature. On models with a higher default, reduces token usage for cost-sensitive work that can trade off some intelligence |
684| `high` | Work where verification matters or edge cases are likely, such as fixing a bug in an existing codebase. The default on the other models in the effort table |
672685| `xhigh` | Deeper reasoning at higher token spend. The default on Opus 4.7 |
673686| `max` | Hard problems you want Claude to work through without you, such as finding security vulnerabilities. `max` may show diminishing returns and is prone to overthinking, so test before adopting it broadly |
674687| `ultracode` | A Claude Code setting rather than a level: plans a [dynamic workflow](https://code.claude.com/docs/en/workflows.md) for each substantive task at any effort level |
from line 700
687700
688701* Retype it outside anything such as quotes, brackets, a path, or a command, in a prompt that doesn't start with `/`
689702* Unset `CLAUDE_CODE_EFFORT_LEVEL` if it's set below `xhigh`, raise your own [`maxEffortLevel`](https://code.claude.com/docs/en/settings-reference#maxeffortlevel) to `xhigh` or above, or ask an organization admin to raise your [organization's limit](#organization-effort-limits)
690* Run `/model` in your session to switch to an Opus 5.5, Sonnet 5.5, Haiku 5.5, or Fable 5.1 model. Where the word can't raise a turn, such as on Amazon Bedrock, [set the effort level](#set-the-effort-level) instead
703* Run `/model` in your session to switch to an Opus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5.2, or Fable 5.1 model. Where the word can't raise a turn, such as on Amazon Bedrock, [set the effort level](#set-the-effort-level) instead
691704
692705#### Set the effort level
693706
from line 776
763776
764777### Extended context
765778
766Fable 5.1, Fable 5, Sonnet 5 and later, Haiku 5.5, Opus 4.6 and later, and Sonnet 4.6 support a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long sessions with large codebases.
779Long sessions with large codebases can use a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model). Fable models, Sonnet 5 and later, Haiku 5.5, Opus 4.6 and later, and Sonnet 4.6 support it.
767780
768Fable 5.1, Fable 5, Sonnet 5 and later, Haiku 5.5, and Opus 4.7 and later run with the 1M window by default, with no `[1m]` suffix needed. That includes sessions on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, and [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway) sessions. To run them with a 200K window instead, see [Turn off 1M context](#turn-off-1m-context).
781Fable models, Sonnet 5 and later, Haiku 5.5, and Opus 4.7 and later run with the 1M window by default, with no `[1m]` suffix needed. That includes sessions on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, and [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway) sessions. To run them with a 200K window instead, see [Turn off 1M context](#turn-off-1m-context).
769782
770783Opus 4.6 and Sonnet 4.6 reach 1M only through their `[1m]` variant, and access to that variant depends on your plan. On Max, Ultra, Team, and Enterprise plans, including both Team Standard and Team Premium seats, Opus 4.6 with 1M context is included with your subscription. Sonnet 4.6 with 1M context requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) on every subscription plan, including Max and Ultra.
771784
from line 807
794807
795808#### Context window behind an LLM gateway
796809
797If you set `ANTHROPIC_BASE_URL` to an [LLM gateway](https://code.claude.com/docs/en/llm-gateway) or another proxy, Claude Code gives each model it recognizes the same context window the model has on the Anthropic API. Fable 5.1, Fable 5, Sonnet 5 and later, Haiku 5.5, and Opus 4.7 and later get the 1M window with no `[1m]` variant to select, and a model that reaches 1M only through its `[1m]` variant, such as Opus 4.6, runs at 200K without it. Claude Code can't detect a lower limit that the gateway or the server behind it enforces. If your gateway rejects requests above 200K tokens, set [`CLAUDE_CODE_AUTO_COMPACT_WINDOW=200000`](https://code.claude.com/docs/en/env-vars) in the environment that starts Claude Code, so sessions on every model [compact at that boundary](#set-the-auto-compact-window).
810If you set `ANTHROPIC_BASE_URL` to an [LLM gateway](https://code.claude.com/docs/en/llm-gateway) or another proxy, Claude Code gives each model it recognizes the same context window the model has on the Anthropic API. Fable models, Sonnet 5 and later, Haiku 5.5, and Opus 4.7 and later get the 1M window with no `[1m]` variant. A model that reaches 1M only through its `[1m]` variant, such as Opus 4.6, runs at 200K without it.
798811
812Claude Code can't detect a lower limit that the gateway or the server behind it enforces. If your gateway rejects requests above 200K tokens, set [`CLAUDE_CODE_AUTO_COMPACT_WINDOW=200000`](https://code.claude.com/docs/en/env-vars) in the environment that starts Claude Code, so sessions on every model [compact at that boundary](#set-the-auto-compact-window).
813
799814#### Turn off 1M context
800815
801816To keep sessions at a 200K window, set `CLAUDE_CODE_DISABLE_1M_CONTEXT=1` in your shell or in a [settings file](https://code.claude.com/docs/en/env-vars.md#set-environment-variables). Claude Code removes the `[1m]` model variants from the model picker. On models that run with the 1M window by default, such as the Fable models, Sonnet 5 and later, and Opus 4.7 and later, it also treats the model as having a 200K context window:
from line 1111
10961111
10971112| Version | Change |
10981113| :- | :- |
1114| v2.1.321 | `fable` resolves to Fable 5.2, except in Claude apps gateway sessions |
1115| v2.1.321 | `best` resolves to the same model as `opus`. Earlier versions use the model `fable` resolves to, where Fable is available |
10991116| v2.1.293 | `haiku` resolves to Haiku 5.5 on the Anthropic API |
11001117| v2.1.284 | `sonnet` resolves to Sonnet 5.5 on the Anthropic API |
11011118| v2.1.280 | `opus` resolves to Opus 5.5 on the Anthropic API, Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform |
No line in this hunk matches that.