What this read moved
1–22 of 22amazon-bedrock Changed · +8 / -8 lines
from line 265
265265
266266Set these environment variables to specific Amazon Bedrock model IDs.
267267
268Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Amazon Bedrock resolves to Opus 5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias resolves to Sonnet 4.5. This example pins each alias to a specific version:
268Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Amazon Bedrock resolves to Opus 5.5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias resolves to Sonnet 4.5. This example pins each alias to a specific version:
269269
270270```bash theme={null}
271271export ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'
from line 277
277277
278278To keep the built-in default models and change only their preferred prefix, set [`ANTHROPIC_BEDROCK_REGION_PREFIX`](#cross-region-inference-profile-prefixes) instead of pinning. The difference shows in what the `opus` alias resolves to:
279279
280| You set | The `opus` alias resolves to |
281| :------------------------------------------------------------ | :---------------------------------------------------------------------------- |
282| `ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'` | `us.anthropic.claude-opus-4-8`, the exact ID you pinned |
283| `ANTHROPIC_BEDROCK_REGION_PREFIX=eu` | `eu.anthropic.claude-opus-5`, the built-in default with your preferred prefix |
280| You set | The `opus` alias resolves to |
281| :------------------------------------------------------------ | :------------------------------------------------------------------------------ |
282| `ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'` | `us.anthropic.claude-opus-4-8`, the exact ID you pinned |
283| `ANTHROPIC_BEDROCK_REGION_PREFIX=eu` | `eu.anthropic.claude-opus-5-5`, the built-in default with your preferred prefix |
284284
285285For current and legacy model IDs, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). For the full list of pinning environment variables, see [Model configuration](/docs/en/model-config#pin-models-for-third-party-deployments).
286286
from line 288
288288
289289| Model type | Default model |
290290| :--------------- | :---------------------------------------------------------------------------------------- |
291| Primary model | Opus 5, for example `us.anthropic.claude-opus-5` in a `us-*` region |
291| Primary model | Opus 5.5, for example `us.anthropic.claude-opus-5-5` in a `us-*` region |
292292| Small/fast model | Sonnet 4.5, for example `us.anthropic.claude-sonnet-4-5-20250929-v1:0` in a `us-*` region |
293293
294294Background tasks such as session title generation use the small/fast model, normally a Haiku-class model. On Amazon Bedrock, Claude Code uses the default Sonnet model for background tasks because Haiku may not be enabled in every account or region. Two selections change which model carries them:
from line 300
300300 Opus models have a higher per-token price than Sonnet models, so a deployment that doesn't pin a primary model is billed at the Opus rate once it updates to v2.1.207 or later. To keep Sonnet 4.5 as the primary model, set `ANTHROPIC_MODEL` to its full model ID. A deployment that steers the default with `ANTHROPIC_DEFAULT_SONNET_MODEL` and doesn't set `ANTHROPIC_DEFAULT_OPUS_MODEL` keeps its steered Sonnet model as the default.
301301</Warning>
302302
303On v2.1.207 through v2.1.218, the primary model on Amazon Bedrock defaulted to Opus 4.8 and the `opus` alias resolved to Opus 4.8. Before v2.1.207, the primary model defaulted to Sonnet 4.5, the `opus` alias resolved to Opus 4.6, and background tasks always used the primary model.
303Before v2.1.280, the primary model on Amazon Bedrock defaulted to Opus 5 and the `opus` alias resolved to Opus 5 from v2.1.219. On v2.1.207 through v2.1.218, the primary model on Amazon Bedrock defaulted to Opus 4.8 and the `opus` alias resolved to Opus 4.8. Before v2.1.207, the primary model defaulted to Sonnet 4.5, the `opus` alias resolved to Opus 4.6, and background tasks always used the primary model.
304304
305305To customize models further, use one of these methods:
306306
from line 373
373373```bash theme={null}
374374export ANTHROPIC_BEDROCK_REGION_PREFIX=global
375375# In a us-* region, the primary model now resolves to
376# global.anthropic.claude-opus-5 instead of us.anthropic.claude-opus-5
376# global.anthropic.claude-opus-5-5 instead of us.anthropic.claude-opus-5-5
377377```
378378
379379The preferred prefix is a preference, not a guarantee, whether it comes from your region or from the variable. How Claude Code applies it depends on whether it can check profile availability in your account:
communications-kit Changed · +9 / -9 lines
from line 212
212212*Fable* is the most
213213capable model for your hardest, longest-running tasks; it is not the
214214default, so select it with `/model fable`, and note that cybersecurity and
215biology content falls back to Opus automatically. Opus 5 runs its own
216checks, so flagged cybersecurity content switches models and flagged
217biology content is refused.
215biology content falls back to Opus automatically. Opus 5.5 and Opus 5 run
216their own checks too: flagged content switches to an earlier Opus, except
217that flagged biology content on Opus 5 is refused.
218218
219219*Try it now:* type `/model` and pick Sonnet if you haven't already. It is
220220the right default for most tasks.
from line 222
222222📖 Model configuration → https://code.claude.com/docs/en/model-config
223223```
224224
225| Model | Best for |
226| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
227| Fable | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content triggers [automatic model fallback to Opus](/docs/en/model-config#automatic-model-fallback) |
228| Opus | Large-scale refactors, complex debugging, architecture decisions, high-stakes changes. On Opus 5, cybersecurity or biology content triggers [automatic model fallback or a refusal](/docs/en/model-config#automatic-model-fallback) |
229| Sonnet | Everyday feature work, bug fixes, tests, documentation, code review. Recommended default. |
230| Haiku | Quick questions, formatting, mechanical edits, rapid iteration |
225| Model | Best for |
226| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
227| Fable | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content triggers [automatic model fallback to Opus](/docs/en/model-config#automatic-model-fallback) |
228| Opus | Large-scale refactors, complex debugging, architecture decisions, high-stakes changes. On Opus 5.5 and Opus 5, cybersecurity or biology content triggers [automatic model fallback or a refusal](/docs/en/model-config#automatic-model-fallback) |
229| Sonnet | Everyday feature work, bug fixes, tests, documentation, code review. Recommended default. |
230| Haiku | Quick questions, formatting, mechanical edits, rapid iteration |
231231
232232**Quick wins to try first**
233233
env-vars Changed · +3 / -2 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 258
258258| `CLAUDE_CODE_DISABLE_PERMISSION_PROMPT_NOTIFY_HOOKS` | Set to `1` to stop Claude Code from running your [`Notification` hooks for unanswered permission requests](/docs/en/hooks#notification) in sessions where Claude Code sends them to the Agent SDK's `canUseTool` callback, which is how Claude Desktop and the VS Code extension host Claude Code. Has no effect in terminal sessions. Requires Claude Code v2.1.233 or later |
259259| `CLAUDE_CODE_DISABLE_POLICY_SKILLS` | Set to `1` to skip loading skills from the system-wide managed skills directory. Useful for container or CI sessions that should not load operator-provisioned skills |
260260| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context. This also skips the background small/fast-model request that [generates a session title](/docs/en/sessions#name-your-sessions) |
261| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and gateways that reject the parameter. On models that think by default, omitting the parameter means the model may still think. To explicitly disable [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) on the Anthropic API, use `MAX_THINKING_TOKENS=0` instead. Neither variable turns thinking off on Fable models, which can't have thinking turned off. On [third-party providers](/docs/en/third-party-integrations), `MAX_THINKING_TOKENS=0` likewise omits the parameter, so the two variables behave the same there |
261| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and gateways that reject the parameter. On models that think by default, omitting the parameter means the model may still think. To explicitly disable [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) on the Anthropic API, use `MAX_THINKING_TOKENS=0` instead. Neither variable turns thinking off on Opus 5.5 or the Fable models, which can't have thinking turned off. On [third-party providers](/docs/en/third-party-integrations), `MAX_THINKING_TOKENS=0` likewise omits the parameter, so the two variables behave the same there |
262262| `CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT` | Set to `1` to skip proactive [auto-compaction](/docs/en/costs#reduce-token-usage) when Claude Code doesn't recognize the model ID, such as an [LLM gateway](/docs/en/llm-gateway) alias. Without this variable, Claude Code compacts at the context window it assumes for the ID. `CLAUDE_CODE_MAX_CONTEXT_TOKENS` can correct the assumed window instead; see [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) for when each variable applies. Requires Claude Code v2.1.223 or later |
263263| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in [fullscreen rendering](/docs/en/fullscreen) and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appear |
264264| `CLAUDE_CODE_DISABLE_WINDOWS_SHELL_LAUNCHER` | Set to `1` to start [PowerShell tool](/docs/en/tools-reference#powershell-tool) commands on Windows directly instead of through the `cmd.exe` launcher. By default, the launcher lets a PowerShell command [running in the background](/docs/en/tools-reference#background-commands) [carry over to the session's next process](/docs/en/agent-view#the-supervisor-process), such as when you [background the session](/docs/en/agent-view#from-inside-a-session). If you set the variable, a backgrounded PowerShell command stops when the session's process exits. Bash commands aren't affected. Requires Claude Code v2.1.269 or later |
errors Changed · +5 / -4 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 152
152152| `<model> can't help with this. Start a new session to continue` | [Request errors](#usage-policy-refusal) |
153153| `Claude Code is unable to respond to this request, which appears to violate our Usage Policy` | [Request errors](#usage-policy-refusal) |
154154| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
155| `Opus 5.5's safeguards flagged this session` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
155156| `<model> has safety measures that flagged this message for a cybersecurity topic` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
156157| `Installation was killed before it could finish (exit code 137)` | [Installation errors](#installation-was-killed-before-it-could-finish) |
157158| `The connection dropped while downloading the update` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |
from line 1936
19351936Unable to resize image (… raw, … base64). The image exceeds the … API limit and compression failed. Please resize the image manually or use a smaller image.
19361937Unable to resize image — could not verify image dimensions are within the 2000x2000px API limit.
19371938Unable to resize image — it is a CMYK JPEG, which Claude Code cannot decode, and at …px it is over the 2000x2000px limit, so it cannot be sent. Re-save it as an RGB PNG or JPEG and try again.
1938Unable to resize image — it is an animated WebP whose first frame Claude Code cannot decode, and at …px it is over the 2000x2000px limit, so it cannot be sent. Save its first frame as a PNG or JPEG and try again.
1939Unable to resize image — its pixels could not be decoded (the file may be damaged, or use an encoding Claude Code cannot read), and it is over the … API limit (… raw, … base64), so it cannot be sent. Re-save it as a PNG or JPEG and try again.
1940```
1941
1942Claude Code normally res
1939Unable to resize image — it is an animated WebP whose first frame Claude Code cannot decode, and at
fast-mode Changed · +4 / -3 lines
from line 8
88
99Fast mode is a high-speed configuration for Claude Opus, making the model up to 2.5x faster at a higher cost per token. Toggle it on with `/fast` when you need speed for interactive work like rapid iteration or live debugging, and toggle it off when cost matters more than latency.
1010
11Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities with faster responses. Fast mode is supported on Opus 5 and Opus 4.8. It is not available on Sonnet, Haiku, or other models.
11Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities with faster responses. Fast mode is supported on Opus 5.5, Opus 5, and Opus 4.8. It is not available on Sonnet, Haiku, or other models.
1212
1313Opus 4.7 doesn't support fast mode, so switching to it turns fast mode off. Fast mode for Opus 4.7 was deprecated on June 25, 2026, and removed on July 24, 2026.
1414
from line 15
1515What to know:
1616
1717* Use `/fast` to toggle on fast mode in the Claude Code CLI. The [VS Code extension](/docs/en/vs-code) offers a **Toggle fast mode** command when the selected model supports fast mode. Claude Code saves that toggle to your [`fastMode` setting](#toggle-fast-mode).
18* Fast mode pricing per MTok input/output is \$10/\$50 on Opus 5 and Opus 4.8.
18* Fast mode pricing per MTok input/output is \$8/\$40 on Opus 5.5 and \$10/\$50 on Opus 5 and Opus 4.8.
1919* Available to Claude Code users on subscription plans (Pro/Max/Team/Enterprise) and on Claude Console. Team and Enterprise organizations need an Owner to enable it first, and Console organizations need access provisioned first, both described under [Requirements](#requirements).
2020* For Claude Code users on subscription plans (Pro/Max/Team/Enterprise), fast mode is available via usage credits only and not included in the subscription rate limits.
2121
from line 41
4141* A small `↯` icon appears next to the prompt while fast mode is active
4242* Run `/fast` again at any time to check whether fast mode is on or off
4343
44Opus 5 is the fast mode default in Claude Code v2.1.219 and later. Before v2.1.219, fast mode defaulted to Opus 4.8 on v2.1.154 through v2.1.218, and to Opus 4.7 on v2.1.142 through v2.1.153.
44Opus 5.5 is the fast mode default in Claude Code v2.1.280 and later. Before v2.1.280, fast mode defaulted to Opus 5 from v2.1.219, to Opus 4.8 on v2.1.154 through v2.1.218, and to Opus 4.7 on v2.1.142 through v2.1.153.
4545
4646When you disable fast mode with `/fast` again, you remain on Opus. To switch to a different model, use `/model`.
4747
from line 68
6868
6969| Model | Input (MTok) | Output (MTok) |
7070| -------- | ------------ | ------------- |
71| Opus 5.5 | \$8 | \$40 |
7172| Opus 5 | \$10 | \$50 |
7273| Opus 4.8 | \$10 | \$50 |
7374
google-vertex-ai Changed · +3 / -3 lines
from line 214
214214
215215Set these environment variables to specific Google Cloud's Agent Platform model IDs.
216216
217Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Google Cloud's Agent Platform resolves to Opus 5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias resolves to Sonnet 4.5. This example pins each alias to a specific version:
217Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Google Cloud's Agent Platform resolves to Opus 5.5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias resolves to Sonnet 4.5. This example pins each alias to a specific version:
218218
219219```bash theme={null}
220220export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'
from line 228
228228
229229| Model type | Default value |
230230| :--------------- | :--------------------------- |
231| Primary model | `claude-opus-5` |
231| Primary model | `claude-opus-5-5` |
232232| Small/fast model | `claude-sonnet-4-5@20250929` |
233233
234234Background tasks such as session title generation use the small/fast model, normally a Haiku-class model. On Google Cloud's Agent Platform, Claude Code uses the default Sonnet model for background tasks because Haiku may not be enabled in every project or region. Two selections change which model carries them:
from line 240
240240 Opus models have a higher per-token price than Sonnet models, so a deployment that doesn't pin a primary model is billed at the Opus rate once it updates to v2.1.207 or later. To keep Sonnet 4.5 as the primary model, set `ANTHROPIC_MODEL` to its full model ID. A deployment that steers the default with `ANTHROPIC_DEFAULT_SONNET_MODEL` and doesn't set `ANTHROPIC_DEFAULT_OPUS_MODEL` keeps its steered Sonnet model as the default.
241241</Warning>
242242
243On v2.1.207 through v2.1.218, the primary model on Google Cloud's Agent Platform defaulted to Opus 4.8 and the `opus` alias resolved to Opus 4.8. Before v2.1.207, the primary model defaulted to Sonnet 4.5, the `opus` alias resolved to Opus 4.6, and background tasks always used the primary model.
243Before v2.1.280, the primary model on Google Cloud's Agent Platform defaulted to Opus 5 and the `opus` alias resolved to Opus 5 from v2.1.219. On v2.1.207 through v2.1.218, the primary model on Google Cloud's Agent Platform defaulted to Opus 4.8 and the `opus` alias resolved to Opus 4.8. Before v2.1.207, the primary model defaulted to Sonnet 4.5, the `opus` alias resolved to Opus 4.6, and background tasks always used the primary model.
244244
245245To customize models further:
246246
model-config Changed · +43 / -45 lines
from line 39
3939
4040| Provider | `opus` | `sonnet` |
4141| :--------------------------------------------------- | :------- | :--------- |
42| Anthropic API | Opus 5 | Sonnet 5 |
43| [Claude Platform on AWS](/docs/en/claude-platform-on-aws) | Opus 5 | Sonnet 4.6 |
44| Amazon Bedrock, Google Cloud's Agent Platform | Opus 5 | Sonnet 4.5 |
42| Anthropic API | Opus 5.5 | Sonnet 5 |
43| [Claude Platform on AWS](/docs/en/claude-platform-on-aws) | Opus 5.5 | Sonnet 4.6 |
44| Amazon Bedrock, Google Cloud's Agent Platform | Opus 5.5 | Sonnet 4.5 |
4545| Microsoft Foundry | Opus 4.6 | Sonnet 4.5 |
4646
4747<span id="fable-alias-resolution" />
from line 52
5252
5353Where an alias 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`.
5454
55Before v2.1.219, `opus` resolved to Opus 4.8 on the Anthropic API from v2.1.154, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.207. Before v2.1.207, `opus` resolved to Opus 4.7 on Claude Platform on AWS and to Opus 4.6 on Amazon Bedrock and Google Cloud's Agent Platform.
55Before v2.1.280, `opus` resolved to Opus 5 on the Anthropic API, Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.219. Before v2.1.219, `opus` resolved to Opus 4.8 on the Anthropic API from v2.1.154, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.207. Before v2.1.207, `opus` resolved to Opus 4.7 on Claude Platform on AWS and to Opus 4.6 on Amazon Bedrock and Google Cloud's Agent Platform.
5656
57Aliases point to the recommended version for your provider and update over time. To pin to a specific version, use the full model name, for example `claude-opus-5`, or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.
57Aliases point to the recommended version for your provider and update over time. To pin to a specific version, use the full model name, for example `claude-opus-5-5`, or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.
5858
5959<Note>
60 Opus 5 requires Claude Code v2.1.219 or later. Sonnet 5 requires v2.1.197 or later. Opus 4.8 requires v2.1.154 or later. Run `claude update` to upgrade.
60 Opus 5.5 requires Claude Code v2.1.280 or later. Opus 5 requires v2.1.219 or later. Sonnet 5 requires v2.1.197 or later. Run `claude update` to upgrade.
6161</Note>
6262
6363### Work with Fable
from line 124
124124
125125Typing `/model <name>` directly behaves like `Enter`. To switch for this session only, open the picker with `/model` and press `s` on the model's row.
126126
127If you switch models with `/model`, the switch also reaches [subagents that inherit the main conversation's model](/docs/en/sub-agents#choose-a-model), because Claude Code resolves their model from the one your session is using when Claude starts them. Switch to Opus before Claude delegates research or test runs to one of them, and that work runs on Opus too. To keep a custom subagent on a smaller model, set `model` in its definition.
128
127129If you set a model with `/model` in [non-interactive mode](/docs/en/headless), with the `-p` flag, your choice applies to the current session only and isn't saved as your default; `/model` in that mode requires Claude Code v2.1.205 or later. Project and managed settings still take precedence and reapply on the next launch. An [organization default model](#organization-default-model) that your admin has configured to override user selection also reapplies on the next launch.
128130
129131In v2.1.144 through v2.1.152, `/model` applied to the current session only and `d` in the picker saved a default.
from line 403
401403
402404The behavior of `default` depends on your account type:
403405
404* **Max, Team Premium, Enterprise, and Anthropic API**: defaults to Opus 5
405* **Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform**: defaults to Opus 5
406* **Pro and Team Standard**: defaults to Sonnet 5
406* **Pro, Max, Team, Enterprise, and Anthropic API**: defaults to Opus 5.5
407* **Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform**: defaults to Opus 5.5
407408* **Microsoft Foundry**: defaults to Sonnet 4.5
408409
409Before v2.1.219, `default` resolved to Opus 4.8 on the Anthropic API, Max, Team Premium, and Enterprise pay-as-you-go from v2.1.154, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.207. Before v2.1.207, `default` resolved to Opus 4.7 on Claude Platform on AWS and to Sonnet 4.5 on Amazon Bedrock and Google Cloud's Agent Platform.
410Before v2.1.280, `default` resolved to Sonnet 5 on Pro and Team Standard, and to Opus 5 on Max, Team Premium, Enterprise, the Anthropic API, Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.219. Before v2.1.219, `default` resolved to Opus 4.8 on the Anthropic API, Max, Team Premium, and Enterprise pay-as-you-go from v2.1.154, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.207. Before v2.1.207, `default` resolved to Opus 4.7 on Claude Platform on AWS and to Sonnet 4.5 on Amazon Bedrock and Google Cloud's Agent Platform.
410411
411412When an admin has set an [organization default model](#organization-default-model), `default` resolves to that model instead of the account-type default above. Requires Claude Code v2.1.196 or later. `default` can also resolve to the model you set with [`ANTHROPIC_DEFAULT_MODEL`](#set-a-default-model-for-new-sessions), under the conditions listed in its section.
412413
from line 465
464465
465466### Automatic model fallback
466467
467This section covers content-based fallback from Fable models and Opus 5. For availability-based fallback when a model is overloaded or unavailable, see [Fallback model chains](#fallback-model-chains).
468This section covers content-based fallback from Fable models, Opus 5.5, and Opus 5. For availability-based fallback when a model is overloaded or unavailable, see [Fallback model chains](#fallback-model-chains).
468469
469Fable models and Opus 5 run with safety classifiers, which most often flag cybersecurity and biology content. When a classifier flags a request and the flagged category has a fallback model, Claude Code re-runs the request on that model and shows a notice in the transcript. For those two categories, the fallback model depends on which model refused:
470Fable models, Opus 5.5, and Opus 5 run with safety classifiers, which most often flag cybersecurity and biology content. When a classifier flags a request and the flagged category has a fallback model, Claude Code re-runs the request on that model and shows a notice in the transcript. For those two categories, the fallback model depends on which model refused:
470471
471* **Fable 5.1 and Fable 5**: biology-flagged requests re-run on Opus 5, and cybersecurity-flagged requests re-run on Opus 4.8.
472* **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.
472473* **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.
473474
474475On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, Claude Code resolves these targets through your deployment instead, and if you set `ANTHROPIC_DEFAULT_OPUS_MODEL`, categories that have a fallback re-run on the pinned model; see [Enable fallback on Bedrock, Agent Platform, and Foundry](#enable-fallback-on-bedrock-agent-platform-and-foundry).
from line 502
501502
502503On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), model IDs are provider-specific, so automatic fallback only operates when Claude Code can identify both models involved:
503504
504* 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 is recognized by its provider model ID or a [`modelOverrides`](#override-model-ids-per-version) mapping.
505* The fallback model must resolve in your deployment. 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 an Opus 4.8 entry in the provider's model list, and biology-flagged requests from a Fable model on an Opus 5 entry.
505* 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 and Opus 5 are recognized by their provider model ID or a [`modelOverrides`](#override-model-ids-per-version) mapping.
506* The fallback model must resolve in your deployment. 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 an Opus 4.8 entry in the provider's model list, and biology-flagged requests from a Fable model or Opus 5.5 on an Opus 5 entry.
506507
507508If either model can't be identified, Claude Code does not switch automatically. The flagged request ends with a refusal message, and you can switch models with [`/model`](#setting-your-model) and retry. Setting `ANTHROPIC_DEFAULT_FABLE_MODEL` to your Fable model ID enables Fable recognition. Setting `ANTHROPIC_DEFAULT_OPUS_MODEL` to an Opus model ID gives the flagged categories a fallback target, unless the pin names a model outside the Opus family or the model that refused; then Claude Code doesn't switch and the refusal stands.
508509
509510#### Security research and biology workloads
510511
511Workloads 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 or Fable 5, Claude Code moves the session to Opus 5 at the first flagged request, and later biology-flagged requests end in refusals there, because Opus 5 has no biology fallback. On Opus 5, you get those refusals from the first flagged request.
512Workloads 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, Claude Code moves the session to Opus 5 at the first flagged request, and later biology-flagged requests end in refusals there, because Opus 5 has no biology fallback. On Opus 5, you get those refusals from the first flagged request.
512513
513514This 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.
514515
from line 519
518519
519520The available effort levels depend on the model. Models not listed here do not support effort:
520521
521| Model | Levels |
522| :--------------------------------------- | :-------------------------------------- |
523| Fable 5.1 and Fable 5 | `low`, `medium`, `high`, `xhigh`, `max` |
524| Opus 5, Sonnet 5, Opus 4.8, and Opus 4.7 | `low`, `medium`, `high`, `xhigh`, `max` |
525| Opus 4.6 and Sonnet 4.6 | `low`, `medium`, `high`, `max` |
522| Model | Levels |
523| :------------------------------------------------- | :-------------------------------------- |
524| Fable 5.1 and Fable 5 | `low`, `medium`, `high`, `xhigh`, `max` |
525| Opus 5.5, Opus 5, Sonnet 5, Opus 4.8, and Opus 4.7 | `low`, `medium`, `high`, `xhigh`, `max` |
526| Opus 4.6 and Sonnet 4.6 | `low`, `medium`, `high`, `max` |
526527
527528If you set a level the active model does not support, Claude Code falls back to the highest supported level at or below the one you set. For example, `xhigh` runs as `high` on Opus 4.6. Your organization or your own settings can also cap the levels a model offers; see [Organization effort limits](#organization-effort-limits).
528529
from line 530
529530With the [`ultracode`](/docs/en/settings-reference#ultracode) setting off, Claude Code resolves the session's effort level in this order, taking the first that applies:
530531
5315321. An explicit choice: the [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment variable, launching with `--effort`, or `/effort` in the session ([a non-interactive `/effort` has narrower effect](#non-interactive-effort))
5322. The model's default effort, on Fable 5, Opus 4.8, or Opus 4.7: from the first time you run one of these models, Claude Code holds that model's default effort across sessions, even when your settings resolve a different level. Opus 5 and Fable 5.1 have no such hold. Whether a level you set ends the hold depends on how you set it, for example:
533 * **Ends the hold**: confirming a level interactively, with `Enter` in the `/effort` slider or the `/model` picker or with a level typed after `/effort`, or picking a level from a connected device's [Remote Control](/docs/en/remote-control#what-connected-devices-see) effort control
534 * **Leaves the hold in place for later sessions**: `--effort` at launch, or `s` in the `/effort` slider or the `/model` picker
5353. Your settings: the level you saved for the model or an [`effortLevel`](/docs/en/settings-reference#effortlevel) key, with the precedence between them and across settings files stated at [`modelSettings`](/docs/en/settings-reference#modelsettings)
5364. The model's default effort: `high` on every model that supports effort, except that Opus 4.7 defaults to `xhigh` and, when 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
5332. Your settings: the level you saved for the model or an [`effortLevel`](/docs/en/settings-reference#effortlevel) key, with the precedence between them and across settings files stated at [`modelSettings`](/docs/en/settings-reference#modelsettings)
5343. The model's default effort: `high` on every model that supports effort, except that Opus 5.5 defaults to `medium`, Opus 4.7 defaults to `xhigh`, and, when 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
537535
536Opus 5.5 starts at `medium` unless one of the sources above sets a level for it, and a top-level `effortLevel` in your user settings file doesn't count for Opus 5.5. That key is the older form `/effort` wrote before Claude Code saved levels per model: it keeps applying where it applied before, on Opus 5, Fable 5.1, and earlier models, while Opus 5.5 and models released after it start at their own default until you choose a level for them with `/effort` or the `/model` picker. A top-level `effortLevel` in project, local, or managed settings, or one passed with `--settings`, applies to every model.
537
538538When you set `low`, `medium`, `high`, or `xhigh` in an interactive session on your machine, you choose how long it lasts by how you confirm it:
539539
540540* `Enter` in the `/effort` slider or the `/model` picker, or a level typed after `/effort`: save the level as your default and apply it in later sessions
from line 550
550550
551551<span id="non-interactive-effort" />
552552
553When you set a level with `/effort` in a [`-p` run](/docs/en/headless), Claude Code applies it to that session only and doesn't save it as your default. On Fable 5, Opus 4.8, and Opus 4.7, that level also neither ends the hold on the model's default effort nor overrides it for the session. While that hold is in effect, a non-interactive `/effort` reports `Not applied`, so pass `--effort` at launch instead.
553When you set a level with `/effort` in a [`-p` run](/docs/en/headless), Claude Code applies it to that session only and doesn't save it as your default.
554554
555555The `/effort` menu also offers `ultracode`. Ultracode is a Claude Code setting rather than a model effort level: it sends `xhigh` to the model and additionally has Claude orchestrate [dynamic workflows](/docs/en/workflows) for substantive tasks. For where it can be set persistently, see the [`ultracode`](/docs/en/settings-reference#ultracode) setting.
556556
from line 582
582582| Level | When to use it |
583583| :---------- | :------------------------------------------------------------------------------------------------------------------------------------- |
584584| `low` | Reserve for short, scoped, latency-sensitive tasks that are not intelligence-sensitive |
585| `medium` | Reduces token usage for cost-sensitive work that can trade off some intelligence |
586| `high` | Balances token usage and intelligence. The default on every model except Opus 4.7 |
585| `medium` | Reduces token usage for cost-sensitive work that can trade off some intelligence. The default on Opus 5.5 |
586| `high` | Balances token usage and intelligence. The default on every model except Opus 5.5 and Opus 4.7 |
587587| `xhigh` | Deeper reasoning at higher token spend. The default on Opus 4.7 |
588588| `max` | Can improve performance on demanding tasks but may show diminishing returns and is prone to overthinking. Test before adopting broadly |
589589| `ultracode` | A Claude Code setting that plans a [dynamic workflow](/docs/en/workflows) for each substantive task with `xhigh` per-message reasoning |
from line 603
603603* **`--effort` flag**: pass a level name to set it for a single session when launching Claude Code
604604* **Environment variable**: set `CLAUDE_CODE_EFFORT_LEVEL` to a level name or `auto`
605605* **Settings**: set a per-model level in [`modelSettings`](/docs/en/settings-reference#modelsettings), or set [`effortLevel`](/docs/en/settings-reference#effortlevel) to `low`, `medium`, `high`, or `xhigh` as the default for models without one. `max` isn't accepted as a level in either key, and `ultracode` has its own [`ultracode`](/docs/en/settings-reference#ultracode) key
606* **From a connected device**: in a [Remote Control](/docs/en/remote-control#what-connected-devices-see) session, pick a level from the effort control on your phone or in your browser. The level applies to the current session only, though it also ends the [hold on the model's default effort](#adjust-effort-level). Requires Claude Code v2.1.234 or later
606* **From a connected device**: in a [Remote Control](/docs/en/remote-control#what-connected-devices-see) session, pick a level from the effort control on your phone or in your browser. The level applies to the current session only. Requires Claude Code v2.1.234 or later
607607* **Skill and subagent frontmatter**: set `effort` in a [skill](/docs/en/skills#frontmatter-reference) or [subagent](/docs/en/sub-agents#supported-frontmatter-fields) markdown file to override the effort level when that skill or subagent runs
608608
609609Frontmatter effort applies when that skill or subagent is active, overriding the session level but not the environment variable. A [`maxEffortLevel`](/docs/en/settings-reference#maxeffortlevel) or [organization effort cap](#organization-effort-limits) still limits the level the skill or subagent runs at.
610610
611On Fable 5, Opus 4.8, and Opus 4.7, frontmatter effort also applies while the [hold on the model's default effort](#adjust-effort-level) is in effect. Before v2.1.267, the hold took precedence and Claude Code ignored the frontmatter level while the hold was active.
612
613611If you set `effortLevel` in [managed settings](/docs/en/managed-settings), Claude Code applies it at the settings step of the [effort resolution order](#adjust-effort-level), and users can still change the level with `/effort` or `--effort`. To keep users at or below a level, set [`maxEffortLevel`](/docs/en/settings-reference#maxeffortlevel).
614612
615613The effort slider appears in `/model` when a supported model is selected. The current effort level is also shown in the session header next to the model name, for example "with low effort", so you can confirm which setting is active without opening `/model`. The footer also briefly shows the effort level at startup and when it changes.
from line 624
626624
627625Extended thinking is the reasoning Claude emits before responding. On models that support [adaptive reasoning](#adjust-effort-level), the effort level is the primary control for how much thinking happens; the settings below turn thinking on or off and control how it displays. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.
628626
629| Control | How to set it |
630| :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
631| Toggle for the current session | Press `Option+T` on macOS or `Alt+T` on Windows and Linux |
632| Set the global default | Run `/config` and toggle thinking mode. Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |
633| Disable through an environment variable | Set [`MAX_THINKING_TOKENS=0`](/docs/en/env-vars), which turns thinking off on the Anthropic API except on Fable models. On [third-party providers](/docs/en/third-party-integrations), Claude Code omits the `thinking` parameter instead, and adaptive-reasoning models may still think. Other values apply only with a [fixed thinking budget](#adaptive-reasoning-and-fixed-thinking-budgets) |
627| Control | How to set it |
628| :-------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
629| Toggle for the current session | Press `Option+T` on macOS or `Alt+T` on Windows and Linux |
630| Set the global default | Run `/config` and toggle thinking mode. Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |
631| Disable through an environment variable | Set [`MAX_THINKING_TOKENS=0`](/docs/en/env-vars), which turns thinking off on the Anthropic API except on Opus 5.5 and Fable models. On [third-party providers](/docs/en/third-party-integrations), Claude Code omits the `thinking` parameter instead, and adaptive-reasoning models may still think. Other values apply only with a [fixed thinking budget](#adaptive-reasoning-and-fixed-thinking-budgets) |
634632
635You can't turn thinking off on Fable models. The session toggle, `alwaysThinkingEnabled`, and `MAX_THINKING_TOKENS=0` have no effect there, and a Fable model decides per step how much to think based on the effort level.
633You can't turn thinking off on Opus 5.5 or the Fable models. The session toggle, `alwaysThinkingEnabled`, and `MAX_THINKING_TOKENS=0` have no effect there, and the model decides per step how much to think based on the effort level.
636634
637635Claude Code collapses thinking output by default. Press `Ctrl+O` to toggle verbose mode and see the reasoning as gray italic text. Interactive sessions on the Anthropic API receive redacted thinking blocks by default, so set `showThinkingSummaries: true` in [settings](/docs/en/settings) if you want the full summaries available when you expand. You are charged for all thinking tokens generated, even when collapsed or redacted.
638636
from line 706
708706If you don't set an auto-compact window, Claude Code compacts when the conversation reaches the model's context limit, except in these sessions:
709707
710708* [Cloud sessions](/docs/en/claude-code-on-the-web) compact as the conversation approaches the model's limit
711* Sonnet 4.6 and Opus 4.6 without [extended context](#extended-context) compact at the 200K boundary, and so do Opus 4.8 and Opus 5 when they run with a 200K context window, such as on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry
709* Sonnet 4.6 and Opus 4.6 without [extended context](#extended-context) compact at the 200K boundary, and so do Opus 4.8 and later when they run with a 200K context window, such as on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry
712710* When you set [`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`](/docs/en/env-vars), models with a native 1M window, such as Sonnet 5 and the Fable models, compact at the 200K boundary
713711* Models running with a native 1M window, such as Sonnet 5, the Fable models, and Opus 4.7 and later on the Anthropic API, compact before the window fills, at about 967K tokens by default. On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, [Pin models for third-party deployments](#pin-models-for-third-party-deployments) says which models run with that window; for the configurations that budget Sonnet 5 at 200K instead, see [Sonnet 5 context window](#sonnet-5-context-window)
714712* Sessions on a model ID Claude Code doesn't recognize, such as an [LLM gateway](/docs/en/llm-gateway) alias, compact at the context window Claude Code assumes for the ID; see [Correct the window for a gateway or custom model ID](#correct-the-window-for-a-gateway-or-custom-model-id)
from line 745
747745This example sets all three variables to make a gateway-routed Opus deployment selectable. Claude Code reads environment variables at startup, so run the exports before launching `claude`, or restart an existing session to pick them up:
748746
749747```bash theme={null}
750export ANTHROPIC_CUSTOM_MODEL_OPTION="my-gateway/claude-opus-5"
748export ANTHROPIC_CUSTOM_MODEL_OPTION="my-gateway/claude-opus-5-5"
751749export ANTHROPIC_CUSTOM_MODEL_OPTION_NAME="Opus via Gateway"
752750export ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION="Custom deployment routed through the internal LLM gateway"
753751```
from line 761
763761
764762When [`availableModels`](#restrict-model-selection) is set, include the custom model ID in the allowlist as well. Otherwise Claude Code filters the custom entry from the picker and rejects a `--model` selection of it like any other excluded model.
765763
766A custom ID that embeds a family name, such as `my-gateway/claude-opus-5`, counts as a specific entry for that family and disables its wildcard, so also list the versions you intend to keep selectable. See [Merge behavior](#merge-behavior).
764A custom ID that embeds a family name, such as `my-gateway/claude-opus-5-5`, counts as a specific entry for that family and disables its wildcard, so also list the versions you intend to keep selectable. See [Merge behavior](#merge-behavior).
767765
768766## Environment variables
769767
settings-example Changed · +7 / -3 lines
from line 23
2323 ```json ~/.claude/settings.json theme={null}
2424 {
2525 "model": "claude-sonnet-5",
26 "effortLevel": "xhigh",
26 "modelSettings": {
27 "claude-sonnet-5": { "effortLevel": "xhigh" }
28 },
2729 "editorMode": "vim",
2830 "theme": "light-daltonized",
2931 "statusLine": {
from line 54
5254 {
5355 // Start every session on Sonnet 5
5456 "model": "claude-sonnet-5",
55 // Reason more deeply than the default high level on models without a saved level; /effort saves a level per model, and --effort sets one for a single session
56 "effortLevel": "xhigh",
57 // Run Sonnet 5 above its default high level; /effort saves a level per model, and --effort sets one for a single session
58 "modelSettings": {
59 "claude-sonnet-5": { "effortLevel": "xhigh" }
60 },
5761 // Vim keybindings in the prompt
5862 "editorMode": "vim",
5963 // The colorblind-friendly light theme
settings-reference Changed · +11 / -11 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 830
830830If your account requires the [usage-credits consent](/docs/en/advisor#fable-advisor-and-usage-credits), accept it first by running `/model fable`. Until you do, picking Fable in `/advisor` saves nothing and Claude Code tells you to run `/model fable` first.
831831
832832* **Scope**: [`Any file`](#scopes)
833* **Type**: string, one of the aliases `"fable"`, `"opus"`, or `"sonnet"`, which resolve to Claude Code's current default version of that model family, or a full model ID such as `"claude-opus-5"`
833* **Type**: string, one of the aliases `"fable"`, `"opus"`, or `"sonnet"`, which resolve to Claude Code's current default version of that model family, or a full model ID such as `"claude-opus-5-5"`
834834* **Default**: unset, so the advisor is off
835835* **Per-session overrides**: `--advisor` takes precedence over this key for one session. [`CLAUDE_CODE_DISABLE_ADVISOR_TOOL`](/docs/en/env-vars) turns the advisor off, and this key can't turn it back on
836836
from line 846
846846
847847Turn [extended thinking](/docs/en/model-config#extended-thinking) off for every session by setting this to `false`. Thinking is on by default, so `true` changes nothing. Most people set this through `/config` rather than by editing the file.
848848
849On models that always think, such as the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` parameter instead of turning thinking off, so adaptive-reasoning models may still think. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.
849On models that always think, such as Opus 5.5 and the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` parameter instead of turning thinking off, so adaptive-reasoning models may still think. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.
850850
851851* **Scope**: [`Any file`](#scopes)
852852* **Type**: Boolean
from line 887
887887
888888Within the same settings file, Claude Code uses a model's saved level rather than this key. [`modelSettings`](#modelsettings) states the cross-file precedence.
889889
890In a session attached to a remote worker, `/effort` applies to that session only. In a `-p` run or the Agent SDK it also applies to that session only, [unless a hold on the model's default effort is in effect](/docs/en/model-config#non-interactive-effort). [Adjust effort level](/docs/en/model-config#adjust-effort-level) lists the interactive picks that also apply to that session only. The message that `/effort` prints says which happened.
890In a session attached to a remote worker, in a `-p` run, and in the Agent SDK, `/effort` applies to that session only. [Adjust effort level](/docs/en/model-config#adjust-effort-level) lists the interactive picks that also apply to that session only. The message that `/effort` prints says which happened.
891891
892892* **Scope**: [`Any file`](#scopes)
893893* **Type**: string, one of:
from line 904
904904}
905905```
906906
907On Opus 4.7, Opus 4.8, and Fable 5, Claude Code holds that model's default effort, organization-set or built-in; [Adjust effort level](/docs/en/model-config#adjust-effort-level) states which ways of setting a level end the hold and which leave it in place. Once the hold ends, Claude Code resolves effort by the precedence stated at [`modelSettings`](#modelsettings).
907In your user settings file, `~/.claude/settings.json`, this key is the older form `/effort` wrote before it saved levels per model, and it keeps applying where it applied before, on Opus 5, Fable 5.1, and earlier models. Opus 5.5 and models released after it ignore it and start at their own default until you save a level for them, which `/effort` writes under [`modelSettings`](#modelsettings). In project, local, and managed settings, and with `--settings`, this key applies to every model.
908908
909909### `enforceAvailableModels`
910910
from line 952
952952
953953### `fastMode`
954954
955Turn [fast mode](/docs/en/fast-mode) on for sessions where it's available, for interactive work like rapid iteration or live debugging where you want speed at a higher cost per token. You don't usually edit this key by hand: running `/fast` writes `fastMode: true` to `~/.claude/settings.json`, and running it again to turn fast mode off removes the key. Fast mode runs only on Opus 5 and Opus 4.8: turning it on from another model switches you to Opus, and switching to an unsupported model turns it off. See [Switch models while fast mode is on](/docs/en/fast-mode#switch-models-while-fast-mode-is-on).
955Turn [fast mode](/docs/en/fast-mode) on for sessions where it's available, for interactive work like rapid iteration or live debugging where you want speed at a higher cost per token. You don't usually edit this key by hand: running `/fast` writes `fastMode: true` to `~/.claude/settings.json`, and running it again to turn fast mode off removes the key. Fast mode runs only on Opus 5.5, Opus 5, and Opus 4.8: turning it on from another model switches you to Opus, and switching to an unsupported model turns it off. See [Switch models while fast mode is on](/docs/en/fast-mode#switch-models-while-fast-mode-is-on).
956956
957957* **Scope**: [`Any file`](#scopes)
958958* **Type**: Boolean
from line 1172
11721172
11731173Edit the key by hand to change or remove a level you saved.
11741174
1175A model's `effortLevel` here takes precedence over the top-level [`effortLevel`](#effortlevel) in the same settings file. Across files, Claude Code resolves each model separately: the highest-precedence [settings file](/docs/en/settings#settings-precedence) that sets either an `effortLevel` for that model or the top-level `effortLevel` decides, so an `effortLevel` in managed settings outranks a level you saved in user settings. [Adjust effort level](/docs/en/model-config#adjust-effort-level) lists what else can override a saved level, such as `--effort` at launch.
1175A model's `effortLevel` here takes precedence over the top-level [`effortLevel`](#effortlevel) in the same settings file. Across files, Claude Code resolves each model separately: the highest-precedence [settings file](/docs/en/settings#settings-precedence) that sets either an `effortLevel` for that model or a top-level `effortLevel` that [applies to that model](#effortlevel) decides, so an `effortLevel` in managed settings outranks a level you saved in user settings. [Adjust effort level](/docs/en/model-config#adjust-effort-level) lists what else can override a saved level, such as `--effort` at launch.
11761176
11771177To cap one model's effort rather than set its level, add a [`maxEffortLevel`](#maxeffortlevel) field to that model's entry. The field requires Claude Code v2.1.267 or later.
11781178
from line 1180
11801180* **Type**: object mapping a model name to an object with an `effortLevel` field, one of `"low"`, `"medium"`, `"high"`, or `"xhigh"`, a [`maxEffortLevel`](#maxeffortlevel) field, or both
11811181* **Default**: unset
11821182
1183Claude Code writes each entry under the model's canonical name, such as `claude-opus-5`, and matches that model's alias, date-suffixed, `[1m]`, and recognized provider-specific IDs to the same entry.
1183Claude Code writes each entry under the model's canonical name, such as `claude-opus-5-5`, and matches that model's alias, date-suffixed, `[1m]`, and recognized provider-specific IDs to the same entry.
11841184
1185This example keeps Opus 5 at `medium` while other models use their own saved or default levels:
1185This example keeps Opus 5.5 at `high` while other models use their own saved or default levels:
11861186
11871187```json settings.json theme={null}
11881188{
11891189 "modelSettings": {
1190 "claude-opus-5": {
1191 "effortLevel": "medium"
1190 "claude-opus-5-5": {
1191 "effortLevel": "high"
11921192 }
11931193 }
11941194}
from line 3220
32203220* **Type**: Boolean
32213221 * `true`: Claude Code adds the command's output to the conversation and Claude replies to it
32223222 * `false`: Claude Code adds the output to context without a reply
3223* **Default**: `true`
3224
3225```json settings.json theme={null}
3226{
3227 "respondToB
3223* **Default**: `
advisor Changed · +2 / -2 lines
from line 90
9090| Sonnet 5 | Fable, Opus 4.7 or later, Sonnet 5 | A Sonnet 4.6 advisor is rejected, and the API refuses an Opus 4.6 advisor |
9191| Opus 4.6 | Fable, Opus, Sonnet 5 | A Sonnet 4.6 advisor is rejected |
9292| Opus 4.7 or Opus 4.8 | Fable, and Opus 4.7 or later | An Opus 4.6 or Sonnet advisor is rejected |
93| Opus 5 | Fable, Opus 5 | An Opus 4.6 or Sonnet advisor is rejected, and the API refuses an Opus 4.7 or Opus 4.8 advisor |
93| Opus 5.5 or Opus 5 | Fable, and Opus 5 or later | An Opus 4.6 or Sonnet advisor is rejected, and the API refuses an Opus 4.7 or Opus 4.8 advisor |
9494| Fable 5 | Fable 5.1 or Fable 5 | An Opus or Sonnet advisor is rejected |
9595| Fable 5.1 | Fable 5.1 | An Opus or Sonnet advisor is rejected, and the API refuses a Fable 5 advisor |
9696
9797Fable 5.1 requires Claude Code v2.1.257 or later. Both Fable models require [Fable access](/docs/en/model-config#work-with-fable).
9898
99Set the advisor as `fable`, `opus`, or `sonnet`. These aliases resolve to Claude Code's built-in default version for each model family, which advances with new Claude Code releases. You can also pass a full model ID such as `claude-opus-5`.
99Set the advisor as `fable`, `opus`, or `sonnet`. These aliases resolve to Claude Code's built-in default version for each model family, which advances with new Claude Code releases. You can also pass a full model ID such as `claude-opus-5-5`.
100100
101101Subagents inherit the configured advisor and apply the same pairing check against their own model.
102102
agent-sdk/python Changed · +1 / -1 lines
from line 1345
13451345Use with the `betas` field in `ClaudeAgentOptions` to enable beta features.
13461346
13471347<Warning>
1348 The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this header with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-token context window return an error. To use a 1M-token context window, migrate to [Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.6, Claude Opus 4.7, or Claude Opus 4.8](https://platform.claude.com/docs/en/about-claude/models/overview), which include 1M context at standard pricing with no beta header required.
1348 The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this header with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-token context window return an error. To use a 1M-token context window, migrate to [Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.6, Claude Opus 4.7, or Claude Opus 4.8](https://platform.claude.com/docs/en/about-claude/models/overview), which include 1M context at standard pricing with no beta header required.
13491349</Warning>
13501350
13511351### `McpSdkServerConfig`
agent-sdk/typescript Changed · +1 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
Nothing in the body moved in this read. What changed is above.
claude-code-on-the-web Changed · +1 / -1 lines
from line 218
218218
219219Cloud sessions support [built-in commands](/docs/en/commands) that produce text output. Commands that only run in the terminal interface, such as `/plugin` or `/resume`, aren't available. Commands that open a picker or panel in the terminal behave differently in cloud sessions:
220220
221* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms require Claude Code v2.1.205 or later in the session's environment and follow each command's [availability notes](/docs/en/commands#all-commands): `/effort` reports `Not applied` while a model's [launch-default effort hold](/docs/en/model-config#adjust-effort-level) is in force.
221* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms require Claude Code v2.1.205 or later in the session's environment and follow each command's [availability notes](/docs/en/commands#all-commands).
222222* **`/fast`**: toggles [fast mode](/docs/en/fast-mode#use-fast-mode-in-cloud-sessions) for the session when fast mode is [available on your account](/docs/en/fast-mode#requirements). Requires Claude Code v2.1.271 or later in the session's environment.
223223* **`/config`**: in your browser at claude.ai/code, opens the Claude Code section of your settings instead of setting a value, and text after the command, including `key=value`, is ignored. To change a setting for a cloud session, set an [environment variable](/docs/en/cloud-environments#set-environment-variables) on the environment, or in a session with one repository, commit the key to that repository's `.claude/settings.json`. [Settings in cloud sessions](/docs/en/settings#settings-in-cloud-sessions) lists what each session reads.
224224
claude-platform-on-aws Changed · +1 / -1 lines
from line 270
270270
271271Claude Platform on AWS uses the same model IDs as the direct Claude API.
272272
273The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias resolves to Opus 5. Before v2.1.219, it resolved to Opus 4.8, and before v2.1.207 to Opus 4.7.
273The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias resolves to Opus 5.5. Before v2.1.280, it resolved to Opus 5 from v2.1.219, to Opus 4.8 from v2.1.207, and to Opus 4.7 before that.
274274
275275If you deploy Claude Code to a team, pin the model IDs explicitly so a new release doesn't move everyone at once:
276276
commands Changed · +1 / -1 lines
from line 77
7777| `/desktop` | Continue the current session in the Claude Code Desktop app. Requires macOS or x64 Windows and a Claude subscription. Alias: `/app` |
7878| `/diff` | Review the changes in your working tree, including the edits Claude has made so far. See [Review changes with /diff](/docs/en/interactive-mode#review-changes-with-%2Fdiff) |
7979| `/doctor` | **[Skill](/docs/en/skills#bundled-skills).** Run a setup checkup that diagnoses issues and can fix them. Checks installation health, including duplicate or leftover installs, `PATH` problems, and unparseable settings files. Finds unused skills, MCP servers, and plugins versus their context cost, flags slow [hooks](/docs/en/hooks), and checks for a newer version on your [release channel](/docs/en/setup#configure-release-channel). Deduplicates local `CLAUDE.md` files against checked-in ones, trims checked-in [`CLAUDE.md`](/docs/en/memory#my-claude-md-is-too-large) files by cutting content Claude could derive from the codebase, and migrates the always-loaded guidance that remains into [skills](/docs/en/skills) and nested `CLAUDE.md` files that load on demand. Also offers to make [auto mode](/docs/en/permissions#permission-modes) your default and to [pre-approve](/docs/en/permissions) frequently denied read-only commands. Reports findings first and asks for confirmation before changing anything. From the terminal, `claude doctor` prints read-only installation diagnostics without starting a session. Alias: `/checkup`. The `CLAUDE.md` trim check requires Claude Code v2.1.206 or later. Before v2.1.205, `/doctor` opened a read-only diagnostics screen and pressing `f` sent the report to Claude |
80| `/effort [level\|auto\|status]` | Set the [effort level](/docs/en/model-config#adjust-effort-level): `low` to `xhigh`, `max`, [`ultracode`](/docs/en/workflows#let-claude-decide-with-ultracode), or `auto`; `status` prints it. `max` and `ultracode` are session-only; the [`ultracode`](/docs/en/settings-reference#ultracode) key persists. Run it while Claude is responding and, once you confirm the [cache warning](/docs/en/prompt-caching#changing-effort-level), if Claude Code shows one, Claude Code applies the new level to the next request in that turn. Before v2.1.242, Claude Code decided from a feature flag it fetched from Anthropic whether to run the command mid-turn or queue it until the turn finished, and always queued it in a session that doesn't [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), such as on a [third-party provider](/docs/en/third-party-integrations). Works in `-p` outside the [effort hold](/docs/en/model-config#adjust-effort-level) |
80| `/effort [level\|auto\|status]` | Set the [effort level](/docs/en/model-config#adjust-effort-level): `low` to `xhigh`, `max`, [`ultracode`](/docs/en/workflows#let-claude-decide-with-ultracode), or `auto`; `status` prints it. `max` and `ultracode` are session-only; the [`ultracode`](/docs/en/settings-reference#ultracode) key persists. Run it while Claude is responding and, once you confirm the [cache warning](/docs/en/prompt-caching#changing-effort-level), if Claude Code shows one, Claude Code applies the new level to the next request in that turn. Before v2.1.242, Claude Code decided from a feature flag it fetched from Anthropic whether to run the command mid-turn or queue it until the turn finished, and always queued it in a session that doesn't [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), such as on a [third-party provider](/docs/en/third-party-integrations). Works in `-p` |
8181| `/exit` | Exit the CLI. In an attached [background session](/docs/en/agent-view#attach-to-a-session), this detaches and the session keeps running. Alias: `/quit` |
8282| `/export [filename]` | Export the current conversation as plain text. With a filename, writes directly to that file. Without, opens a dialog to copy to clipboard or save to a file |
8383| `/fast [on\|off]` | Toggle [fast mode](/docs/en/fast-mode) on or off. Run it while Claude is responding and Claude Code toggles fast mode without waiting for the turn to end, though the running turn finishes at its original speed. Before v2.1.242, Claude Code decided from a feature flag it fetched from Anthropic whether to run the command mid-turn or queue it until the turn finished, and always queued it in a session that doesn't [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching). Availability in non-interactive mode with `-p` is limited; see [Toggle fast mode](/docs/en/fast-mode#toggle-fast-mode). Requires Claude Code v2.1.205 or later |
costs Changed · +2 / -2 lines
from line 233
233233
234234### Choose the right model
235235
236Sonnet handles most coding tasks well and costs less than Opus. Reserve Opus for complex architectural decisions or multi-step reasoning. Use `/model` to switch models mid-session, or set a default in `/config`. For simple subagent tasks, specify `model: haiku` in your [subagent configuration](/docs/en/sub-agents#choose-a-model).
236Sonnet handles most coding tasks well and costs less than Opus. Reserve Opus for complex architectural decisions or multi-step reasoning. Use `/model` to switch models mid-session, or set a default in `/config`. A switch to Opus also applies to the [subagents that inherit your session's model](/docs/en/model-config#setting-your-model). For simple subagent tasks, specify `model: haiku` in your [subagent configuration](/docs/en/sub-agents#choose-a-model).
237237
238238### Reduce MCP server overhead
239239
from line 307
307307
308308Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the default budget can be tens of thousands of tokens per request depending on the model.
309309
310For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, or by disabling thinking in `/config`. You can't turn off thinking on Fable models, which always use extended thinking.
310For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, or by disabling thinking in `/config`. You can't turn off thinking on Opus 5.5 or the Fable models, which always use extended thinking.
311311
312312On models with a [fixed thinking budget](/docs/en/model-config#adaptive-reasoning-and-fixed-thinking-budgets), you can also lower the budget by setting the `MAX_THINKING_TOKENS` [environment variable](/docs/en/env-vars), for example `MAX_THINKING_TOKENS=8000`. Adaptive-reasoning models ignore nonzero budgets, so use effort levels there instead.
313313
desktop Changed · +1 / -1 lines
from line 641
641641
642642To set environment variables for local sessions and dev servers on any platform, open the environment dropdown in the prompt box, hover over **Local**, and click the gear icon to open the local environment editor. Variables you save here are stored encrypted on your machine and apply to every local session and preview server you start. You can also add variables to the `env` key in your `~/.claude/settings.json` file, though these reach Claude sessions only and not dev servers. See [environment variables](/docs/en/env-vars) for the full list of supported variables.
643643
644[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthropic API, set `MAX_THINKING_TOKENS` to `0` in the local environment editor to turn thinking off; this has no effect on Fable models, which always use extended thinking. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.
644[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthropic API, set `MAX_THINKING_TOKENS` to `0` in the local environment editor to turn thinking off; this has no effect on Opus 5.5 or the Fable models, which always use extended thinking. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.
645645
646646On models with [adaptive reasoning](/docs/en/model-config#adjust-effort-level), `MAX_THINKING_TOKENS` values other than `0` are ignored because adaptive reasoning controls thinking depth instead. On Opus 4.6 and Sonnet 4.6, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` to `1` to use a fixed thinking budget; Fable models, Sonnet 5, and Opus 4.7 and later always use adaptive reasoning and have no fixed-budget mode.
647647
github-actions Changed · +1 / -1 lines
from line 272
272272 anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
273273 prompt: "Generate a summary of yesterday's commits and open issues"
274274 claude_args: |
275 --model claude-opus-4-8
275 --model claude-opus-5-5
276276 --allowedTools "mcp__github__list_commits,mcp__github__list_issues"
277277```
278278
interactive-mode Changed · +1 / -1 lines
from line 34
3434| `Ctrl+Enter` or `Ctrl+X Ctrl+S` | Send queued messages now | Interrupts the current turn so your [queued messages](#queue-messages-while-claude-works), and your draft with them, go out right away instead of when the turn ends. In [shell mode](#shell-mode-with-prefix), the key queues your command without interrupting. In terminals that don't report extended keys, `Ctrl+Enter` arrives as plain `Enter`; `Ctrl+X Ctrl+S` works in any terminal. Requires Claude Code v2.1.275 or later |
3535| `Shift+Tab`, or `Alt+M` on Windows when the Node or Bun runtime doesn't enable VT input mode | Cycle permission modes | Cycle through `default` (labeled Manual in the mode indicator), `acceptEdits`, `plan`, and, when available, `bypassPermissions` and then `auto`. From `auto`, the first press switches to `default`. See [permission modes](/docs/en/permission-modes). On a file permission prompt, the same key closes an open [comment field](/docs/en/permissions#add-a-comment-when-you-answer-a-permission-prompt). With no field open, it selects the option that allows the action for the rest of the session, when the prompt offers that option |
3636| `Option+P` (macOS) or `Alt+P` (Windows/Linux) | Switch model | Switch models without clearing your prompt |
37| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Fable 5.1 or Fable 5, which always use extended thinking. Works on macOS without configuring Option as Meta |
37| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Opus 5.5 or the Fable models, which always use extended thinking. Works on macOS without configuring Option as Meta |
3838| `Option+O` (macOS) or `Alt+O` (Windows/Linux) | Toggle fast mode | Enable or disable [fast mode](/docs/en/fast-mode) |
3939
4040### Text editing
prompt-caching Changed · +1 / -1 lines
from line 84
8484
8585The [`opusplan` model setting](/docs/en/model-config#opusplan-model-setting) resolves to Opus during plan mode and Sonnet during execution, so each plan-mode toggle is a model switch and starts a fresh cache.
8686
87[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models and Opus 5 is also a model switch. When a safety classifier flags a request in a category that has a fallback model, Claude Code re-runs the request on that model and the session continues there.
87[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models, Opus 5.5, and Opus 5 is also a model switch. When a safety classifier flags a request in a category that has a fallback model, Claude Code re-runs the request on that model and the session continues there.
8888
8989When a skill or command's frontmatter names a [`model`](/docs/en/skills#frontmatter-reference) other than the session's current model, that turn is also a model switch: the next request reads the entire conversation history with no cache hits. The session model resumes on your next prompt. A `context: fork` skill sets the [forked subagent's model](/docs/en/skills#run-skills-in-a-subagent) instead.
9090
statusline Changed · +1 / -1 lines
from line 218
218218 "prompt_id": "550e8400-e29b-41d4-a716-446655440000",
219219 "transcript_path": "/path/to/transcript.jsonl",
220220 "model": {
221 "id": "claude-opus-5",
221 "id": "claude-opus-5-5",
222222 "display_name": "Opus"
223223 },
224224 "workspace": {
sub-agents Changed · +2 / -2 lines
from line 291
291291| `description` | Yes | When Claude should delegate to this subagent |
292292| `tools` | No | [Tools](#available-tools) the subagent can use, as a comma-separated string such as `Read, Grep, Bash` or a YAML list. Inherits every tool available to subagents if omitted. If no entry in the list resolves to a tool, the subagent usually [fails to launch](/docs/en/errors#agent-would-be-spawned-with-zero-tools) with an error naming the entries. To preload Skills into context, use the `skills` field rather than listing `Skill` here |
293293| `disallowedTools` | No | Tools to deny, removed from inherited or specified list. Same format as `tools`. An entry with a specifier, such as `Bash(git push *)`, still [removes the whole tool](#available-tools) |
294| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, `fable`, a full model ID such as `claude-opus-5`, or `inherit`. When you omit it, Claude Code picks the model in the [subagent model order](#choose-a-model) |
294| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, `fable`, a full model ID such as `claude-opus-5-5`, or `inherit`. When you omit it, Claude Code picks the model in the [subagent model order](#choose-a-model) |
295295| `permissionMode` | No | [Permission mode](#permission-modes): `default`, `acceptEdits`, `auto`, `dontAsk`, `bypassPermissions`, `plan`, or `manual` as an alias for `default`. The `manual` alias requires Claude Code v2.1.200 or later. Ignored for [plugin subagents](#choose-the-subagent-scope) |
296296| `maxTurns` | No | Maximum number of agentic turns before the subagent stops. When the subagent reaches the limit, Claude Code returns its output marked as partial, and Claude can [resume it](#resume-subagents) to continue. The partial marking requires Claude Code v2.1.246 or later |
297297| `skills` | No | [Skills](/docs/en/skills) to preload into the subagent's context at startup. The full skill content is injected, not only the description. Subagents can still invoke unlisted project, user, and plugin skills through the Skill tool |
from line 340
340340The `model` field controls which model the subagent uses:
341341
342342* **Model alias**: use one of the available aliases: `sonnet`, `opus`, `haiku`, or `fable`
343* **Full model ID**: use a full model ID such as `claude-opus-5` or `claude-sonnet-5`. Accepts the same values as the `--model` flag
343* **Full model ID**: use a full model ID such as `claude-opus-5-5` or `claude-sonnet-5`. Accepts the same values as the `--model` flag
344344* **inherit**: use the same model as the main conversation
345345
346346When Claude invokes a subagent, it can also pass a `model` parameter for that specific invocation. Claude Code resolves the subagent's model in this order: