Docs search: models / page 8 of 12 / Source Intelligence

mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …l/aup). These attacks fall into two categories with different threat models: * **Jailbreaks and direct prompt injection**, where the *user* of your application is the adversary and crafts inputs int…

reduce-hallucinations Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-hallucinations …verifying claims with citations. --- Even the most advanced language models, such as Claude, can sometimes generate text that is factually incorrect or inconsistent with the given context. This pheno…

reduce-latency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-latency …the appropriate model for your use case. Anthropic offers a [range of models](https://platform.claude.com/docs/en/models/overview) with different capabilities and performance characteristics. Consider…

reduce-prompt-leak Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-prompt-leak …ant` turn. (Note: prefilling is not supported on Claude 4.6 and later models and [Claude Mythos Preview](https://anthropic.com/glasswing).) <Accordion title="Example: Safeguarding proprietary analyti…

Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …anaged lists but not remove from them. For `fallbackModel`, `availableModels`, and [`modelPicker`](https://code.claude.com/docs/en/settings-reference#modelpicker), the managed value replaces lower lay…

Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …sor` without arguments to open a picker listing the available advisor models, or pass the model directly: ``` /advisor opus ``` The command confirms with `Advisor set to` followed by the advisor mod…

How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …Spawn subagents, invoke skills, ask the user, track tasks | On the [models that don't get the task-tracking tools](https://code.claude.com/docs/en/agent-sdk/todo-tracking.md#model-availability), Cla…

Configure your agent Claude Code CLI · in the page agent-sdk/configuration …cached at the new model's rates. For more information, see [Switching models](https://code.claude.com/docs/en/prompt-caching.md#switching-models). ## Configure specific features The table below maps…

Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …per-model token counts and cost. This is useful when you run multiple models (for example, Haiku for subagents and Opus for the main agent) and want to see where tokens are going. Each entry's `costB…

Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …onversation compaction completes | Log the generated summary | | [`PreModelSwitch`](https://code.claude.com/docs/en/hooks#premodelswitch) | No | Yes | A requested model switch, before it happens (can…

Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …inside a user message wrapped in `<system-reminder>` tags or, on some models, as a separate message with the `system` role. ## Compare the four approaches The four customization methods differ in wh…

Configure permissions Claude Code CLI · in the page agent-sdk/permissions …ts before they run, and allows or blocks each one it reviews. For the models and providers auto mode requires and the order it evaluates actions in, see [Eliminate permission prompts with auto mode](h…

Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …ecific IDs](https://code.claude.com/docs/en/model-config.md#available-models) | | `fallback_model` | `str \| None` | `None` | Fallback model to use if the primary model fails. Accepts a comma-separate…

Securely deploying AI agents Claude Code CLI · in the page agent-sdk/secure-deployment …instructions embedded in content they process) or model error. Claude models are designed to resist this; see the [model overview](https://platform.claude.com/docs/en/about-claude/models/overview) and…

Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …gents Claude Opus 5 delegates to subagents more readily than earlier models, so the [depth, concurrency, and spend limits](#cap-subagent-depth-concurrency-and-spend) matter most on queries that run O…

Track todos Claude Code CLI · in the page agent-sdk/todo-tracking …/en/tools-reference.md#task-tool-availability) by default only on the models listed under [Model availability](#model-availability). Newer models track multi-step work without a written todo list, so…

Scale to many tools with tool search Claude Code CLI · in the page agent-sdk/tool-search …itself. ## Configure tool search Tool search is on by default. For models on the SDK's unsupported-model list, the SDK loads tool definitions upfront instead, and no `ENABLE_TOOL_SEARCH` value over…

Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …ecific IDs](https://code.claude.com/docs/en/model-config.md#available-models) | | `onElicitation` | `(request: ElicitationRequest, options: { signal: AbortSignal }) => Promise<ElicitationResult>` | `u…

Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …s → General → Magic → Enable Python API**. ### Specify teammates and models Claude decides the number of teammates to spawn based on your task, or you can specify exactly what you want: ```text wra…

Manage multiple agents with agent view Claude Code CLI · in the page agent-view …starts with fast mode off, so first use `/model` to pick one of the [models that support fast mode](https://code.claude.com/docs/en/fast-mode.md). The hint under the input, not the header, confirms w…

Claude Code on Amazon Bedrock Claude Code CLI · in the page amazon-bedrock …account with Amazon Bedrock access enabled * Access to desired Claude models (for example, Claude Sonnet 4.6) in Amazon Bedrock * AWS CLI installed and configured (optional - only needed if you don't…

Configure auto mode Claude Code CLI · in the page auto-mode-config ….md#eliminate-prompts-with-auto-mode), which also cover the supported models and the organization-level control on Team and Enterprise plans. By default, the classifier trusts only the working direct…

Best practices for Claude Code Claude Code CLI · in the page best-practices …n stop doing](#what-you-can-stop-doing) lists the advice that current models have made unnecessary. > [!NOTE] > > Setup for a whole team is on a separate page: [Set up Claude Code for your organizati…

Claude Code changelog Claude Code CLI · in the page changelog …et-aside` **15 improvements** * Improved the `/model` picker: "More models" is now an unnumbered row below every other, and older models open under it without renumbering the rest * Gateway: Improve…

Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry Claude Code CLI · in the page claude-apps-gateway …enforces model access server-side, rejecting requests for non-granted models, and selects each group's managed settings policy, which the CLI applies at the [managed settings tier](https://code.claude…

Claude apps gateway configuration Claude Code CLI · in the page claude-apps-gateway-config …plier for the spend meter and for the cost figures developers see * [`models`](#models) and `auto_include_builtin_models`: admin-curated model list and per-upstream IDs * [`managed`](#managed): manage…

Deploy Claude apps gateway on AWS Claude Code CLI · in the page claude-apps-gateway-on-aws …sign in to through your IdP. Their Claude Code sessions reach Claude models on Amazon Bedrock through the gateway's IAM role, so no model credentials land on developer machines. The reference configu…

Deploy Claude apps gateway on Google Cloud Claude Code CLI · in the page claude-apps-gateway-on-gcp …er on the VPC created in the walkthrough below * Access to the Claude models you need in Model Garden, in a region that publishes them * A Google Workspace OAuth 2.0 web-application client with redire…

Claude apps gateway spend limits Claude Code CLI · in the page claude-apps-gateway-spend-limits …ent Platform, and Microsoft Foundry ID forms. 3. List price for the [`models[].id`](https://code.claude.com/docs/en/claude-apps-gateway-config#models) you mapped to that upstream ID, for upstream stri…

Claude Code on Claude Platform on AWS Claude Code CLI · in the page claude-platform-on-aws …billing. Requests reach Anthropic's API directly, so you get the same models and API features as the [Claude API](https://platform.claude.com/docs) on the same release schedule. You authenticate with…

Let Claude coordinate ongoing work with Projects Claude Code CLI · in the page claude-projects …ead on Opus at high effort, which draws on your plan fastest; [Choose models and let Claude manage context](#choose-models-and-let-claude-manage-context) covers the alternatives. 4. Ask Claude to [pro…

Scan your codebase for vulnerabilities Claude Code CLI · in the page claude-security …y yourself. The plugin runs locally in your session, uses [whichever models you have access to in Claude Code](#models-and-providers), and each scan counts toward your [usage](https://code.claude.com…

claude-tag Claude Code CLI · in the page claude-tag …de Tag remembers</span></div></div></a></li><li id="/claude-tag/users/models" class="relative scroll-m-4 first:scroll-m-20" data-title="Choose the model"><a href="/docs/claude-tag/users/models" class=…

CLI reference Claude Code CLI · in the page cli-reference …v2.1.203 or later. On the main conversation's model, overrides the [`modelSettings`](https://code.claude.com/docs/en/settings-reference#modelsettings) and [`effortLevel`](https://code.claude.com/docs…

Configure cloud environments Claude Code CLI · in the page cloud-environments …laude.com/docs/en/model-config.md#surface-coverage) for how `availableModels` is enforced in cloud sessions. Settings deployed to your device through MDM or managed settings files don't apply, because…

Commands Claude Code CLI · in the page commands …Claude Code from inside a session. They provide a quick way to switch models, manage permissions, clear context, run a workflow, and more. Type `/` to see the commands available to you, or type `/` f…

Common workflows Claude Code CLI · in the page common-workflows …tterns used here ``` ```text wrap theme={null} what are the key data models? ``` ```text wrap theme={null} how is authentication handled? ``` > [!TIP] > > Tips: > > * Start with broad questions, th…

Communications kit Claude Code CLI · in the page communications-kit …rise plan, Anthropic does not use > your code or prompts to train its models. > Details: https://code.claude.com/docs/en/data-usage > https://code.claude.com/docs/en/security > > Where to go…

Explore the context window Claude Code CLI · in the page context-window …If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5 and later, Haiku 5.5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended…

Manage costs effectively Claude Code CLI · in the page costs …: a seat-based usage window on a subscription plan, shared across all models, so the developer can't restore access by switching models with `/model`. The message shows when the window resets. After t…

Data usage Claude Code CLI · in the page data-usage …you the choice to allow your data to be used to improve future Claude models. We will train new models using data from Free, Pro, Max, and Ultra accounts when this setting is on (including when you us…

Desktop application Claude Code CLI · in the page desktop …k a [model](https://code.claude.com/docs/en/model-config.md#available-models) from the model picker toward the right end of the row. You can change the model during the session. Type your task and pr…

Get started with the desktop app Claude Code CLI · in the page desktop-quickstart …del picker toward the right end of the row under the prompt box. See [models](https://code.claude.com/docs/en/model-config.md#available-models) for a comparison of the available models. You can change…

Environment variables Claude Code CLI · in the page env-vars …RTING` * `CLAUDE_CODE_TMUX_TRUECOLOR` * `FALLBACK_FOR_ALL_PRIMARY_MODELS` * `IS_DEMO` One other variable has its own rule: `FORCE_HYPERLINK` reads a number, so only `0` turns it off. Each var…

Error reference Claude Code CLI · in the page errors …nt-switch-to-the-default-model) | | `Model switch ... blocked by a PreModelSwitch hook` | [Request errors](#model-switch-was-blocked-by-a-premodelswitch-hook) | | `couldn't save it as your default` /…

Speed up responses with fast mode Claude Code CLI · in the page fast-mode …arch-preview). Fast mode is a high-speed configuration for supported models, making the model up to 2.5x faster at a higher cost per token. Toggle it on with `/fast` when you need speed for interacti…

Feature availability Claude Code CLI · in the page feature-availability …n.md#sign-in-without-an-api-key) * **Amazon Bedrock**: you use Claude models from the Amazon Bedrock model catalog and set `CLAUDE_CODE_USE_BEDROCK`. The [Mantle endpoint](https://code.claude.com/docs…

Run Claude Code through a gateway Claude Code CLI · in the page gateways …teway products, and doesn't support routing Claude Code to non-Claude models through any gateway. See [Other LLM gateways](https://code.claude.com/docs/en/llm-gateway) for the admin rollout checklist,…

Use Claude Code GitHub Actions with cloud providers Claude Code CLI · in the page github-actions-cloud-providers …ss on your provider: * **Amazon Bedrock**: access granted to Claude models. Cross-region inference profiles, such as the `us.` model IDs in this page's examples, need access granted in every region…