144 pages for medium.

choosing-a-model Claude Developer Platform · in the page about-claude/models/choosing-a-model …n your evals. On Claude Opus 5.5 and Claude Haiku 5.5 the default is `medium`; start there and adjust the same way. On Claude Opus 4.8 and Claude Opus 4.7, the `xhigh` effort level, between `high` and… Or, for the model with the same capabilities and no access approval requirement: Claude Developer Platform · in the page about-claude/models/migration-guide …{"type": "disabled"}, output_config={"effort": "high"}, # or "medium", "low" messages=[{"role": "user", "content": "..."}], ) ``` #### Recommended changes These are not required… optimizing-for-cost-and-intelligence Claude Developer Platform · in the page about-claude/models/optimizing-for-cost-and-intelligence …t agent workloads, start with Claude Opus 5.5 at its default effort (`medium`). A more capable model can finish a task with less work, which can offset much of the per-token premium. Anthropic measur… content-moderation Claude Developer Platform · in the page about-claude/use-case-guides/content-moderation …block user queries that are deemed high risk, whereas users with many medium risk queries are flagged for human review. <CodeGroup exclude="shell"> ```python Python def assess_risk_level(message,… PDF Processing Claude Developer Platform · in the page agents-and-tools/agent-skills/best-practices …and maintainability 4. Verify adherence to project conventions ``` **Medium freedom** (pseudocode or scripts with parameters): Use when: * A preferred pattern exists * Some variation is acceptable… enterprise Claude Developer Platform · in the page agents-and-tools/agent-skills/enterprise …, broad glob patterns, path traversal (`../`) | Medium: might access unintended data | | Tool calls | Instructions directing Claude to use bash,… advisor-tool Claude Developer Platform · in the page agents-and-tools/tool-use/advisor-tool …with effort settings For coding tasks, pairing a Sonnet executor at medium [effort](https://platform.claude.com/docs/en/build-with-claude/effort) with an Opus advisor achieves intelligence comparabl… computer-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/computer-use-tool …sitive workloads. * **Claude Sonnet 4.6 and Claude Opus 4.6:** use `medium` as the default (best accuracy-to-cost ratio). Avoid `max`, which adds token cost without improving accuracy on UI tasks. O… Beta Claude Developer Platform · in the page api/beta …port` Whether the model supports max effort level. - `medium: BetaCapabilitySupport` Whether the model supports medium effort level. - `supported: boolean` Whe… Agents Claude Developer Platform · in the page api/beta/agents …or additional details and options. - `effort: optional "low" or "medium" or "high" or 2 more or BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or 3 more or null` How hard Clau… Archive Agent Claude Developer Platform · in the page api/beta/agents/archive …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `hig… Create Agent Claude Developer Platform · in the page api/beta/agents/create …or additional details and options. - `effort: optional "low" or "medium" or "high" or 2 more or BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or 3 more or null` How hard Clau… List Agents Claude Developer Platform · in the page api/beta/agents/list …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `hig… Get Agent Claude Developer Platform · in the page api/beta/agents/retrieve …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `hig… Update Agent Claude Developer Platform · in the page api/beta/agents/update …or additional details and options. - `effort: optional "low" or "medium" or "high" or 2 more or BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or 3 more or null` How hard Clau… Versions Claude Developer Platform · in the page api/beta/agents/versions …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `hig… List Agent Versions Claude Developer Platform · in the page api/beta/agents/versions/list …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `hig… Messages Claude Developer Platform · in the page api/beta/messages …utput_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may res… Batches Claude Developer Platform · in the page api/beta/messages/batches …t_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may… Create a Message Batch Claude Developer Platform · in the page api/beta/messages/batches/create …t_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may… Count tokens in a Message Claude Developer Platform · in the page api/beta/messages/count_tokens …utput_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may res… Create a Message Claude Developer Platform · in the page api/beta/messages/create …utput_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may res… Models Claude Developer Platform · in the page api/beta/models …port` Whether the model supports max effort level. - `medium: BetaCapabilitySupport` Whether the model supports medium effort level. - `supported: boolean` Whe… List Models Claude Developer Platform · in the page api/beta/models/list …port` Whether the model supports max effort level. - `medium: BetaCapabilitySupport` Whether the model supports medium effort level. - `supported: boolean` Whe… Get a Model Claude Developer Platform · in the page api/beta/models/retrieve …port` Whether the model supports max effort level. - `medium: BetaCapabilitySupport` Whether the model supports medium effort level. - `supported: boolean` Whe… Sessions Claude Developer Platform · in the page api/beta/sessions …dditional details and options. - `effort: optional "low" or "medium" or "high" or 2 more or BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or 3 more or null` How hard… Archive Session Claude Developer Platform · in the page api/beta/sessions/archive …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `h… Create Session Claude Developer Platform · in the page api/beta/sessions/create …dditional details and options. - `effort: optional "low" or "medium" or "high" or 2 more or BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or 3 more or null` How hard… Events Claude Developer Platform · in the page api/beta/sessions/events …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… List Events Claude Developer Platform · in the page api/beta/sessions/events/list …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… Stream Events Claude Developer Platform · in the page api/beta/sessions/events/stream …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… List Sessions Claude Developer Platform · in the page api/beta/sessions/list …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `h… Get Session Claude Developer Platform · in the page api/beta/sessions/retrieve …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `h… Threads Claude Developer Platform · in the page api/beta/sessions/threads …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… Archive Session Thread Claude Developer Platform · in the page api/beta/sessions/threads/archive …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… Events Claude Developer Platform · in the page api/beta/sessions/threads/events …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… List Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/list …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… Stream Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/stream …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… List Session Threads Claude Developer Platform · in the page api/beta/sessions/threads/list …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… Get Session Thread Claude Developer Platform · in the page api/beta/sessions/threads/retrieve …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`,… Update Session Claude Developer Platform · in the page api/beta/sessions/update …effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `h… Messages Claude Developer Platform · in the page api/messages …s output, such as the output format. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may result… Batches Claude Developer Platform · in the page api/messages/batches …tput, such as the output format. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may res… Create a Message Batch Claude Developer Platform · in the page api/messages/batches/create …tput, such as the output format. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may res… Count tokens in a Message Claude Developer Platform · in the page api/messages/count_tokens …s output, such as the output format. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may result… Create a Message Claude Developer Platform · in the page api/messages/create …s output, such as the output format. - `effort: optional "low" or "medium" or "high" or 2 more or null` How much effort the model should put into its response. Higher effort levels may result… Models Claude Developer Platform · in the page api/models …port` Whether the model supports max effort level. - `medium: CapabilitySupport` Whether the model supports medium effort level. - `supported: boolean` Whether… List Models Claude Developer Platform · in the page api/models/list …port` Whether the model supports max effort level. - `medium: CapabilitySupport` Whether the model supports medium effort level. - `supported: boolean` Whether… Get a Model Claude Developer Platform · in the page api/models/retrieve …port` Whether the model supports max effort level. - `medium: CapabilitySupport` Whether the model supports medium effort level. - `supported: boolean` Whether… effort Claude Developer Platform · in the page build-with-claude/effort …ig.effort` on the request. The following example runs one request at `medium` effort. <CodeGroup> ```bash cURL curl https://api.anthropic.com/v1/messages \ -H "x-api-key: $ANTHROPIC_API_KEY"…