Docs search: medium / page 2 of 3 / Source Intelligence

extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …s in adaptive mode. Claude Opus 5.5 and Claude Haiku 5.5 default to `"medium"`, and other models that support effort default to `"high"` (see [Effort levels](https://platform.claude.com/docs/en/build-…

mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …"type": "string", "enum": ["high", "medium", "low", "info"], }, }, "required": ["claim", "eviden…

prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …tasks, with `xhigh` for the most capability-sensitive workloads and `medium` or `low` for routine work. Lower effort settings on Claude Fable 5 still perform well and often exceed `xhigh` performance…

Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …ith-claude/effort) level, `high`, then test the other levels (`low`, `medium`, `xhigh`, and `max`) against your own evals. Effort is the primary control for trading off intelligence, latency, and cost…

prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …ikely to skip a search, stop early, or skip a check at this level. * `medium` is the default. Start here for most work, including agentic coding. * `high` suits knowledge work, longer agent tasks, and…

prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …ntelligence-sensitive use cases, use a minimum of `high` effort. * **`medium`:** Good for cost-sensitive use cases that need to reduce token usage while trading off intelligence. * **`low`:** Reserve…

prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …a separate pass instead. * **Efficiency at lower effort:** `low` and `medium` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) produce strong quality at a fraction of the tokens…

prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …de base until its tests pass. In Anthropic's testing, at its default `medium` effort the model matched or beat Claude Opus 5 at `high` effort on such tasks, in fewer steps and with fewer tokens. It al…

prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …etting balances token usage and intelligence for most use cases. * **`medium`:** Good for cost-sensitive use cases that need to reduce token usage while trading off intelligence. * **`low`:** Reserve…

prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …tency-sensitive. For agentic coding and multistep tool use, start at `medium` for well-specified tasks and move to `high` for harder or longer ones. For chat and other latency-sensitive work, start at…

thinking Claude Developer Platform · in the page build-with-claude/thinking …table, "at `high` effort or below" means the request works at `low`, `medium`, and `high` effort and returns a 400 error at `xhigh` or `max`. On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Cla…

thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …hat benefit from it. Provides deep reasoning on complex tasks. | | `medium` (default on Claude Opus 5.5 and Claude Haiku 5.5) | Claude uses moderate thinking. Might skip thinking for simple queries.…

apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …ccepts. Each `ClaudeModel` declares which of the five levels (`low`, `medium`, `high`, `xhigh`, `max`) its model takes, if any: some models don't accept effort at all. ### When to use Claude versus t…

Replace NODE_UID with the node's UID: Claude Developer Platform · in the page manage-claude/wif-providers/spiffe …s a sidecar container that shares a memory-backed `emptyDir` volume (`medium: Memory`) with your application container so the bearer SVID never lands on the node's disk. Mount the SPIRE Agent socket f…

agent-setup Claude Developer Platform · in the page managed-agents/agent-setup …", "model": { "id": "claude-opus-5-5", "effort": { "type": "medium" }, "speed": "standard" }, "system": "You are a helpful coding agent.", "description": null, "tools": [ {…

Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: Claude Developer Platform · in the page models/fable-5-1/migration-guide …tem"` message changes it. Only the named levels are accepted (`low`, `medium`, `high`, `xhigh`, `max`), and the `mid-conversation-output-config-2026-07-01` beta header is required. See [Per-message ef…

overview Claude Developer Platform · in the page models/fable-5/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M…

overview Claude Developer Platform · in the page models/haiku-4-5/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M…

migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …"thinking": { "type": "adaptive" }, "output_config": { "effort": "medium" }, "messages": [{ "role": "user", "content": "..." }] } ``` Adaptive thinking is on by default, so a response can start…

overview Claude Developer Platform · in the page models/mythos-5/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M…

overview Claude Developer Platform · in the page models/opus-4-5/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | **Claude Opus 4.5** (this model) | 200K…

overview Claude Developer Platform · in the page models/opus-4-6/overview …| 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | **Claude Opus 4.6** (this model) | 1M…

overview Claude Developer Platform · in the page models/opus-4-7/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | **Claude Opus 4.7** (this model) | 1M…

overview Claude Developer Platform · in the page models/opus-4-8/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | **Claude Opus 4.8** (this model) | 1M…

migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …the only request parameter that controls it. All five levels (`low`, `medium`, `high`, `xhigh`, `max`) are supported, and the default is `medium`. See [Recommended effort levels for Claude Opus 5.5](h…

whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …claude/effort) controls thinking depth; its default on this model is `medium`. For the context window, output limits, knowledge cutoff, and prices, see the [Claude Opus 5.5 model page](https://platfor…

overview Claude Developer Platform · in the page models/opus-5/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | **Claude Opus 5** (this model) | 1M…

Models overview Claude Developer Platform · in the page models/overview …| `medium` | `high`…

overview Claude Developer Platform · in the page models/sonnet-4-5/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M…

overview Claude Developer Platform · in the page models/sonnet-4-6/overview …| 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M…

migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …architectures" }], "output_config": { "effort": "medium" } }' ``` ```bash CLI ant messages create \ --model claude-sonnet-5-5 \ --max-tokens 4096 \ --…

overview Claude Developer Platform · in the page models/sonnet-5-5/overview …128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 | | **Claude Sonnet 5.5** (this model) | 1M |…

whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …ge points to `between_tools`. `between_tools` is accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max` effort, a request with `between_tools` returns a 400 error. To run at `xhigh` or `…

overview Claude Developer Platform · in the page models/sonnet-5/overview …| 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 | | [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M…

overview Claude Developer Platform · in the page release-notes/overview …r steering Claude Opus 5: the model supports the full ladder (`low`, `medium`, `high`, `xhigh`, `max`), with `max` for capability-critical work. * Mid-conversation tool changes are now in beta on Clau…

Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …vel = Literal[ "low", # Minimal thinking, fastest responses "medium", # Moderate thinking "high", # Deep reasoning "xhigh", # Extended reasoning; falls back to "high" on models tha…

Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …description: z.string(), estimated_complexity: z.enum(["low", "medium", "high"]) }) ), risks: z.array(z.string()) }); type FeaturePlan = z.infer<typeof FeaturePlan>; // Convert to JSO…

Manage multiple agents with agent view Claude Code CLI · in the page agent-view …ocs/en/model-config.md#adjust-effort-level)**: `/effort` with `low`, `medium`, `high`, `xhigh`, or `max`, for example `/effort high`. To start sessions in [ultracode](/docs/en/workflows.md#let-claude-…

Share session output as artifacts Claude Code CLI · in the page artifacts …n to use an artifact Use an artifact when terminal text is the wrong medium for what Claude produced: output that is easier to look at and interact with than to read line by line. Claude builds the p…

Authentication Claude Code CLI · in the page authentication …e.com/pricing](https://claude.com/pricing?utm_source=claude_code\&utm_medium=docs\&utm_content=authentication_pro_max). * **Claude for Teams or Enterprise**: log in with the claude.ai account your tea…

Claude Code changelog Claude Code CLI · in the page changelog …and no longer repeat git's own error text * Changed `/code-review` at medium effort to also report cleanup and CLAUDE.md conventions findings on models without tuned review settings, including Opus 5.…