The whole hunk
from line 4, old and new numbered
/
lines
from line 4
44description: Comprehensive guide to prompt engineering techniques for Claude's latest models, covering clarity, examples, XML structuring, thinking, and agentic systems.
55---
66
7This is the reference for prompt engineering with current Claude models, including Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 4.5. The page is organized in three parts:
7This is the reference for prompt engineering with current Claude models, including Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 4.5. The page is organized in three parts:
88
99* **[Model-specific guidance](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#model-specific-guidance)** first: where a single model behaves differently and what to change in your prompt.
1010* **Techniques for all current models** after that: general principles, output and formatting, tool use, thinking, and agentic systems.
from line 11
1111* **Migration considerations** last, for prompts moving from earlier generations.
1212
1313<Tip>
14 For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1). For Claude Fable 5 capabilities and API changes, see [Introducing Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5). For details on what's new in Claude Sonnet 5, see [What's new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/whats-new-sonnet-5). For details on what's new in Claude Opus 5, see [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/whats-new-opus-5). For migration guidance, see the [Migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide).
14 For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1). For Claude Fable 5 capabilities and API changes, see [Introducing Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5). For details on what's new in Claude Sonnet 5, see [What's new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/whats-new-sonnet-5). For details on what's new in Claude Opus 5, see [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/whats-new-opus-5). For migration guidance, see the [Migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide). For Claude Opus 5.5, see [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5).
1515</Tip>
1616
1717## Model-specific guidance
from line 23
2323| Claude Fable 5.1 and Claude Mythos 5.1 | [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1) | Differences from Claude Fable 5: effort levels, finishing long tasks, user-facing progress updates, passing thinking blocks back unchanged, tool-call batching in agent loops, search triggering at low effort, formatting, and writing density. |
2424| Claude Fable 5 and Claude Mythos 5 | [Prompting Claude Fable 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5) | Differences from Claude Opus 4.8: effort levels, instruction following, long-run progress claims, memory systems, and the `reasoning_extraction` refusal category. |
2525| Claude Sonnet 5 | [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5) | Differences from Claude Sonnet 4.6: response length, effort and thinking-depth calibration, tool use triggering, literal instruction following, and design and frontend defaults. |
26| Claude Opus 5.5 | [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5) | Differences from Claude Opus 5: effort calibration, prompts written for thinking disabled, user-facing progress updates, safeguard false positives, and tools for complex visual inputs. |
2627| Claude Opus 5 | [Prompting Claude Opus 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5) | Differences from prior Opus models: response length and verbosity, user-facing progress updates, written deliverable length, task scope and over-verification, subagent control, and self-correction. |
2728| Claude Opus 4.8 | [Prompting Claude Opus 4.8](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-4-8) | Response length, effort and thinking-depth calibration, tool use triggering, literal instruction following, subagent control, and design and frontend defaults. |
2829
from line 110
109110 -H "x-api-key: $ANTHROPIC_API_KEY" \
110111 -H "anthropic-version: 2023-06-01" \
111112 -d '{
112 "model": "claude-opus-5",
113 "model": "claude-opus-5-5",
113114 "max_tokens": 1024,
114115 "system": "You are a helpful coding assistant specializing in Python.",
115116 "messages": [
from line 121
120121
121122 ```bash CLI
122123 ant messages create \
123 --model claude-opus-5 \
124 --model claude-opus-5-5 \
124125 --max-tokens 1024 \
125126 --system "You are a helpful coding assistant specializing in Python." \
126127 --message '{role: user, content: "How do I sort a list of dictionaries by key?"}'
from line 131
130131 client = anthropic.Anthropic()
131132
132133 message = client.messages.create(
133 model="claude-opus-5",
134 model="claude-opus-5-5",
134135 max_tokens=1024,
135136 system="You are a helpful coding assistant specializing in Python.",
136137 messages=[
from line 146
145146 const client = new Anthropic();
146147
147148 const message = await client.messages.create({
148 model: "claude-opus-5",
149 model: "claude-opus-5-5",
149150 max_tokens: 1024,
150151 system: "You are a helpful coding assistant specializing in Python.",
151152 messages: [{ role: "user", content: "How do I sort a list of dictionaries by key?" }]
from line 160
159160
160161 var parameters = new MessageCreateParams
161162 {
162 Model = Model.ClaudeOpus5,
163 Model = Model.ClaudeOpus5_5,
163164 MaxTokens = 1024,
164165 System = "You are a helpful coding assistant specializing in Python.",
165166 Messages =
from line 177
176177 client := anthropic.NewClient()
177178
178179 message, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
179 Model: anthropic.ModelClaudeOpus5,
180 Model: anthropic.ModelClaudeOpus5_5,
180181 MaxTokens: 1024,
181182 System: []anthropic.TextBlockParam{
182183 {Text: "You are a helpful coding assistant specializing in Python."},
from line 196
195196 AnthropicClient client = AnthropicOkHttpClient.fromEnv();
196197
197198 MessageCreateParams params = MessageCreateParams.builder()
198 .model(Model.CLAUDE_OPUS_5)
199 .model(Model.CLAUDE_OPUS_5_5)
199200 .maxTokens(1024)
200201 .system("You are a helpful coding assistant specializing in Python.")
201202 .addUserMessage("How do I sort a list of dictionaries by key?")
from line 214
213214 messages: [
214215 ['role' => 'user', 'content' => 'How do I sort a list of dictionaries by key?']
215216 ],
216 model: 'claude-opus-5',
217 model: 'claude-opus-5-5',
217218 system: 'You are a helpful coding assistant specializing in Python.',
218219 );
219220
from line 225
224225 client = Anthropic::Client.new
225226
226227 message = client.messages.create(
227 model: "claude-opus-5",
228 model: "claude-opus-5-5",
228229 max_tokens: 1024,
229230 system: "You are a helpful coding assistant specializing in Python.",
230231 messages: [
from line 306
305306If you would like Claude to identify itself correctly in your application or use specific API strings:
306307
307308```text Sample prompt for model identity wrap
308The assistant is Claude, created by Anthropic. The current model is Claude Opus 5.
309The assistant is Claude, created by Anthropic. The current model is Claude Opus 5.5.
309310```
310311
311312For LLM-powered apps that need to specify model strings:
312313
313314```text Sample prompt for model string wrap
314When an LLM is needed, please default to Claude Opus 5 unless the user requests
315otherwise. The exact model string for Claude Opus 5 is claude-opus-5.
315When an LLM is needed, please default to Claude Opus 5.5 unless the user requests
316otherwise. The exact model string for Claude Opus 5.5 is claude-opus-5-5.
316317```
317318
318319## Output and formatting
from line 543
542543
543544Claude's latest models offer thinking capabilities that can be especially helpful for tasks involving reflection after tool use or complex multistep reasoning. You can guide its initial or interleaved thinking for better results.
544545
545Claude 4.6 and later models and Claude Mythos Preview use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`), where Claude dynamically decides when and how much to think. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5, thinking is always on and adaptive thinking is the only mode. Claude calibrates its thinking based on two factors: the `effort` parameter and query complexity. Higher effort elicits more thinking, and more complex queries do the same. On easier queries that don't require thinking, the model responds directly. In internal evaluations, adaptive thinking reliably drives better performance than extended thinking. Consider moving to adaptive thinking.
546Claude 4.6 and later models and Claude Mythos Preview use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`), where Claude dynamically decides when and how much to think. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on and adaptive thinking is the only mode. Claude calibrates its thinking based on two factors: the `effort` parameter and query complexity. Higher effort elicits more thinking, and more complex queries do the same. On easier queries that don't require thinking, the model responds directly. In internal evaluations, adaptive thinking reliably drives better performance than extended thinking. Consider moving to adaptive thinking.
546547
547548Use adaptive thinking for workloads that require agentic behavior such as multistep tool use, complex coding tasks, and long-horizon agent loops. Older models use manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) with `budget_tokens`; see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#supported-models) for which configuration each model accepts.
548549
from line 772
771772 ```
772773</CodeGroup>
773774
774If you are not using extended thinking, no changes are required. On Claude Opus 4.6 through Claude Opus 4.8 and Claude Sonnet 4.6, thinking is off when you omit the `thinking` parameter. On Claude Opus 5 and Claude Sonnet 5, thinking is on by default when you omit the `thinking` parameter. On Claude Opus 5, you can disable it only at effort `high` or lower. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5, thinking is always on, regardless of whether you set the `thinking` parameter.
775If you are not using extended thinking, no changes are required. On Claude Opus 4.6 through Claude Opus 4.8 and Claude Sonnet 4.6, thinking is off when you omit the `thinking` parameter. On Claude Opus 5 and Claude Sonnet 5, thinking is on by default when you omit the `thinking` parameter. On Claude Opus 5, you can disable it only at effort `high` or lower. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on, regardless of whether you set the `thinking` parameter.
775776
776777* **Prefer general instructions over prescriptive steps.** A prompt like "think thoroughly" often produces better reasoning than a hand-written step-by-step plan. Claude's reasoning frequently exceeds what a human would prescribe.
777778* **Multishot examples work with thinking.** Use `<thinking>` tags inside your few-shot examples to show Claude the reasoning pattern. It will generalize that style to its own extended thinking blocks.
from line 1081
10801081
108110826. **Tune anti-laziness prompting:** If your prompts previously encouraged the model to be more thorough or use tools more aggressively, dial back that guidance. Claude 4.6 models are more proactive and may overtrigger on instructions that were needed for previous models.
10821083
10837. **Pass thinking blocks back unchanged and keep history append-only:** Append each assistant turn exactly as the API returned it, thinking blocks included. On Claude Fable 5.1, [modifying the conversation before a thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) results in an error, or in the block being dropped if you opt into that: editing earlier messages, rebuilding `system` or `tools`, or summarizing older turns in place between requests invalidates every later thinking block, so move those changes to mid-conversation system messages and server-side context management. See [Keep the conversation history append-only](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#keep-the-conversation-history-append-only).
10847. **Pass thinking blocks back unchanged and keep history append-only:** Append each assistant turn exactly as the API returned it, thinking blocks included. On Claude Fable 5.1 and Claude Opus 5.5, [modifying the conversation before a thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) results in an error, or in the block being dropped if you opt into that: editing earlier messages, rebuilding `system` or `tools`, or summarizing older turns in place between requests invalidates every later thinking block, so move those changes to mid-conversation system messages and server-side context management. See [Keep the conversation history append-only](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#keep-the-conversation-history-append-only).
10841085
10851086For detailed migration steps, see the [Migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide).
10861087
from line 1102
11011102
11021103 <Card title="Prompting Claude Sonnet 5" icon="terminal" href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5">
11031104 Behavioral differences and prompting patterns for Claude Sonnet 5, covering effort, adaptive thinking defaults, tool use, and migration from Claude Sonnet 4.6.
1105 </Card>
1106
1107 <Card title="Prompting Claude Opus 5.5" icon="terminal" href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5">
1108 Behavioral differences and prompting patterns for Claude Opus 5.5, covering effort calibration, thinking always on, progress updates, safeguard false positives, and visual inputs.
11041109 </Card>
11051110
11061111 <Card title="Prompting Claude Opus 5" icon="terminal" href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5">