Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 28 Aug 2026
One change · api

thinking-steering-and-cost changedbuild-with-claude/thinking-steering-and-cost

Nearest release: v2.1.251, published 2 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+22added
Lines−22removed
From line 57 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits15to this page, all time

The whole hunk

from line 57, old and new numbered
/
lines
from line 57
5757 
5858```json
5959{
60 "model": "claude-opus-4-8",
60 "model": "claude-opus-5",
6161 "max_tokens": 4096,
6262 "output_config": { "effort": "medium" },
6363 "messages": [{ "role": "user", "content": "..." }]
from line 173
173173 # First request - establish cache
174174 print("First request - establishing cache")
175175 response1 = client.messages.create(
176 model="claude-opus-4-8",
176 model="claude-opus-5",
177177 max_tokens=16000,
178178 thinking={"type": "adaptive"},
179179 messages=MESSAGES,
from line 187
187187 # Second request - same configuration (cache hit expected)
188188 print("\nSecond request - same configuration (cache hit expected)")
189189 response2 = client.messages.create(
190 model="claude-opus-4-8",
190 model="claude-opus-5",
191191 max_tokens=16000,
192192 thinking={"type": "adaptive"},
193193 messages=MESSAGES,
from line 201
201201 # Third request - different effort level (cache miss expected)
202202 print("\nThird request - different effort level (cache miss expected)")
203203 response3 = client.messages.create(
204 model="claude-opus-4-8",
204 model="claude-opus-5",
205205 max_tokens=16000,
206206 thinking={"type": "adaptive"},
207207 output_config={"effort": "medium"},
from line 249
249249 // First request - establish cache
250250 console.log("First request - establishing cache");
251251 const response1 = await client.messages.create({
252 model: "claude-opus-4-8",
252 model: "claude-opus-5",
253253 max_tokens: 16000,
254254 thinking: { type: "adaptive" },
255255 messages
from line 265
265265 // Second request - same configuration (cache hit expected)
266266 console.log("\nSecond request - same configuration (cache hit expected)");
267267 const response2 = await client.messages.create({
268 model: "claude-opus-4-8",
268 model: "claude-opus-5",
269269 max_tokens: 16000,
270270 thinking: { type: "adaptive" },
271271 messages
from line 281
281281 // Third request - different effort level (cache miss expected)
282282 console.log("\nThird request - different effort level (cache miss expected)");
283283 const response3 = await client.messages.create({
284 model: "claude-opus-4-8",
284 model: "claude-opus-5",
285285 max_tokens: 16000,
286286 thinking: { type: "adaptive" },
287287 output_config: { effort: "medium" },
from line 303
303303 Console.WriteLine("First request - establishing cache");
304304 var parameters1 = new MessageCreateParams
305305 {
306 Model = Model.ClaudeOpus4_8,
306 Model = Model.ClaudeOpus5,
307307 MaxTokens = 16000,
308308 Thinking = new ThinkingConfigAdaptive(),
309309 Messages =
from line 333
333333 Console.WriteLine("\nSecond request - same configuration (cache hit expected)");
334334 var parameters2 = new MessageCreateParams
335335 {
336 Model = Model.ClaudeOpus4_8,
336 Model = Model.ClaudeOpus5,
337337 MaxTokens = 16000,
338338 Thinking = new ThinkingConfigAdaptive(),
339339 Messages =
from line 373
373373 Console.WriteLine("\nThird request - different effort level (cache miss expected)");
374374 var parameters3 = new MessageCreateParams
375375 {
376 Model = Model.ClaudeOpus4_8,
376 Model = Model.ClaudeOpus5,
377377 MaxTokens = 16000,
378378 Thinking = new ThinkingConfigAdaptive(),
379379 OutputConfig = new OutputConfig
from line 462
462462 // First request - establish cache
463463 fmt.Println("First request - establishing cache")
464464 response1, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
465 Model: anthropic.ModelClaudeOpus4_8,
465 Model: anthropic.ModelClaudeOpus5,
466466 MaxTokens: 16000,
467467 Thinking: anthropic.ThinkingConfigParamUnion{
468468 OfAdaptive: &anthropic.ThinkingConfigAdaptiveParam{},
from line 480
480480 // Second request - same configuration (cache hit expected)
481481 fmt.Println("\nSecond request - same configuration (cache hit expected)")
482482 response2, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
483 Model: anthropic.ModelClaudeOpus4_8,
483 Model: anthropic.ModelClaudeOpus5,
484484 MaxTokens: 16000,
485485 Thinking: anthropic.ThinkingConfigParamUnion{
486486 OfAdaptive: &anthropic.ThinkingConfigAdaptiveParam{},
from line 498
498498 // Third request - different effort level (cache miss expected)
499499 fmt.Println("\nThird request - different effort level (cache miss expected)")
500500 response3, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
501 Model: anthropic.ModelClaudeOpus4_8,
501 Model: anthropic.ModelClaudeOpus5,
502502 MaxTokens: 16000,
503503 Thinking: anthropic.ThinkingConfigParamUnion{
504504 OfAdaptive: &anthropic.ThinkingConfigAdaptiveParam{},
from line 529
529529 // First request - establishing cache
530530 IO.println("First request - establishing cache");
531531 MessageCreateParams params1 = MessageCreateParams.builder()
532 .model(Model.CLAUDE_OPUS_4_8)
532 .model(Model.CLAUDE_OPUS_5)
533533 .maxTokens(16000L)
534534 .thinking(ThinkingConfigAdaptive.builder().build())
535535 .addUserMessageOfBlockParams(List.of(
from line 549
549549 // Second request - same configuration (cache hit expected)
550550 IO.println("\nSecond request - same configuration (cache hit expected)");
551551 MessageCreateParams params2 = MessageCreateParams.builder()
552 .model(Model.CLAUDE_OPUS_4_8)
552 .model(Model.CLAUDE_OPUS_5)
553553 .maxTokens(16000L)
554554 .thinking(ThinkingConfigAdaptive.builder().build())
555555 .addUserMessageOfBlockParams(List.of(
from line 573
573573 // Third request - different effort level (cache miss expected)
574574 IO.println("\nThird request - different effort level (cache miss expected)");
575575 MessageCreateParams params3 = MessageCreateParams.builder()
576 .model(Model.CLAUDE_OPUS_4_8)
576 .model(Model.CLAUDE_OPUS_5)
577577 .maxTokens(16000L)
578578 .thinking(ThinkingConfigAdaptive.builder().build())
579579 .outputConfig(OutputConfig.builder()
from line 645
645645 ]
646646 ]
647647 ]],
648 model: 'claude-opus-4-8',
648 model: 'claude-opus-5',
649649 thinking: ['type' => 'adaptive'],
650650 );
651651 
from line 678
678678 'content' => 'Analyze the characters in this passage.'
679679 ]
680680 ],
681 model: 'claude-opus-4-8',
681 model: 'claude-opus-5',
682682 thinking: ['type' => 'adaptive'],
683683 );
684684 
from line 719
719719 'content' => 'Analyze the setting in this passage.'
720720 ]
721721 ],
722 model: 'claude-opus-4-8',
722 model: 'claude-opus-5',
723723 thinking: ['type' => 'adaptive'],
724724 outputConfig: ['effort' => 'medium'],
725725 );
from line 750
750750 
751751 puts "First request - establishing cache"
752752 response1 = client.messages.create(
753 model: "claude-opus-4-8",
753 model: "claude-opus-5",
754754 max_tokens: 16000,
755755 thinking: {
756756 type: "adaptive"
from line 775
775775 
776776 puts "\nSecond request - same configuration (cache hit expected)"
777777 response2 = client.messages.create(
778 model: "claude-opus-4-8",
778 model: "claude-opus-5",
779779 max_tokens: 16000,
780780 thinking: {
781781 type: "adaptive"
from line 810
810810 
811811 puts "\nThird request - different effort level (cache miss expected)"
812812 response3 = client.messages.create(
813 model: "claude-opus-4-8",
813 model: "claude-opus-5",
814814 max_tokens: 16000,
815815 thinking: {
816816 type: "adaptive"
Feedback