@doublenickk: Anthropic shipped 125 settings for Claude The official docs cover 40 One developer found the other 85 and his API bill …

X AI KOLs Timeline Products
anthropic claude settings cost-optimization api configuration undocumented

Summary

A developer discovered 85 undocumented settings for Anthropic's Claude API, leading to significant cost reductions by optimizing configuration such as memory scoping, extended thinking, and cache control.

Anthropic shipped 125 settings for Claude The official docs cover 40 One developer found the other 85 and his API bill dropped from $340 to $87 - not by using a cheaper model - not by writing shorter prompts just by moving one line in a config file to the right place > memory scoped per project → past clients never bleed into new work > Extended Thinking on Light by default → 18–25% fewer Opus tokens in week one > cache_control moved to the right line → the fix that turned a $340 bill into $87 > plugins and MCP servers toggled off when idle → saved 25–40K tokens per session > per-project model override → Haiku for docs, Sonnet for infra, Opus only where it matters most Claude users are running a $100/month tool at 30% of its actual capability
Original Article
View Cached Full Text

Cached at: 05/25/26, 06:45 AM

Anthropic shipped 125 settings for Claude

The official docs cover 40

One developer found the other 85 and his API bill dropped from $340 to $87

  • not by using a cheaper model
  • not by writing shorter prompts

just by moving one line in a config file to the right place

memory scoped per project → past clients never bleed into new work Extended Thinking on Light by default → 18–25% fewer Opus tokens in week one cache_control moved to the right line → the fix that turned a $340 bill into $87 plugins and MCP servers toggled off when idle → saved 25–40K tokens per session per-project model override → Haiku for docs, Sonnet for infra, Opus only where it matters

most Claude users are running a $100/month tool at 30% of its actual capability

Thank you for such nice words!

I agree with you

I’m not entirely sure about that

this is the main task!

I’m glad you liked it

yep

I’ll be glad to hear feedback from you later

Thank you for such a nice comment

this is true

Similar Articles

@_avichawla: Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everythi…

X AI KOLs Timeline

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across