Public story · 2026-02-21 · source-backed

Prompt Engineering

Issue

2026-02-21

Confidence

source-backed

Sources

Redaction

redacted

Story

6. Gemini 3.1 Pro Thinking Levels: Cut API Costs 50-70% | Intermediate HIGH thinking is the default, billing at $12/M tokens. Most requests don't need it.

Route complexity: LOW (1,024 tokens) for classification/summarization, MEDIUM (8,192) for code review, HIGH (32,768) for complex debugging
Use thinking_config=types.ThinkingConfig(thinking_level="MEDIUM") in Google SDK
Never mix thinkingLevel and thinkingBudget — returns 400 error
Use gemini-3.1-pro-preview-customtools variant for agent workflows ($2/$12 per M tokens)
Monitor thinking tokens separately — HIGH can cost 63x more than LOW per request Source: Apiyi Guide

7. Optimize Prompt Caching by Provider | Advanced Full-context caching paradoxically INCREASES latency by 8.8% on GPT-4o. System-prompt-only is optimal.

Cache stable system prompt and tool definitions only — exclude dynamic tool results and conversation history
For Anthropic: explicit cache breakpoints after system prompt, 5-minute TTL (90% read savings)
Keep timestamps, user IDs, session data OUTSIDE cacheable prefix
For OpenAI: stable content first, dynamic last. DON'T cache full conversation context
Fixed function definitions — each tool definition change breaks the entire cached prefix Source: arXiv 2601.06007

Source trail

Apiyi Guide arXiv 2601.06007

Entities

Advanced Full Apiyi Guide Cache Cut API Costs

Prompt Engineering

Story

Related stories

Strategic Prompt Caching for 45-80% Cost Savings (Intermediate, 20 min)

Gemini 3.2 Flash Leaked: 92% of GPT-5.5 Performance at 1/15th the Cost

June 2026 was the biggest model launch month ever, and ChatGPT just dropped below 50% share

Source trail

Entities

Cursor Built Its Own Model. It Matches Opus 4.7 at 10-60x Lower Cost.

Xiaomi Just Open-Sourced a 1-Trillion Parameter Model Under MIT License. It Built a Compiler in 4 Hours.

ML Ops & Prompt Engineering

Sam Altman Just Offered $2 Million in Compute to Every YC Startup. The Lock-In Is the Product.

GPT-5.5 Is Here. It's Fast, It's Expensive, and It Changes How You Prompt.

Provenance