Tutorials Intermediate
OpenAI Ultrafast: Pay 6x Only When Latency Matters
A Python router that buys Ultrafast speed only where users wait, with fallback and cost tracking.
9 min read·Kodetra Technologies
5d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
Tutorials Intermediate
Ember-1: A/B Test Its 40% Token Savings in Python
Fireworks' Ember-1 claims 40% fewer tokens than Kimi K3. Build a harness to verify it.
8 min read·Kodetra Technologies
6d ago
Machine Learning Intermediate
Unmask a Stealth LLM: Fingerprint Any Model API
Port the Ox Alpha probe kit to Python: normalized token counts, error DNA, ranked verdict.
14 min read·Kodetra Technologies
Aug 28
Tutorials Intermediate
Grok 4.6 Agents: Dodge the 200K Price Cliff
Keep long-running Grok 4.6 agents cheap: cache keys, token budgets, and the 200K cliff.
10 min read·Kodetra Technologies
Aug 14
Tutorials Intermediate
DeepSeek V4-Flash KV Cache: Cut Input Costs 50x
Structure prompts so DeepSeek's disk cache hits, and pay ~50x less on repeated input tokens.
9 min read·Kodetra Technologies
Aug 5
Tutorials Intermediate
Opus 5 Effort Router: Auto-Pick Cost vs Capability
Route each task to the right Claude Opus 5 effort level and cut your token bill.
7 min read·Kodetra Technologies
Jul 27
Tutorials Intermediate
Gemini 3.6 Flash: Cut Agent Tokens With thinking_level
Build a token-thrifty tool-calling agent on Gemini 3.6 Flash using the new thinking_level control.
10 min read·Kodetra Technologies
Jul 22
Tutorials Intermediate
Kimi K3 Reasoning Effort: Stream Thoughts, Cut Cost
Tune Kimi K3's low/high/max reasoning effort and stream reasoning_content to control token cost.
9 min read·Kodetra Technologies
Jul 21
Tutorials Intermediate
Kimi K3: Query a Million-Token Repo for Pennies
Point the OpenAI SDK at Moonshot's 2.8T K3, load a whole repo, and cut cost with caching.
8 min read·Kodetra Technologies
Jul 17
Tutorials Intermediate
Muse Spark 1.1: Drop-In Agent, Self-Managed Context
Point the OpenAI SDK at Meta's agent model, add tools, let it self-manage a 1M-token context.
10 min read·Kodetra Technologies
Jul 17
Tutorials Intermediate
GPT-5.6 Persisted Reasoning: Reuse Thinking Across Turns
Use reasoning.context to reuse GPT-5.6's chain of thought across turns and cut redundant tokens.
9 min read·Kodetra Technologies
Jul 16
Tutorials Intermediate
Prompt Cache Retention: Cut OpenAI Bills Up to 90%
Structure prompts, set prompt_cache_retention, and read cached_tokens to slash GPT-5.6 input costs.
8 min read·Kodetra Technologies
Jul 11Page 1 of 3