remaining tut

• Deep Learning
• AWS
• YOLO
• Big Data

---

Model Provider	Model Name	Size Tier*	Parameter Size (≈)	Model Type	Text	Audio	Image	5 High-value Uses (SRE/Ops)	Cost /1M Input	Cost /1M Output	Cost Category†	Latency Class‡
Anthropic	Claude Opus 4	Very Large	480 B	Reasoning	✅	—	—	Autonomous code refactoring; complex RCA runbooks; long-horizon agents; compliance reasoning; 200 k-ctx mining	Docs	Docs	Very High	Medium
Anthropic	Claude Sonnet 4	Large	160 B	Reasoning	✅	—	—	Ticket summarization; structured RAG; incident copilots; FinOps advice; multilingual bots	Docs	Docs	High	Low-Medium
Anthropic	Claude Haiku 3.5	Small	34 B	Reasoning	✅	—	—	Real-time alert enrichment; log bucketing; FAQ chat; SQL generation; batch summarization	Docs	Docs	Mid	Low
Azure AI	GPT-4o	Large	175 B+	Multimodal Reasoning	✅	✅	✅	War-room chat with screenshots; voice RCA; on-call assistants; test-plan generation; PII redaction	Info	Info	High	Medium
Azure AI	GPT-3.5 Turbo	Mid	12 B	Reasoning	✅	—	—	High-volume transforms; Teams/Slack bots; doc summarization; synthetic traces; autocomplete	Pricing	Pricing	Low	Low
OpenAI	GPT-5	Very Large	1 T	Reasoning	✅	✅	Image (lite)	Agent coding; capacity-planning sims; SLO drift forecasts; change-risk reviews; voice post-mortems	Pricing	Pricing	Mid	Medium
OpenAI	GPT-4o-mini	Small	38 B	Reasoning	✅	—	✅	Cost-aware chat; CLI assistants; autoscaling policies; alert deduplication; pre-labeling	Pricing	Pricing	Low	Low
OpenAI	o3-mini	Micro	8 B	Reasoning	✅	—	—	Intent routing; math/regex helper; anomaly scoring; guard-rails; config linting	Pricing	Pricing	Low	Very Low
Google	Gemini 2.5 Pro	Very Large	540 B	Multimodal Reasoning	✅	—	✅	200 k-ctx reviews; multimodal debugging; compliance audits; capacity what-ifs; cost sandboxing	Pricing	Pricing	Mid	Medium
Google	Gemini 2.5 Flash	Mid	25 B	Reasoning	✅	—	✅	Latency-critical chat; doc labeling; cost anomaly alerts; code hints; live translation	Pricing	Pricing	Low	Very Low

Star History