C.W.K.
Stream
Lesson 02 of 08 · published

Model Lineup 2026

~22 min · models, gpt-5, o-series

Level 0Tokenizer
0 XP0/54 lessons0/10 achievements
0/120 XP to next level120 XP to go0% complete

OpenAI's model catalog in 2026 spans frontier reasoning models, efficient mini/nano variants, and specialized models for images, audio, and realtime interactions. The primary API is the Responses API, though Chat Completions remains fully supported.

Flagship Models (GPT-5.x Series)

ModelContextMax OutputInput $/1MOutput $/1MKey Feature
gpt-5.41.05M128K$2.50$15.00Flagship, reasoning none→xhigh
gpt-5.4-mini400K128K$0.75$4.50Fast & affordable
gpt-5.4-nano400K128K$0.20$1.25Ultra-lightweight

GPT-4.x & o-Series

ModelContextInput $/1MOutput $/1MNotes
gpt-4.11M$2.00$8.00Best non-reasoning model
gpt-4o128K$2.50$10.00Multimodal (text+vision)
o3200K$2.00$8.00Advanced reasoning
o4-mini200K$1.10$4.40Efficient reasoning

Key notes: gpt-5.4 defaults to reasoning_effort: "none" — set it to "low", "medium", "high", or "xhigh" to enable chain-of-thought reasoning. Prompts exceeding 272K input tokens are charged at 2× input and 1.5× output for the entire session. gpt-4.1 excels at instruction following and tool calling with its 1M token context window.

External links

Exercise

Build a 6-row table comparing gpt-5, gpt-5-mini, gpt-4.1, gpt-4.1-mini, o3, and o4-mini on: input price, output price, context window, best-fit job. Pull current numbers from the official pricing page; do not guess.

Progress

Progress is local-only — sign in to sync across devices.
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.