VISION & MULTIMODAL · 紅葉
GPT
9 models from OpenAI, living in Maple Highlands.
| Model | Context | Input | Output | Accepts |
|---|---|---|---|---|
| GPT Chat Latestopenai/gpt-chat-latest | 400K | $5.00 | $30.0 | text, files, images |
| GPT-5.2 Chatopenai/gpt-5.2-chat | 128K | $1.75 | $14.0 | text, files, images |
| GPT-5.1openai/gpt-5.1 | 400K | $1.25 | $10.0 | text, files, images |
| GPT-5openai/gpt-5 | 400K | $1.25 | $10.0 | text, files, images |
| GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | 128K | $2.50 | $10.0 | text, files, images |
| GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | 128K | $2.50 | $10.0 | text, files, images |
| GPT-4oopenai/gpt-4o | 128K | $2.50 | $10.0 | text, files, images |
| GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13 | 128K | $5.00 | $15.0 | text, files, images |
| GPT-4 Turboopenai/gpt-4-turbo | 128K | $10.0 | $30.0 | text, images |
Questions and answers
Which GPT model has the largest context window?
GPT Chat Latest (OpenAI), with 400K tokens.
Which GPT model is cheapest per input token?
GPT-5, at $1.25 per million input tokens ($10.0 per million output tokens).
Which GPT models accept images?
GPT Chat Latest, GPT-5.2 Chat, GPT-5.1, GPT-5, GPT-4o (2024-11-20), GPT-4o (2024-08-06) and 3 more (9 of 9).
Which GPT models support reasoning?
GPT-5.1, GPT-5 (2 of 9).
Answers are computed from the 2026-10-24 catalog snapshot.