Model comparison
GPT-4o (2024-08-06) vs GPT-5 Codex
Price history, scores and specs for both models, line by line. Every value shows where it came from and when we last confirmed it.
OpenAI
GPT-4o (2024-08-06)
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.
OpenAI
GPT-5 Codex
GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows.
Quick take
Where each one leads
- GPT-5 Codex scores higher on the Artificial Analysis Intelligence Index: 24.9 to 7.7.
Each line comes from a checked value in the tables below. Pick on your workload: price and usage matter for high volume, context and scores for long documents and agent loops.
Price history
Prices side by side, day by day
- GPT-4o (2024-08-06)
- GPT-5 Codex No price history checked yet
- GPT-4o (2024-08-06)
- GPT-5 Codex No price history checked yet
Prices are the listed OpenRouter base rates in US dollars. A day we could not confirm is left out of the line, never filled in.
Price
What each one costs now
| Measure | GPT-4o (2024-08-06) | GPT-5 Codex |
|---|---|---|
| Input price | $2.50 per million tokens | Not checked yet |
| Output price | $10.00 per million tokens | Not checked yet |
Scores
Benchmarks, with source and date
| Measure | GPT-4o (2024-08-06) | GPT-5 Codex |
|---|---|---|
| Artificial Analysis Intelligence Index | 7.7 | 24.9 Leads |
| LMArena text rating (Elo) | 1,300 | Not checked yet |
| LMArena vision rating (Elo) | 1,137 | Not checked yet |
Specs
Context, modalities and tool use
| Measure | GPT-4o (2024-08-06) | GPT-5 Codex |
|---|---|---|
| Context window | 128,000 tokens | Not checked yet |
| Reads | Text, Images, Files | Not checked yet |
| Writes | Text | Not checked yet |
| Tool calling | Yes | Not checked yet |
| Reasoning mode | No | Not checked yet |
| Open weights | No | Not checked yet |
| Listed since | 6 Aug 2024 | Not checked yet |
Usage
How much each one is used
| Measure | GPT-4o (2024-08-06) | GPT-5 Codex |
|---|---|---|
| Tokens served on OpenRouter in a day | 376.5M (for 10 Nov 2026) | Not checked yet |
| Requests on OpenRouter in a day | 455.4K (for 10 Nov 2026) | Not checked yet |
| Tool calls on OpenRouter in a day | 702 (for 10 Nov 2026) | Not checked yet |
| Token usage, last 7 days | Down 17% on the week before (for 10 Nov 2026) | Not checked yet |
- GPT-4o (2024-08-06)
- GPT-5 Codex No usage checked yet
How this works
One link, either order
This link stays the same whichever order you name the two models in, so you can share it as it is. A line appears only when at least one model has a value we confirmed from a source; values we have not confirmed are left out, never guessed. To add a third record of any type, use the open comparison. Read how we check facts.