Model comparison
Codex Auto Review vs GPT-5.5
List rate, corouter rate, context, and which ID to send for codex-auto-review versus gpt-5.5. A sample of 1 million input tokens plus 200 thousand output tokens is about $1.10 on corouter (input $0.500, output $0.600). A sample of 1 million input tokens plus 200 thousand output tokens is about $1.10 on corouter (input $0.500, output $0.600).
| Codex Auto Review | GPT-5.5 | |
|---|---|---|
| ID | codex-auto-review | gpt-5.5 |
| Vendor | OpenAI | OpenAI |
| List input | $5.00 | $5.00 |
| corouter input | $0.500 | $0.500 |
| List output | $30.00 | $30.00 |
| corouter output | $3.00 | $3.00 |
| Cache read | $0.050 | $0.050 |
| Context | 1.1M | 1.1M |
Price gap
Codex Auto Review and GPT-5.5 share the same corouter input and output rates: $0.500 input and $3.00 output. The difference in this pair is the model ID, not the rate card.
Window and modalities
Both windows are 1.1M. Codex Auto Review is listed with these modalities: Chat, Reasoning, Code. GPT-5.5 is listed with these modalities: Chat, Reasoning, Code, Vision.
When to send codex-auto-review
Codex Auto Review lists at the same input and output rate as GPT-5.6 Sol and is a review ID, not an alias of GPT-6 Luna. Send codex-auto-review when the caller asks for that ID.
Both are OpenAI IDs. The field you change is model: codex-auto-review or gpt-5.5.
When to send gpt-5.5
GPT-5.5 keeps the GPT-5.6 Sol list rate on input and output, with a cache-read rate and no cache-write rate. Send gpt-5.5 when a workload was already qualified on that exact ID.
Both are OpenAI IDs. The field you change is model: gpt-5.5 or codex-auto-review.
The same volume, two bills
A sample of 1 million input tokens plus 200 thousand output tokens is about $1.10 on corouter (input $0.500, output $0.600).
A sample of 1 million input tokens plus 200 thousand output tokens is about $1.10 on corouter (input $0.500, output $0.600).
Questions
- Which output rate is lower, Codex Auto Review or GPT-5.5?
- Codex Auto Review and GPT-5.5 share the same corouter input and output rates: $0.500 input and $3.00 output. The difference in this pair is the model ID, not the rate card.
- Is corouter affiliated with the model vendors?
- No. corouter is not affiliated with OpenAI or Anthropic. Vendor names identify the model and the published list rate.
- How do you start billing?
- Create a console account and spend prepaid credits. The minimum top-up is $5. The API base is https://api.corouter.co. Put the ID you chose in the model field.