Model comparison
Claude Sonnet 5 vs GPT-5.3 Codex
List rate, corouter rate, context, and which ID to send for claude-sonnet-5 versus gpt-5.3-codex. A sample of 1 million input tokens plus 200 thousand output tokens is about $0.800 on corouter (input $0.400, output $0.400). A sample of 1 million input tokens plus 200 thousand output tokens is about $0.910 on corouter (input $0.350, output $0.560).
| Claude Sonnet 5 | GPT-5.3 Codex | |
|---|---|---|
| ID | claude-sonnet-5 | gpt-5.3-codex |
| Vendor | Anthropic | OpenAI |
| List input | $2.00 | $1.75 |
| corouter input | $0.400 | $0.350 |
| List output | $10.00 | $14.00 |
| corouter output | $2.00 | $2.80 |
| Cache read | $0.040 | $0.035 |
| Context | 1M | 272K |
Price gap
On output, Claude Sonnet 5 is lower: $2.00 on corouter versus $2.80 for GPT-5.3 Codex, about 1.40×. Input is $0.400 versus $0.350.
Window and modalities
Claude Sonnet 5 lists a 1M window and GPT-5.3 Codex lists 272K. A larger window does not change the per-token rate. Prompts past the window need a split or a different ID. Claude Sonnet 5 is listed with these modalities: Chat, Vision, Code. GPT-5.3 Codex is listed with these modalities: Chat, Reasoning, Code, Vision.
When to send claude-sonnet-5
Claude Sonnet 5 lists below Sonnet 4.6 on both input and output and keeps the 1M window plus the Code tag. Send claude-sonnet-5 for that newer Sonnet ID.
This ID uses the familiar messages JSON shape. The other side is gpt-5.3-codex from OpenAI. corouter is not affiliated with OpenAI or Anthropic.
When to send gpt-5.3-codex
GPT-5.3 Codex is a coding ID with a 272K window. Its list rate matches GPT-5.2 Codex; the difference you bill is the ID itself, gpt-5.3-codex.
This ID uses the familiar chat-completions JSON shape. The other side is claude-sonnet-5 from Anthropic. corouter is not affiliated with OpenAI or Anthropic.
The same volume, two bills
A sample of 1 million input tokens plus 200 thousand output tokens is about $0.800 on corouter (input $0.400, output $0.400).
A sample of 1 million input tokens plus 200 thousand output tokens is about $0.910 on corouter (input $0.350, output $0.560).
Questions
- Which output rate is lower, Claude Sonnet 5 or GPT-5.3 Codex?
- On output, Claude Sonnet 5 is lower: $2.00 on corouter versus $2.80 for GPT-5.3 Codex, about 1.40×. Input is $0.400 versus $0.350.
- 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.