Model comparison
Claude Sonnet 4.6 vs GPT-5.3 Codex
List rate, corouter rate, context, and which ID to send for claude-sonnet-4-6 versus gpt-5.3-codex. A sample of 1 million input tokens plus 200 thousand output tokens is about $1.20 on corouter (input $0.600, output $0.600). 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 4.6 | GPT-5.3 Codex | |
|---|---|---|
| ID | claude-sonnet-4-6 | gpt-5.3-codex |
| Vendor | Anthropic | OpenAI |
| List input | $3.00 | $1.75 |
| corouter input | $0.600 | $0.350 |
| List output | $15.00 | $14.00 |
| corouter output | $3.00 | $2.80 |
| Cache read | $0.060 | $0.035 |
| Context | 1M | 272K |
Price gap
On output, GPT-5.3 Codex is lower: $2.80 on corouter versus $3.00 for Claude Sonnet 4.6, about 1.07×. Input is $0.350 versus $0.600.
Window and modalities
Claude Sonnet 4.6 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 4.6 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-4-6
Claude Sonnet 4.6 keeps the previous Sonnet list rate, above Sonnet 5, with a 1M window and the Code tag. Send claude-sonnet-4-6 when a runbook still names it.
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-4-6 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 $1.20 on corouter (input $0.600, output $0.600).
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 4.6 or GPT-5.3 Codex?
- On output, GPT-5.3 Codex is lower: $2.80 on corouter versus $3.00 for Claude Sonnet 4.6, about 1.07×. Input is $0.350 versus $0.600.
- 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.