Model comparison
Claude Opus 4.6 vs Codex Auto Review
List rate, corouter rate, context, and which ID to send for claude-opus-4-6 versus codex-auto-review. A sample of 1 million input tokens plus 200 thousand output tokens is about $8.00 on corouter (input $4.00, output $4.00). A sample of 1 million input tokens plus 200 thousand output tokens is about $1.10 on corouter (input $0.500, output $0.600).
| Claude Opus 4.6 | Codex Auto Review | |
|---|---|---|
| ID | claude-opus-4-6 | codex-auto-review |
| Vendor | Anthropic | OpenAI |
| List input | $5.00 | $5.00 |
| corouter input | $4.00 | $0.500 |
| List output | $25.00 | $30.00 |
| corouter output | $20.00 | $3.00 |
| Cache read | $0.400 | $0.050 |
| Context | 1M | 1.1M |
Price gap
On output, Codex Auto Review is lower: $3.00 on corouter versus $20.00 for Claude Opus 4.6, about 6.67×. Input is $0.500 versus $4.00.
Window and modalities
Codex Auto Review lists a 1.1M window and Claude Opus 4.6 lists 1M. A larger window does not change the per-token rate. Prompts past the window need a split or a different ID. Claude Opus 4.6 is listed with these modalities: Chat, Vision, Reasoning. Codex Auto Review is listed with these modalities: Chat, Reasoning, Code.
When to send claude-opus-4-6
Claude Opus 4.6 is the earliest Opus 4 ID still on this rate card, at the same list rate as Opus 4.7. Send claude-opus-4-6 only when that older ID is the one in the request.
This ID uses the familiar messages JSON shape. The other side is codex-auto-review from OpenAI. corouter is not affiliated with OpenAI or Anthropic.
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.
This ID uses the familiar chat-completions JSON shape. The other side is claude-opus-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 $8.00 on corouter (input $4.00, output $4.00).
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, Claude Opus 4.6 or Codex Auto Review?
- On output, Codex Auto Review is lower: $3.00 on corouter versus $20.00 for Claude Opus 4.6, about 6.67×. Input is $0.500 versus $4.00.
- 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.