Model comparison
Claude Haiku 4.5 vs Codex Auto Review
List rate, corouter rate, context, and which ID to send for claude-haiku-4-5 versus codex-auto-review. A sample of 1 million input tokens plus 200 thousand output tokens is about $1.60 on corouter (input $0.800, output $0.800). 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 Haiku 4.5 | Codex Auto Review | |
|---|---|---|
| ID | claude-haiku-4-5 | codex-auto-review |
| Vendor | Anthropic | OpenAI |
| List input | $1.00 | $5.00 |
| corouter input | $0.800 | $0.500 |
| List output | $5.00 | $30.00 |
| corouter output | $4.00 | $3.00 |
| Cache read | $0.080 | $0.050 |
| Context | 200K | 1.1M |
Price gap
On output, Codex Auto Review is lower: $3.00 on corouter versus $4.00 for Claude Haiku 4.5, about 1.33×. Input is $0.500 versus $0.800.
Window and modalities
Codex Auto Review lists a 1.1M window and Claude Haiku 4.5 lists 200K. A larger window does not change the per-token rate. Prompts past the window need a split or a different ID. Claude Haiku 4.5 is listed with these modalities: Chat, Vision. Codex Auto Review is listed with these modalities: Chat, Reasoning, Code.
When to send claude-haiku-4-5
Claude Haiku 4.5 is the short-window, low list-rate Claude row: 200K, chat and vision, no Code tag. Send claude-haiku-4-5 for volume that fits that window.
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-haiku-4-5 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 $1.60 on corouter (input $0.800, output $0.800).
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 Haiku 4.5 or Codex Auto Review?
- On output, Codex Auto Review is lower: $3.00 on corouter versus $4.00 for Claude Haiku 4.5, about 1.33×. Input is $0.500 versus $0.800.
- 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.