Model comparison
Claude Haiku 4.5 vs Claude Opus 4.8
List rate, corouter rate, context, and which ID to send for claude-haiku-4-5 versus claude-opus-4-8. A sample of 1 million input tokens plus 200 thousand output tokens is about $0.400 on corouter (input $0.200, output $0.200). A sample of 1 million input tokens plus 200 thousand output tokens is about $2.00 on corouter (input $1.00, output $1.00).
| Claude Haiku 4.5 | Claude Opus 4.8 | |
|---|---|---|
| ID | claude-haiku-4-5 | claude-opus-4-8 |
| Vendor | Anthropic | Anthropic |
| List input | $1.00 | $5.00 |
| corouter input | $0.200 | $1.00 |
| List output | $5.00 | $25.00 |
| corouter output | $1.00 | $5.00 |
| Cache read | $0.020 | $0.100 |
| Context | 200K | 1M |
Price gap
On output, Claude Haiku 4.5 is lower: $1.00 on corouter versus $5.00 for Claude Opus 4.8, about 5.00×. Input is $0.200 versus $1.00.
Window and modalities
Claude Opus 4.8 lists a 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. Claude Opus 4.8 is listed with these modalities: Chat, Vision, Reasoning.
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.
Both are Anthropic IDs. The field you change is model: claude-haiku-4-5 or claude-opus-4-8.
When to send claude-opus-4-8
Claude Opus 4.8 matches the Opus 5 list rate and window, without the Opus 5.5 cache-read cut. Send claude-opus-4-8 to keep an Opus 4.8 client unchanged.
Both are Anthropic IDs. The field you change is model: claude-opus-4-8 or claude-haiku-4-5.
The same volume, two bills
A sample of 1 million input tokens plus 200 thousand output tokens is about $0.400 on corouter (input $0.200, output $0.200).
A sample of 1 million input tokens plus 200 thousand output tokens is about $2.00 on corouter (input $1.00, output $1.00).
Questions
- Which output rate is lower, Claude Haiku 4.5 or Claude Opus 4.8?
- On output, Claude Haiku 4.5 is lower: $1.00 on corouter versus $5.00 for Claude Opus 4.8, about 5.00×. Input is $0.200 versus $1.00.
- 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.