Model comparison
Claude Haiku 4.5 vs Claude Sonnet 4.6
List rate, corouter rate, context, and which ID to send for claude-haiku-4-5 versus claude-sonnet-4-6. 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 $1.20 on corouter (input $0.600, output $0.600).
| Claude Haiku 4.5 | Claude Sonnet 4.6 | |
|---|---|---|
| ID | claude-haiku-4-5 | claude-sonnet-4-6 |
| Vendor | Anthropic | Anthropic |
| List input | $1.00 | $3.00 |
| corouter input | $0.200 | $0.600 |
| List output | $5.00 | $15.00 |
| corouter output | $1.00 | $3.00 |
| Cache read | $0.020 | $0.060 |
| Context | 200K | 1M |
Price gap
On output, Claude Haiku 4.5 is lower: $1.00 on corouter versus $3.00 for Claude Sonnet 4.6, about 3.00×. Input is $0.200 versus $0.600.
Window and modalities
Claude Sonnet 4.6 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 Sonnet 4.6 is listed with these modalities: Chat, Vision, 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.
Both are Anthropic IDs. The field you change is model: claude-haiku-4-5 or claude-sonnet-4-6.
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.
Both are Anthropic IDs. The field you change is model: claude-sonnet-4-6 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 $1.20 on corouter (input $0.600, output $0.600).
Questions
- Which output rate is lower, Claude Haiku 4.5 or Claude Sonnet 4.6?
- On output, Claude Haiku 4.5 is lower: $1.00 on corouter versus $3.00 for Claude Sonnet 4.6, about 3.00×. Input is $0.200 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.