Claude Haiku 5.5
官方定价输入 $0.10 / 输出 $0.50。适合高并发、低延迟的分类、抽取和路由。
分类、抽取、路由先走这条。
Haiku for high volume, Sonnet for everyday work, Opus for the hardest jobs. Same account, billed by channel discount.
Haiku for high volume, Sonnet for everyday work, Opus for the hardest jobs. Same account, billed by channel discount.
Different models · Different strengths
Pick the strength first, then the channel. Model IDs stay the same; discounts follow the channel.
官方定价输入 $0.10 / 输出 $0.50。适合高并发、低延迟的分类、抽取和路由。
分类、抽取、路由先走这条。
在 Sonnet 5 上加强编码与长上下文稳定性,适合作为默认开发模型。
仓库阅读、改 bug、常规实现用它。
官方定价输入 $4 / 输出 $20。适合最难的代理、复杂编码和多步推理。
最难的代理和编码任务再切这条。
Model notes come from the current catalog. Live prices on this site take precedence.
Channel discounts
Same models, billed by channel. Check the discount, then pick the route.
Routed via official subscription, best value for daily development and debugging
19% of list price
Choose a channelRouted via official subscription, best value for daily development and debugging
39% of list price
Choose a channelRouted via AWS/Azure cloud services, high stability for production environments
65% of list price
Choose a channelDiscounts come from the same source as channel management. Live prices on this site take precedence.
Public benchmarks
Intelligence Index for capability, output speed for how fast it writes. Numbers come from the Artificial Analysis public API.
Source: Artificial Analysis. Speed is median output tokens/s. Latency is time to first token in seconds. Source: Artificial Analysis

From one chat to your own workflow
Once the model is chosen, take the same Model ID into your tools in three steps.
Open your AI Code With account and create the key you'll use in your tool or application.
Use the OpenAI-compatible endpoint and paste in the exact Model ID.
Start with Haiku, then switch to Sonnet or Opus when the task needs it.