Claude Haiku 4.5 on Google Cloud is a high-performance model for a wide range of use cases and coding tasks, with the speed and cost efficiency to power free products and high-volume user experiences.
Retirement Date: Not sooner than Oct 15, 2026.
- Free tier user experiences: Claude Haiku 4.5 on Google Cloud delivers near-frontier performance at a cost and speed that makes free agent products and agentic use cases economically viable at scale.
- Latency-sensitive experiences: Claude Haiku 4.5 on Google Cloud's speed is ideal for real-time applications like customer service agents and chatbots where response time is critical.
- Coding sub-agents: Use Claude Haiku 4.5 on Google Cloud to power sub-agents, enabling multi-agent systems that tackle complex refactors, migrations, and large feature builds with quality and speed.
- Financial analysis: Use Claude Haiku 4.5 on Google Cloud to monitor thousands of data streams—tracking regulatory changes, market signals, and portfolio risks to preemptively adapt compliance and trading systems at previously impossible scales.
- Research sub-agents: Perform parallel analyses across multiple data sources while maintaining fast response times. Ideal for rapid business intelligence, competitive analysis, and real-time decision support.
- Business tasks: Claude Haiku 4.5 on Google Cloud is capable of producing and editing office files like slides, documents, and spreadsheets. It also better supports strategy and campaign planning, business analysis and brainstorming.
Try in Agent Studio View model card in Model Garden
| Model ID | claude-haiku-4-5 |
|
|---|---|---|
| Launch stage | GA | |
| Supported inputs & outputs |
|
|
| Token limits |
|
|
| Capabilities |
|
|
| Usage types |
|
|
| Technical specifications | ||
| Images |
|
|
| Documents |
|
|
| Versions |
|
|
| Supported regions | ||
|
Model availability (Includes fixed quota & Provisioned Throughput) |
|
|
|
ML processing |
|
|
| Quota limits |
us-east5:
europe-west1:
global endpoint:
|
|
| Pricing | See Pricing. | |