Claude Haiku 4.5
Anthropic's fastest, lightweight model — ideal for high-throughput, latency-sensitive, cost-conscious workloads.
VisionToolsStructured outputFiles
Context window
200K
Max output
64K
Input price
$1.00 /1M
Output price
$5.00 /1M
Available routes
The same Claude Haiku 4.5 runs on 7 different routes through the Opper gateway. Each route has its own data-handling posture.
| Provider | Region | Zero data retention | Training | Logging | Contract | Input | Output |
|---|---|---|---|---|---|---|---|
| Anthropic | US | Opt-in | No (opt-in) | Abuse monitoring; default duration not in public docs (DPA needed). | Enterprise | $1.00 | $5.00 |
| AWS Bedrock | EU | Default | No | None | PAYG | $1.10 | $5.50 |
| Azure OpenAI | EU | Opt-in | No | Up to 30 days for abuse monitoring | EA/MCA-E | $1.00 | $5.00 |
| Google Cloud | US | Opt-in | No | Abuse monitoring. Partner-model coverage requires written verification. | PAYG | $1.00 | $5.00 |
| Google Cloud | EU | Opt-in | No | Abuse monitoring. Vertex ZDR doc excludes partner models — partner-specific terms apply, verify in writing. | PAYG | $1.10 | $5.50 |
| Google Cloud | EU | Opt-in | No | Abuse monitoring. Vertex ZDR doc excludes partner models — partner-specific terms apply, verify in writing. | PAYG | $1.00 | $5.00 |
| Google Cloud | EU | Opt-in | No | Abuse monitoring. Vertex ZDR doc excludes partner models — partner-specific terms apply, verify in writing. | PAYG | $1.10 | $5.50 |
Human review: Abuse-flagged only