Anthropic: Claude Haiku 4.5
anthropic/claude-haiku-4-5Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.
Providers
8 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Amazon Bedrock | $1.00 | $5.00 | $0.10 | 0.97s | 66 tps | 100% |
 Anthropic | $1.00 | $5.00 | $0.10 | 0.55s | 83 tps | 100% |
 Google Vertexus-east5 | $1.10 | $5.50 | $0.11 | 2.55s | 197 tps | 100% |
| Amazon Bedrockeu-west-1 | $1.10 | $5.50 | $0.11 | 0.87s | 95 tps | 100% |
| Google Vertexeurope-west1 | $1.10 | $5.50 | $0.11 | 0.38s | 89 tps | 100% |
| Google Vertexglobal | $1.00 | $5.00 | $0.10 | 0.68s | 75 tps | 99.95% |
 Azureglobal | $1.00 | $5.00 | $0.10 | 0.57s | 78 tps | 99.89% |
| Amazon Bedrockus-east-1 | $1.10 | $5.50 | $0.11 | 1.21s | 95 tps | 98.72% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Claude Haiku 4.5 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Claude Haiku 4.5 costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Apps
Tools that most often run Claude Haiku 4.5, by tokens this week.
Activity
948.1B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
