API Status

claude-haiku-4.5 Benchmarks

Provider: bedrock

Explore real-world latency and throughput results for claude-haiku-4.5. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the bedrock provider hub to compare every tracked model side-by-side.


Benchmark Overview

Avg Tokens / Second

38.70

Avg Time to First Token (ms)

1200.00

Runs Analysed

1419

Last Updated

Apr 3, 2026, 10:43 AM

Key Insights

  • claude-haiku-4.5 streams at 38.70 tokens/second on average across the last 1419 benchmark runs.

  • Performance fluctuated by 61.72 tokens/second (159.5% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 1200.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.

  • Latest measurements completed on Apr 3, 2026, 10:43 AM based on 1419 total samples.

Performance Distribution

Distribution of throughput measurements showing performance consistency across benchmark runs.

Performance Over Time

Historical performance trends showing how throughput has changed over the benchmarking period.

claude-haiku-4.5

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
bedrockclaude-haiku-4.538.703.0864.801200.00

Frequently Asked Questions

The latest rolling average throughput is 38.70 tokens per second with an average time to first token of 1200.00 ms across 1419 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 10:43 AM.

Related Links