This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Anthropic has launched a newer release, Claude Haiku 5.5. We suggest considering it instead.
Claude 4.5 Haiku (Non-reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Claude 4.5 Haiku (Non-reasoning) for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 4 providers
Lowest Cost per Task
Cost per Intelligence Index task
Total 4 providers
Claude 4.5 Haiku (non-reasoning) is available through 4 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
Pricing
Cost per Intelligence Index Task: Claude 4.5 Haiku (Non-reasoning)
Pricing: Cache Hit, Input, and Output: Claude 4.5 Haiku (Non-reasoning)
Output Speed vs. Cost per Task: Claude 4.5 Haiku (Non-reasoning)
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Claude 4.5 Haiku (Non-reasoning)
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Claude 4.5 Haiku (Non-reasoning)
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Claude 4.5 Haiku (Non-reasoning)
Caching
Cache Hit Rate: Claude 4.5 Haiku (Non-reasoning)
Cost per Task vs. Cache Hit Rate: Claude 4.5 Haiku (Non-reasoning)
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Claude 4.5 Haiku (Non-reasoning) providers
Claude 4.5 Haiku (Non-reasoning) is available through 4 API providers: Amazon, Azure, Anthropic, and Google Vertex. Each provider offers different performance characteristics and pricing.
Claude 4.5 Haiku (Non-reasoning) is currently available through 4 API providers that we benchmark and track.
The providers with the lowest time to first answer token for Claude 4.5 Haiku (Non-reasoning) are Google Vertex (0.64s), Anthropic (0.82s), and Amazon (0.89s). Lower latency means faster initial response time.
2 of 4 providers support JSON mode for Claude 4.5 Haiku (Non-reasoning): Anthropic and Google Vertex.
All 4 providers of Claude 4.5 Haiku (Non-reasoning) support function calling (tool use).
When choosing a provider for Claude 4.5 Haiku (Non-reasoning), consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Claude 4.5 Haiku (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview