This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Anthropic has launched a newer release, Claude Haiku 5.5. We suggest considering it instead.

Anthropic

•

Claude 4.5 Haiku

•

Proprietary model

•

Released October 2025

Claude 4.5 Haiku (Reasoning) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Claude 4.5 Haiku (Reasoning) for your use-case.

Fastest

Amazon

122.6 t/s

Google Vertex

97.6 t/s

Azure

87.4 t/s

Anthropic

86.5 t/s

Output speed

Total 4 providers

Lowest Latency

Azure

15.04 s

Amazon

15.64 s

Google Vertex

16.63 s

Anthropic

20.71 s

Time to first answer token

Total 4 providers

Lowest Price

Google Vertex

$0.77

Anthropic

$0.77

Azure

$0.77

Amazon

$0.85

Blended price (per 1M tokens)

Total 4 providers

Claude 4.5 Haiku is available through 4 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

For output speed, the top providers are Amazon (122.6 t/s), Google Vertex (97.6 t/s), and Azure (87.4 t/s).
For latency, Azure (15.04s), Amazon (15.64s), and Google Vertex (16.63s) offer the lowest time to first answer token.
For pricing, Google Vertex (0.77), Anthropic (0.77), and Azure (0.77) offer the lowest blended prices per 1M tokens.

Speed

Output tokens per second · Higher is better

Latency

Seconds to first answer token received · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Pricing

Pricing: Cache Hit, Input, and Output: Claude 4.5 Haiku Providers

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Cost per Intelligence Index Task: Claude 4.5 Haiku Providers

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Output Speed vs. Price: Claude 4.5 Haiku Providers

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Speed

Measured by Output Speed (tokens per second)

Output Speed: Claude 4.5 Haiku (Reasoning)

Output speed: output tokens per second · 10,000 input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Time per Intelligence Index Task: Claude 4.5 Haiku Providers

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Cost per Task vs. Time per Task: Claude 4.5 Haiku Providers

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task

Most attractive quadrant

Pareto line

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token: Claude 4.5 Haiku Providers

Seconds to first token received · Lower is better · 10,000 input tokens

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Cache Behaviour

Cache Hit Rate: Claude 4.5 Haiku Providers

Share of cacheable input tokens served from cache · Median of the last four weeks, updated Sep 26, 2026

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic coding sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate: Claude 4.5 Haiku Providers

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Sep 26, 2026

Most attractive quadrant

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time: Claude 4.5 Haiku Providers

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Key Comparison Metrics & API Features



Amazon Bedrock	200k	Proprietary	$0.38	123	15.64	19.72	--
Google	200k	Proprietary	$0.24	98	16.63	21.75	--
Anthropic	200k	Proprietary	$0.28	86	20.71	26.49	--
Microsoft Azure	200k	Proprietary	$0.22	87	15.04	20.76	--

Frequently Asked Questions

Common questions about Claude 4.5 Haiku (Reasoning) providers

Claude 4.5 Haiku (Reasoning) is available through 4 API providers: Amazon, Google Vertex, Anthropic, and Azure. Each provider offers different performance characteristics and pricing.

Claude 4.5 Haiku (Reasoning) is currently available through 4 API providers that we benchmark and track.

The fastest providers for Claude 4.5 Haiku (Reasoning) by output speed are Amazon (122.6 t/s), Google Vertex (97.6 t/s), and Azure (87.4 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first answer token for Claude 4.5 Haiku (Reasoning) are Azure (15.04s), Amazon (15.64s), and Google Vertex (16.63s). Lower latency means faster initial response time.

The most affordable providers for Claude 4.5 Haiku (Reasoning) by blended price are Google Vertex ($0.77 per 1M tokens), Anthropic ($0.77 per 1M tokens), and Azure ($0.77 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.

The providers with the lowest input token pricing for Claude 4.5 Haiku (Reasoning) are Google Vertex ($1.00 per 1M input tokens), Anthropic ($1.00 per 1M input tokens), and Azure ($1.00 per 1M input tokens).

The providers with the lowest output token pricing for Claude 4.5 Haiku (Reasoning) are Google Vertex ($5.00 per 1M output tokens), Anthropic ($5.00 per 1M output tokens), and Azure ($5.00 per 1M output tokens).

2 of 4 providers support JSON mode for Claude 4.5 Haiku (Reasoning): Google Vertex and Anthropic.

All 4 providers of Claude 4.5 Haiku (Reasoning) support function calling (tool use).

The best provider for Claude 4.5 Haiku (Reasoning) depends on your priorities: Amazon offers the highest output speed, Azure has the lowest latency, and Google Vertex provides the most competitive pricing.

When choosing a provider for Claude 4.5 Haiku (Reasoning), consider: output speed (for throughput-intensive tasks), 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 (Reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview

Claude 4.5 Haiku (Reasoning) API Provider Benchmarking & Analysis

Fastest

Lowest Latency

Lowest Price

Speed

Latency

Price

Pricing

Pricing: Cache Hit, Input, and Output: Claude 4.5 Haiku Providers

Cache Hit

Cost per Intelligence Index Task: Claude 4.5 Haiku Providers

Cost per Intelligence Index Task

Output Speed vs. Price: Claude 4.5 Haiku Providers

Output Speed

Speed

Output Speed: Claude 4.5 Haiku (Reasoning)

Output Speed

Model Performance Representation

Time per Intelligence Index Task: Claude 4.5 Haiku Providers

Time per Intelligence Index Task

Cost per Task vs. Time per Task: Claude 4.5 Haiku Providers

Cost per Intelligence Index Task

Latency

Time to First Answer Token: Claude 4.5 Haiku Providers

Time to First Answer Token

Median

Cache Behaviour

Cache Hit Rate: Claude 4.5 Haiku Providers

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate: Claude 4.5 Haiku Providers

Cost per Intelligence Index Task

End-to-End Response Time

End-to-End Response Time: Claude 4.5 Haiku Providers

End-to-End Response Time

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access Claude 4.5 Haiku (Reasoning)?

How many API providers offer Claude 4.5 Haiku (Reasoning)?

Which provider is fastest for Claude 4.5 Haiku (Reasoning)?

Which provider has the lowest latency for Claude 4.5 Haiku (Reasoning)?

Which provider is cheapest for Claude 4.5 Haiku (Reasoning)?

Which provider has the lowest input price for Claude 4.5 Haiku (Reasoning)?

Which provider has the lowest output price for Claude 4.5 Haiku (Reasoning)?

Which Claude 4.5 Haiku (Reasoning) providers support JSON mode?

Which Claude 4.5 Haiku (Reasoning) providers support function calling?

Which is the best provider for Claude 4.5 Haiku (Reasoning)?

How do I choose a provider for Claude 4.5 Haiku (Reasoning)?

Does provider performance for Claude 4.5 Haiku (Reasoning) change over time?

What are the overall capabilities of Claude 4.5 Haiku (Reasoning)?