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 3.5 Haiku. We suggest considering it instead.

Anthropic

•

Proprietary model

•

Released March 2024

Claude 3 Haiku API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Claude 3 Haiku for your use-case.

Lowest Time per Task

Time per Intelligence Index task (minutes)

Total 1 provider

Lowest Cost per Task

Cost per Intelligence Index task

Total 1 provider

Claude 3 Haiku is available through Amazon.

Benchmarks of providers are not available for this model.

Please see the models page for Claude 3 Haiku for details of the model and its intelligence compared to other models.

Time per Task

Inference time (minutes) per Intelligence Index task · Lower is better

No data available

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

No data available

Pricing

Cost per Intelligence Index Task: Claude 3 Haiku

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

No data available

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.

Pricing: Cache Hit, Input, and Output: Claude 3 Haiku

Price (USD per M Tokens) · Lower is better

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.

Output Speed vs. Cost per Task: Claude 3 Haiku

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task

Most attractive quadrant

No data available

Output tokens, including reasoning tokens, received per second over a request's full duration, from sending the request to receiving the final token. The headline value averages each Performance v3 workload over the past 5 days, then averages the workloads.

Speed

Average of the single-request and multi-turn agentic workloads measured

Output Speed: Claude 3 Haiku

Output tokens divided by total request time · Includes time to first token · Average of the single-request and multi-turn agentic workloads measured · Higher is better

No data available

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: Claude 3 Haiku

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

No data available

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.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: Claude 3 Haiku

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

No data available

Share of requests over the past 5 days that the endpoint failed with an error, a rate limit or a timeout. Failures on our side are left out of both counts. Across several workloads, the failures and requests are pooled before dividing.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Key Comparison Metrics & API Features



Amazon Bedrock	--	--	--	--	200k			Proprietary

Frequently Asked Questions

Common questions about Claude 3 Haiku providers

Claude 3 Haiku is available through 1 API provider: Amazon. Each provider offers different performance characteristics and pricing.

Claude 3 Haiku is currently available through 1 API provider that we benchmark and track.

The most affordable provider for Claude 3 Haiku by blended price is Amazon ($0.35 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.

The provider with the lowest input token pricing for Claude 3 Haiku is Amazon ($0.25 per 1M input tokens).

The provider with the lowest output token pricing for Claude 3 Haiku is Amazon ($1.25 per 1M output tokens).

The only provider of Claude 3 Haiku supports function calling (tool use).

When choosing a provider for Claude 3 Haiku, 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 3 Haiku's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview

Claude 3 Haiku API Provider Benchmarking & Analysis

Lowest Time per Task

Lowest Cost per Task

Time per Task

Cost per Task

Pricing

Cost per Intelligence Index Task: Claude 3 Haiku

Cost per Intelligence Index Task

Pricing: Cache Hit, Input, and Output: Claude 3 Haiku

Cache Hit

Output Speed vs. Cost per Task: Claude 3 Haiku

End-to-End Output Speed

Speed

Output Speed: Claude 3 Haiku

End-to-End Output Speed

Time Period

Latency

Time to First Answer Token: Claude 3 Haiku

Time to First Answer Token

Time Period

Reliability

Endpoint Error Rate: Claude 3 Haiku

Endpoint Error Rate

Time Period

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access Claude 3 Haiku?

How many API providers offer Claude 3 Haiku?

Which provider is cheapest for Claude 3 Haiku?

Which provider has the lowest input price for Claude 3 Haiku?

Which provider has the lowest output price for Claude 3 Haiku?

Which Claude 3 Haiku providers support function calling?

How do I choose a provider for Claude 3 Haiku?

Does provider performance for Claude 3 Haiku change over time?

What are the overall capabilities of Claude 3 Haiku?