AnthropicReleased on Oct 22, 2024

Claude 3.5 Haiku: API Pricing, Context Window & Benchmarks

Claude 3.5 Haiku is a language model from Anthropic, released in October 2024.

Claude 3.5 Haiku is Anthropic's fastest model, delivering advanced coding, tool use, and reasoning capabilities at an accessible price. It excels at user-facing products, specialized sub-agent tasks, and generating personalized experiences

Input
Text
Output
Text

Claude 3.5 Haiku benchmarks

Rankings

Quality Tracker

Claude 3.5 Haiku Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Wed Jul 22 2026
Notice missing or incorrect data?

Claude 3.5 Haiku pricing

Providers

Claude 3.5 Haiku starts at $0.800 per million input tokens and $4.00 per million output tokens via Bedrock. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
Bedrock logoBedrock
$0.800$4.00200.0K/200.0K
/0.50
104/
/
Google logoGoogle
$0.800$4.00200.0K/200.0K
/0.40
42/
/
Anthropic logoAnthropic
$1.00$5.00200.0K/200.0K
/0.30
100/
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

Loading chart...
Loading chart...
Loading chart...

Claude 3.5 Haiku context window

Input and output token limits for Claude 3.5 Haiku, plus how it ranks on long-context understanding.

InputOutput
200Ktokens
200Ktokens
301 pages of text
200K
8K128K1M

Claude 3.5 Haiku API

Available from the model provider

Claude 3.5 Haiku has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Claude 3.5 Haiku latency

Claude 3.5 Haiku time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Claude 3.5 Haiku examples

Recent arena outputs from Claude 3.5 Haiku, picked from the highest-ranked matchups.

Claude 3.5 Haiku license

Claude 3.5 Haiku is a proprietary model available under its provider's product and API terms.

License
Proprietary
Hosted access

Proprietary license - usage restrictions apply

Claude 3.5 Haiku resources

Official sources for Claude 3.5 Haiku: api documentation, official playground, official launch post.

Claude 3.5 Haiku vs other models

The most-compared alternatives to Claude 3.5 Haiku are Llama 3.1 70B Instruct, Claude 3 Sonnet, o1. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Claude 3.5 Haiku

Models ranked just above and below Claude 3.5 Haiku by LLM Stats score.

 

Llama 3.1 70B Instruct

Score pending
 

Claude 3 Sonnet

Score pending
 

o1

Score pending
 

Nova Lite

Score pending
 

Mistral Small 3.2 24B Instruct

Score pending
 

Nova Micro

Score pending

FAQ

Common questions about Claude 3.5 Haiku.

When was Claude 3.5 Haiku released?

Claude 3.5 Haiku was released on October 22, 2024 by Anthropic. This is the official Claude 3.5 Haiku release date tracked on LLM Stats.

How much does Claude 3.5 Haiku cost?

Claude 3.5 Haiku pricing starts at $0.80 per million input tokens and $4.00 per million output tokens via Bedrock, the lowest price among tracked providers.

Is Claude 3.5 Haiku available via API?

Yes, Claude 3.5 Haiku is available via API. See the official documentation for authentication and endpoint details. It is served by 3 providers tracked on LLM Stats.

Who created Claude 3.5 Haiku?

Claude 3.5 Haiku was created by Anthropic.

What is the license for Claude 3.5 Haiku?

Claude 3.5 Haiku is released under the Proprietary license.

What is Claude 3.5 Haiku latency?

Claude 3.5 Haiku p95 time to first token is 0.30 seconds via Anthropic over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use Claude 3.5 Haiku?

Claude 3.5 Haiku is available through 3 providers including Bedrock, Google, Anthropic.

Where is the Claude 3.5 Haiku paper or technical report?

Claude 3.5 Haiku has a paper or technical report available at https://www.anthropic.com/news/claude-3-5-haiku. Use that source for architecture, training, release and evaluation details.

What models should I compare Claude 3.5 Haiku against?

Common Claude 3.5 Haiku comparisons include Claude 3.5 Haiku vs Llama 3.1 70B Instruct, Claude 3.5 Haiku vs Claude 3 Sonnet, Claude 3.5 Haiku vs o1. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.