Activefastllm Proprietary

Claude 3.5 Haiku

by Anthropic· Released October 2024· Cutoff April 2024

Claude 3.5 Haiku is Anthropic's fastest model in the Claude 3.5 family, offering low latency and high throughput for everyday tasks. It combines speed with strong performance on coding, reasoning, and language tasks, making it ideal for real-time applications and cost-sensitive deployments.

Official Site API Docs

Input cost

$0.80 per 1M tokens

Output cost

$4.00 per 1M tokens

Context window

200K tokens

Max output

8192 tokens

Modalities

textimage

License

proprietary

Capabilities

Function CallingVisionCode GenerationStreamingJSON ModeTool UseMultilingual Support

Best For

Fast, cost-effective inference for real-time applications and high-volume tasks.

Strengths

Lowest latency among Claude models
Strong coding and reasoning for its size
Cost-effective pricing
Supports vision and tool use

Limitations

Lower overall intelligence compared to Claude 3.5 Sonnet and Opus
Not suitable for complex multi-step reasoning tasks
Smaller context window than some competitors

Use Cases

Real-time chatbots

Code autocomplete and generation

Customer support automation

Content moderation

Data extraction and classification

Lightweight summarization

Translation and multilingual tasks

Improvements Over Previous Model

Context window increased from 100K to 200K tokens
Significantly faster inference — ~3× lower latency than Claude 3 Haiku
Added native vision/image input support
Improved coding benchmark scores (HumanEval 92% vs 85%)
Lower pricing: $0.80/M tokens vs $1.25/M tokens input

Back to all models