claude-3.5-haiku

completions

byanthropic

claude-3.5-haiku

completions

Published by: anthropicProvider:

anthropic

Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions. This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems. This model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).

Released

Oct 22, 2024

Knowledge

Apr 1, 2024

License

Proprietary

Context

200K

Input

$0.8 / 1M tokens

Output

$4 / 1M tokens

Cached

$0.08 / 1M tokens

Cached Write

$1.6 / 1M tokens

Capabilities: tools

Accepts: text, image

Returns: text

Released Oct 22, 2024Knowledge Cutoff: Apr 1, 2024License: Proprietary

Context: 200K Input: $0.8 / 1M tokensOutput: $4 / 1M tokensCached: $0.08 / 1M tokensCached Write: $1.6 / 1M tokensCapabilities: toolsAccepts: text, imageReturns: text

Access claude-3.5-haiku through LangDB AI Gateway

Recommended

Integrate with anthropic's claude-3.5-haiku and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for claude-3.5-haiku

Category Performance Scores:

Academia: Score 30.70 (Top 77% - Rank #258)
Marketing: Score 50.33 (Top 37% - Rank #124)
Science: Score 45.96 (Top 78% - Rank #262)
Writing: Score 45.16 (Top 47% - Rank #158)

Overall Performance: 43.03513888888889 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	3.30	Top 89%	Mathematics
AAII	20.20	Top 76%	General
DROP	83.10	Top 42%	General Knowledge
GPQA	41.20	Top 78%	STEM (Physics, Chemistry, Biology)
HLE	3.50	Top 93%	General Knowledge
HumanEval	88.10	Top 39%	Programming
LiveCodeBench	31.40	Top 55%	Programming
MATH-500	72.10	Top 67%	Mathematics
MMLU-Pro	64.20	Top 75%	General Knowledge
SciCode	27.40	Top 56%	Scientific

HumanEval Score: 88.10 - Coding capability benchmark

GPQA Score: 41.20 - Graduate-level reasoning benchmark

Model Comparison:

Provider: anthropic

Model Type: completions

Context Size: 200000 tokens

Comparing against 335 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

3.3

Mathematics

AAII

20.2

General

DROP

83.1

General Knowledge

GPQA

41.2

STEM (Physics, Chemistry, Biology)

HLE

3.5

General Knowledge

HumanEval

88.1

Programming

LiveCodeBench

31.4

Programming

MATH-500

72.1

Mathematics

MMLU-Pro

64.2

General Knowledge

SciCode

27.4

Scientific

Metric	AIME	AAII	DROP	GPQA	HLE	HumanEval	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	3.3	20.2	83.1	41.2	3.5	88.1	31.4	72.1	64.2	27.4

Compare with Similar Models

gemini-2.5-pro

gpt-4.1

gemini-2.5-pro-preview

grok-4

gemini-2.5-flash

gemini-2.5-flash-preview

Code Examples

Integration samples and API usage

Code Samples for claude-3.5-haiku

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="claude-3.5-haiku",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "claude-3.5-haiku",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3.5-haiku",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: claude-3.5-haiku

Provider: anthropic

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from anthropic

claude-3.5-haiku

claude-3.5-haiku

Access claude-3.5-haiku through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

claude-sonnet-4.5

claude-sonnet-4

claude-opus-4

claude-3.7-sonnet

claude-3-5-sonnet-20240620

claude-3-haiku-20240307

claude-3.5-haiku by anthropic - AI Model Details, Pricing, and Performance Metrics

claude-3.5-haiku

claude-3.5-haiku

Access claude-3.5-haiku through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

claude-sonnet-4.5

claude-sonnet-4

claude-opus-4

claude-3.7-sonnet

claude-3-5-sonnet-20240620

claude-3-haiku-20240307