claude-haiku-4.5

completions

byanthropic

claude-haiku-4.5

completions

Published by: anthropicProvider:

anthropic

Claude Haiku 4.5 is our fastest, most cost-efficient model, matching Sonnet 4’s performance on coding, computer use, and agent tasks. Claude Haiku 4.5 scores 73.3% on SWE-bench Verified, making it one of the world's best coding models.

Released

Oct 15, 2025

Knowledge

Feb 1, 2025

License

Proprietary

Context

200K

Input

$1 / 1M tokens

Output

$5 / 1M tokens

Cached

$0.1 / 1M tokens

Cached Write

$1.5 / 1M tokens

Capabilities: tools

Accepts: text, image

Returns: text

Released Oct 15, 2025Knowledge Cutoff: Feb 1, 2025License: Proprietary

Context: 200K Input: $1 / 1M tokensOutput: $5 / 1M tokensCached: $0.1 / 1M tokensCached Write: $1.5 / 1M tokensCapabilities: toolsAccepts: text, imageReturns: text

Access claude-haiku-4.5 through LangDB AI Gateway

Recommended

Integrate with anthropic's claude-haiku-4.5 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-haiku-4.5

Category Performance Scores:

Maths: Score 39.00 (Top 56% - Rank #180)
Finance: Score 40.35 (Top 56% - Rank #180)
Science: Score 68.09 (Top 36% - Rank #116)
Writing: Score 52.80 (Top 43% - Rank #138)
Academia: Score 57.35 (Top 35% - Rank #112)
Marketing: Score 53.53 (Top 40% - Rank #128)
Programming: Score 37.00 (Top 39% - Rank #125)

Overall Performance: 49.73198412698413 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
HLE	4.30	Top 67%	General Knowledge
GPQA	73.00	Top 33%	STEM (Physics, Chemistry, Biology)
SciCode	34.40	Top 38%	Scientific
MMLU-Pro	80.00	Top 37%	General Knowledge
LiveCodeBench	51.10	Top 38%	Programming
AA Math Index	39.00	Top 56%	Mathematics
AA Coding Index	37.00	Top 39%	Programming
AAII	41.70	Top 35%	General

GPQA Score: 73.00 - Graduate-level reasoning benchmark

Model Comparison:

Provider: anthropic

Model Type: completions

Context Size: 200000 tokens

Comparing against 320 models in the database

Performance Analytics for claude-haiku-4.5

Usage Statistics (Last 2 Days):

Total Requests: 6 API calls
Average TPS: 621.78 tokens per second
Average Response Time: 4699.40ms
Average Time to First Token: 921.80ms
Total Cost: $0.03
Average Request Cost: $0.0045

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
11/12/2025	3	387.80	5608.60ms	859.10ms	$0.01
11/17/2025	3	968.00	3790.30ms	984.50ms	$0.02

Performance Summary:

Model: claude-haiku-4.5 by anthropic

Monitoring Period: 11/11/2025 to 11/18/2025

Average Daily Requests: 3

Peak Daily Requests: 3

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

621.78 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

HLE

4.3

General Knowledge

GPQA

73.0

STEM (Physics, Chemistry, Biology)

SciCode

34.4

Scientific

MMLU-Pro

80.0

General Knowledge

LiveCodeBench

51.1

Programming

AA Math Index

39.0

Mathematics

AA Coding Index

37.0

Programming

AAII

41.7

General

Metric	HLE	GPQA	SciCode	MMLU-Pro	LiveCodeBench	AA Math Index	AA Coding Index	AAII
Score	4.3	73.0	34.4	80.0	51.1	39.0	37.0	41.7

Compare with Similar Models

gemini-3-pro-preview

gemini-2.5-pro

gpt-4.1

gemini-2.5-pro-preview

grok-4

gemini-2.5-flash

Code Examples

Integration samples and API usage

Code Samples for claude-haiku-4.5

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-haiku-4.5",
    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-haiku-4.5",
    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-haiku-4.5",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: claude-haiku-4.5

Provider: anthropic

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

Create API Key

Related Models

Similar models from anthropic

claude-haiku-4.5

claude-haiku-4.5

Access claude-haiku-4.5 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

claude-opus-4.5

claude-sonnet-4.5

claude-sonnet-4

claude-opus-4

claude-3.7-sonnet

claude-3-5-sonnet-20240620

claude-haiku-4.5 by anthropic - AI Model Details, Pricing, and Performance Metrics

claude-haiku-4.5

claude-haiku-4.5

Access claude-haiku-4.5 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

claude-opus-4.5

claude-sonnet-4.5

claude-sonnet-4

claude-opus-4

claude-3.7-sonnet

claude-3-5-sonnet-20240620