claude-opus-4

completions

byanthropic

claude-opus-4

completions

Published by: anthropicProvider:

anthropic

Our most capable and intelligent model yet. Claude Opus 4 sets new standards in complex reasoning and advanced coding

Released

Aug 5, 2025

Knowledge

Mar 1, 2025

License

Proprietary

Context

200K

Input

$15 / 1M tokens

Output

$75 / 1M tokens

Cached

$1.5 / 1M tokens

Cached Write

$18.75 / 1M tokens

Capabilities: tools

Accepts: text, image

Returns: text

Released Aug 5, 2025Knowledge Cutoff: Mar 1, 2025License: Proprietary

Context: 200K Input: $15 / 1M tokensOutput: $75 / 1M tokensCached: $1.5 / 1M tokensCached Write: $18.75 / 1M tokensCapabilities: toolsAccepts: text, imageReturns: text

Access claude-opus-4 through LangDB AI Gateway

Recommended

Integrate with anthropic's claude-opus-4 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-opus-4

Category Performance Scores:

Academia: Score 56.20 (Top 28% - Rank #94)
Finance: Score 39.30 (Top 54% - Rank #181)
Marketing: Score 53.02 (Top 34% - Rank #114)
Maths: Score 36.30 (Top 54% - Rank #181)
Science: Score 69.15 (Top 28% - Rank #94)
Writing: Score 52.43 (Top 38% - Rank #128)

Overall Performance: 51.067499999999995 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	56.30	Top 29%	Mathematics
AAII	42.30	Top 27%	General
AA Math Index	36.30	Top 54%	Mathematics
GPQA	70.10	Top 29%	STEM (Physics, Chemistry, Biology)
HLE	5.90	Top 36%	General Knowledge
LiveCodeBench	54.20	Top 34%	Programming
MATH-500	94.10	Top 27%	Mathematics
MMLU-Pro	86.00	Top 3%	General Knowledge
SciCode	40.90	Top 4%	Scientific

GPQA Score: 70.10 - Graduate-level reasoning benchmark

Model Comparison:

Provider: anthropic

Model Type: completions

Context Size: 200000 tokens

Comparing against 335 models in the database

Performance Analytics for claude-opus-4

Usage Statistics (Last 2 Days):

Total Requests: 69 API calls
Average TPS: 5439.83 tokens per second
Average Response Time: 20037.40ms
Average Time to First Token: 8363.90ms
Total Cost: $139.56
Average Request Cost: $2.0227

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
10/3/2025	68	5603.05	19736.50ms	8463.10ms	$139.45
10/8/2025	1	31.11	40499.60ms	1622.50ms	$0.11

Performance Summary:

Model: claude-opus-4 by anthropic

Monitoring Period: 10/2/2025 to 10/9/2025

Average Daily Requests: 35

Peak Daily Requests: 68

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

5439.83 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

56.3

Mathematics

AAII

42.3

General

AA Math Index

36.3

Mathematics

GPQA

70.1

STEM (Physics, Chemistry, Biology)

HLE

5.9

General Knowledge

LiveCodeBench

54.2

Programming

MATH-500

94.1

Mathematics

MMLU-Pro

86.0

General Knowledge

SciCode

40.9

Scientific

Metric	AIME	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	56.3	42.3	36.3	70.1	5.9	54.2	94.1	86.0	40.9

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-opus-4

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-opus-4",
    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-opus-4",
    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-opus-4",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: claude-opus-4

Provider: anthropic

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