Anthropic: Claude Opus 4

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Model lab: Anthropic
Model family: claude-opus

Modalitiestext, image, pdf → text

Context window200,000

Maximum output32,000

InputUSD 12 / 1M tokens

OutputUSD 60 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to anthropic/claude-opus-4-20250514.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "anthropic/claude-opus-4-20250514"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Claude Opus 4 API Pricing

Type	Price information
Input	USD 12 / 1M tokens
Output	USD 60 / 1M tokens
Cached input	USD 1.2 / 1M tokens
Cache write	USD 15 / 1M tokens

Benchmarks

Benchmark	Score	Measurement	Source
Aider Polyglot	72	percent correct · Date: 2025-05-25

Performance

Performance trends

Throughput90.7 tok/sCurrent

Time to first token1.3 sCurrent

End-to-end latency7.9 sCurrent

Throughput

Current90.7 tok/s

Window average89.5 tok/s

Time to first token

Current1.3 s

Window average1.5 s

End-to-end latency

Current7.9 s

Window average7.5 s

Tail latency (P99)

Current13.9 s

Window average17.3 s

Prompt cache hit rate

Current31.5%

Window average23.2%

Error rate

Current0.7%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Claude Opus 4 Compare models

Model	Input price	Output price	Context window	Capabilities
Claude Opus 4This page	USD 12 / 1M tokens	USD 60 / 1M tokens	200,000	Text output · Reasoning · Tool calling
Claude Opus 5.5	USD 3.2 / 1M tokens	USD 16 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Claude Opus 5	USD 4 / 1M tokens	USD 20 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Claude Opus 4.8	USD 3.43432 / 1M tokens	USD 17.17168 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Claude Opus 4.7	USD 4 / 1M tokens	USD 20 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling

Model specifications

Input: text, image, pdf
Output: text
Context window: 200,000
Maximum output: 32,000
Release date: 2025-05-22
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Claude Opus 4 for?

Flagship Claude model for deep reasoning, coding, and long-horizon agents

What inputs and outputs does Claude Opus 4 support?

Recorded inputs: text, images, PDF; outputs: text.

How is Claude Opus 4 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 12 / 1M tokens; Output USD 60 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Claude Opus 4?

Current model records list Context window 200,000 tokens; Maximum output 32,000 tokens.

What model parameter does the Quickstart use?

The example uses anthropic/claude-opus-4-20250514. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.