Anthropic
Claude Opus 4 API
Claude Opus 4 is Anthropic's most intelligent model — excelling at complex reasoning, multi-step agentic workflows, advanced coding, and nuanced long-form writing. It has a 200K token context window and supports vision. Use Opus when output quality matters more than cost.
- Input
- $15.00
- Output
- $75.00
- Context
- 200K
- Vision
- Yes
/ 1M tokens
/ 1M tokens
tokens
Top use cases
- Complex multi-step agents and tool use
- Research-grade analysis and synthesis
- Production-quality long-form writing
- Advanced coding (architecture, refactoring, code review)
- High-stakes decision support
Use Claude Opus 4 in 30 seconds
ModelServer is OpenAI-compatible. Point your existing OpenAI SDK at modelserver.dev/v1 and set the model name to claude-opus-4.
claude-opus-4.py
from openai import OpenAI
client = OpenAI(
api_key="sk-modelserver-...",
base_url="https://modelserver.dev/v1",
)
response = client.chat.completions.create(
model="claude-opus-4",
messages=[
{"role": "user", "content": "Hello, Claude Opus 4!"}
],
)
print(response.choices[0].message.content)Frequently asked questions
- How much does Claude Opus 4 cost?
- Claude Opus 4 is priced at $15.00 per 1M input tokens and $75.00 per 1M output tokens via ModelServer. ModelServer adds a flat 5.5% platform fee on top — no markups on individual tokens, no monthly minimum.
- What is the Claude Opus 4 context window?
- Claude Opus 4 supports a 200K token context window. You can put roughly 150,000 words in a single prompt.
- Is Claude Opus 4 OpenAI-compatible via ModelServer?
- Yes. Point your OpenAI SDK base_url to https://modelserver.dev/v1 and set model="claude-opus-4". Existing OpenAI-SDK code works without modification.
- Who is Claude Opus 4 best for?
- Teams that need the highest output quality and can pay flagship pricing.
- Does Claude Opus 4 support vision input?
- Yes. Claude Opus 4 accepts image inputs alongside text. Pass images as base64 or URL in the OpenAI-compatible message format.