Anthropic

Claude Sonnet 4 API

Claude Sonnet 4 is the workhorse of the Claude 4 family — strong reasoning, fast latency, and 5× cheaper than Opus. It has a 200K context window, supports vision, and is the recommended default for most production workloads.

Input
$3.00
/ 1M tokens
Output
$15.00
/ 1M tokens
Context
200K
tokens
Vision
Yes

Top use cases

  • Production chat and customer support
  • Code generation and review at scale
  • Document summarization and Q&A
  • RAG-backed knowledge assistants
  • Most agentic workflows

Use Claude Sonnet 4 in 30 seconds

ModelServer is OpenAI-compatible. Point your existing OpenAI SDK at modelserver.dev/v1 and set the model name to claude-sonnet-4.

claude-sonnet-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-sonnet-4",
    messages=[
        {"role": "user", "content": "Hello, Claude Sonnet 4!"}
    ],
)

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

Frequently asked questions

How much does Claude Sonnet 4 cost?
Claude Sonnet 4 is priced at $3.00 per 1M input tokens and $15.00 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 Sonnet 4 context window?
Claude Sonnet 4 supports a 200K token context window. You can put roughly 150,000 words in a single prompt.
Is Claude Sonnet 4 OpenAI-compatible via ModelServer?
Yes. Point your OpenAI SDK base_url to https://modelserver.dev/v1 and set model="claude-sonnet-4". Existing OpenAI-SDK code works without modification.
Who is Claude Sonnet 4 best for?
The default Claude — pick this unless you have a specific reason not to.
Does Claude Sonnet 4 support vision input?
Yes. Claude Sonnet 4 accepts image inputs alongside text. Pass images as base64 or URL in the OpenAI-compatible message format.

Other Anthropic models

Claude Sonnet 4 API — Pricing & Access — ModelServer