Anthropic

Anthropic: Claude 3 Sonnet

stable

Claude 3 Sonnet is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

claude-3-sonnet-20240229claude-3
ProviderQuick start
Context
200K
tokens
Max output
4.1K
tokens
Input
$3.00
per 1M
Output
$15.00
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
Anthropic
Anthropic
200K$3.00$15.00

Pricing

ItemPriceUnit
Input$3.00per 1M tokens
Output$15.00per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
claude-3-sonnet-20240229
Family
claude-3
Status
stable
Knowledge
-
Released
-
Gateway Config
API
2023-06-01
Auth
ANTHROPIC_API_KEY
Discovery
static
Provider type
static

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@anthropic/claude-3-sonnet-20240229",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.anthropic.com/v1
Chat completions
https://api.anthropic.com/v1/chat/completions
Model
claude-3-sonnet-20240229
Auth env
ANTHROPIC_API_KEY

Claude 3 Sonnet FAQ

How much does the Claude 3 Sonnet API cost?

Through Anthropic, Claude 3 Sonnet costs $3.00 per 1M input tokens and $15.00 per 1M output tokens.

What is the context window of Claude 3 Sonnet?

Claude 3 Sonnet accepts up to 200K tokens of context and returns up to 4.1K output tokens on Anthropic.

What can Claude 3 Sonnet do?

Claude 3 Sonnet supports chat, function calling and image input. It accepts text and image input.

How do I call Claude 3 Sonnet through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @anthropic/claude-3-sonnet-20240229. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.