Using Claude Sonnet 4 on Replicate API

Implementation guide · Claude 4 · Anthropic

Deprecated

Replicate API exposes Claude Sonnet 4 through model ID anthropic/claude-4-sonnet. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-18. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Replicate API and generate an API key.
  2. 2
    Use the Replicate API SDK or REST API to call anthropic/claude-4-sonnet — see the documentation for request format.
  3. 3
    You'll be billed $3.00/1M input, $15.00/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

Install
pip install replicate
API key
REPLICATE_API_TOKEN
Model ID
anthropic/claude-4-sonnet

Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.

import replicate

# reads REPLICATE_API_TOKEN from env
# anthropic/claude-4-sonnet format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "anthropic/claude-4-sonnet",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Pricing on Replicate API

TypePrice (per 1M)
Input tokens$3.00
Output tokens$15.00

Capabilities

VisionMultimodalStructured Outputs

About Claude Sonnet 4

Claude Sonnet 4 API snapshot (claude-sonnet-4-20250514) is deprecated and scheduled to retire from Anthropic-operated platforms on June 15, 2026. Use Claude Sonnet 4.6 for current integrations.

Full model details →

Model Specs

Released2025-05-22
Context200K

Also available on(6)

Anthropic$3.00/1MOpenRouter$3.00/1MVercel AI Gateway$3.00/1M
Compare all providers →

Provider

Replicate API

Replicate

San Francisco, California, United States