Using Grok 4 on Replicate API

Implementation guide · Grok 4 · xAI

Serverless

Replicate API exposes Grok 4 through model ID grok-4. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-09. 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 grok-4 — see the documentation for request format.
  3. 3
    You'll be billed $7.20/1M input, $36.00/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

Install
pip install replicate
API key
REPLICATE_API_TOKEN
Model ID
grok-4

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
# grok-4 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "grok-4",
    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$7.20
Output tokens$36.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt Caching

About Grok 4

Original Grok 4 API model (grok-4-0709) with 256K context, reasoning, text and image input, function calling, structured outputs, live browsing, and code execution support. xAI lists May 15, 2026 as the API retirement date for this model; new integrations should use Grok 4.3.

Full model details →

Model Specs

Released2025-07-09
Context256k
ArchitectureDecoder Only

Also available on(3)

xAI Console$1.25/1MOpenRouter$3.00/1MMicrosoft Foundry
Compare all providers →

Provider

Replicate API

Replicate

San Francisco, California, United States