Overview

Provider Type

Trial Credits

API Endpoint


                                                        https://api.replicate.com/v1

Free Tier Highlights

Varies by model

Quick Start Guide

1

Sign up at https://replicate.com/

2

Link GitHub account

3

Add payment method (or use trial)

4

Get API Token

5

Use Python/JS SDK

Available Models

Model Name	ID	Context	Capabilities
meta/llama-3-70b-instruct	`meta/llama-3-70b-instruct`	8 000 tokens	-
stability-ai/sdxl	`stability-ai/sdxl`	Image	-
mistralai/mistral-7b-instruct-v0.2	`mistralai/mistral-7b-instruct-v0.2`	32 000 tokens	-

Integration Examples

Ready-to-use code snippets for your applications.

Select a Model

Select Model

main.py

import replicate

# pip install replicate
# export REPLICATE_API_TOKEN=YOUR_TOKEN

output = replicate.run(
    "meta/llama-3-70b-instruct",
    input={
        "prompt": "Write a short poem about AI",
        "max_tokens": 512
    }
)

print("".join(output))

index.js

import Replicate from 'replicate';

const replicate = new Replicate({
  auth: 'YOUR_REPLICATE_TOKEN'
});

const output = await replicate.run(
  'meta/llama-3-70b-instruct',
  {
    input: {
      prompt: 'Write a short poem about AI',
      max_tokens: 512
    }
  }
);

console.log(output.join(''));

terminal

curl -s -X POST https://api.replicate.com/v1/predictions \
  -H "Authorization: Bearer YOUR_REPLICATE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "version": "MODEL_VERSION_ID",
    "input": {
      "prompt": "Write a short poem about AI",
      "max_tokens": 512
    }
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.replicate.com/v1/models/meta/llama-3-70b-instruct:generateContent?key=$apiKey";

$data = [
    "contents" => [
        ["parts" => [["text" => "Explain quantum mechanics"]]]
    ]
];

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/json']);

$response = curl_exec($ch);
curl_close($ch);

echo $response;
?>

main.go

package main

import (
    "context"
    "fmt"
    "log"
    "github.com/google/generative-ai-go/genai"
    "google.golang.org/api/option"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, option.WithAPIKey("YOUR_API_KEY"))
    if err != nil { log.Fatal(err) }
    defer client.Close()

    model := client.GenerativeModel("meta/llama-3-70b-instruct")
    resp, err := model.GenerateContent(ctx, genai.Text("Explain quantum mechanics"))
    if err != nil { log.Fatal(err) }
    
    // ...
}

main.py

import replicate

# pip install replicate
# export REPLICATE_API_TOKEN=YOUR_TOKEN

output = replicate.run(
    "meta/llama-3-70b-instruct",
    input={
        "prompt": "Write a short poem about AI",
        "max_tokens": 512
    }
)

print("".join(output))

index.js

import Replicate from 'replicate';

const replicate = new Replicate({
  auth: 'YOUR_REPLICATE_TOKEN'
});

const output = await replicate.run(
  'meta/llama-3-70b-instruct',
  {
    input: {
      prompt: 'Write a short poem about AI',
      max_tokens: 512
    }
  }
);

console.log(output.join(''));

terminal

curl -s -X POST https://api.replicate.com/v1/predictions \
  -H "Authorization: Bearer YOUR_REPLICATE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "version": "MODEL_VERSION_ID",
    "input": {
      "prompt": "Write a short poem about AI",
      "max_tokens": 512
    }
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.replicate.com/v1/models/stability-ai/sdxl:generateContent?key=$apiKey";

$data = [
    "contents" => [
        ["parts" => [["text" => "Explain quantum mechanics"]]]
    ]
];

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/json']);

$response = curl_exec($ch);
curl_close($ch);

echo $response;
?>

main.go

package main

import (
    "context"
    "fmt"
    "log"
    "github.com/google/generative-ai-go/genai"
    "google.golang.org/api/option"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, option.WithAPIKey("YOUR_API_KEY"))
    if err != nil { log.Fatal(err) }
    defer client.Close()

    model := client.GenerativeModel("stability-ai/sdxl")
    resp, err := model.GenerateContent(ctx, genai.Text("Explain quantum mechanics"))
    if err != nil { log.Fatal(err) }
    
    // ...
}

main.py

import replicate

# pip install replicate
# export REPLICATE_API_TOKEN=YOUR_TOKEN

output = replicate.run(
    "meta/llama-3-70b-instruct",
    input={
        "prompt": "Write a short poem about AI",
        "max_tokens": 512
    }
)

print("".join(output))

index.js

import Replicate from 'replicate';

const replicate = new Replicate({
  auth: 'YOUR_REPLICATE_TOKEN'
});

const output = await replicate.run(
  'meta/llama-3-70b-instruct',
  {
    input: {
      prompt: 'Write a short poem about AI',
      max_tokens: 512
    }
  }
);

console.log(output.join(''));

terminal

curl -s -X POST https://api.replicate.com/v1/predictions \
  -H "Authorization: Bearer YOUR_REPLICATE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "version": "MODEL_VERSION_ID",
    "input": {
      "prompt": "Write a short poem about AI",
      "max_tokens": 512
    }
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.replicate.com/v1/models/mistralai/mistral-7b-instruct-v0.2:generateContent?key=$apiKey";

$data = [
    "contents" => [
        ["parts" => [["text" => "Explain quantum mechanics"]]]
    ]
];

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/json']);

$response = curl_exec($ch);
curl_close($ch);

echo $response;
?>

main.go

package main

import (
    "context"
    "fmt"
    "log"
    "github.com/google/generative-ai-go/genai"
    "google.golang.org/api/option"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, option.WithAPIKey("YOUR_API_KEY"))
    if err != nil { log.Fatal(err) }
    defer client.Close()

    model := client.GenerativeModel("mistralai/mistral-7b-instruct-v0.2")
    resp, err := model.GenerateContent(ctx, genai.Text("Explain quantum mechanics"))
    if err != nil { log.Fatal(err) }
    
    // ...
}

Free Tier Pricing & Limits

Rate Limit

Requests per minute

Varies by model

Daily Quota

Requests per day

Credit-based

Token Limit

Tokens per minute

Pay-per-prediction

Monthly Quota

Per month limit

One-time trial

Free Credits

One-time

Small trial credit

Use Cases

Image Generation Workflows

Running specific niche models

Prototyping with new research papers

Scalable backend for ML apps

Limitations & Considerations

Pay-per-second billing (can be expensive)

Cold starts for less popular models

Trial credits are minimal

Requires credit card for sustained use

Community Hub

Live

Join the discussion, share tips, and rate Replicate.

Quick Reactions

Add Discussion

Display Name

Comment

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Cookie Consent

Replicate

Overview

Provider Type

API Endpoint

Free Tier Highlights

Why Choose Replicate?

Quick Start Guide

Sign up at https://replicate.com/

Link GitHub account

Add payment method (or use trial)

Get API Token

Use Python/JS SDK

Available Models

Integration Examples

Select Model

Free Tier Pricing & Limits

Rate Limit

Daily Quota

Token Limit

Monthly Quota

Free Credits

Use Cases

Limitations & Considerations

Community Hub

Quick Reactions

Add Discussion

Recent Activity

Ready to Get Started?

Cookie Consent

Replicate

Overview

Provider Type

API Endpoint

Free Tier Highlights

Why Choose Replicate?

Quick Start Guide

Sign up at https://replicate.com/

Link GitHub account

Add payment method (or use trial)

Get API Token

Use Python/JS SDK

Available Models

Integration Examples

Select Model

Free Tier Pricing & Limits

Rate Limit

Daily Quota

Token Limit

Monthly Quota

Free Credits

Use Cases

Limitations & Considerations

Community Hub

Quick Reactions

Add Discussion

Recent Activity

Suggest an Edit

Ready to Get Started?