Overview

Provider Type

API

API Endpoint


                                                        https://api.llm.kiwi/v1

Free Tier Highlights

Baseline rate limits (figures not published)

Quick Start Guide

1

Sign in at llm.kiwi/login with Google or GitHub

2

create an API key

3

set base URL https://api.llm.kiwi/v1 with model "auto"

Available Models

Model Name	ID	Context	Capabilities
Auto router Free	`auto`	-	-
MiniMax M3 Free	`minimax-m3`	-	-
Nemotron 3 Ultra Free	`nemotron-3-ultra`	-	-
Nemotron 3 Super Free	`nemotron-3-super`	-	-
MiniMax M2.5 Free	`minimax-m2.5`	-	-

Integration Examples

Ready-to-use code snippets for your applications.

Select a Model

Select Model

main.py

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLM_KIWI_KEY",
    base_url="https://api.llm.kiwi/v1"
)

response = client.chat.completions.create(
    model="auto",
    messages=[
        {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
)

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

index.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_LLM_KIWI_KEY',
  baseURL: 'https://api.llm.kiwi/v1'
});

const response = await client.chat.completions.create({
  model: 'auto',
  messages: [
    { role: 'user', content: 'Give me three tips for writing clean code.' }
  ]
});

console.log(response.choices[0].message.content);

terminal

curl https://api.llm.kiwi/v1/chat/completions \
  -H "Authorization: Bearer YOUR_LLM_KIWI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [
      {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.llm.kiwi/v1/models/auto:generateContent?key=$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("auto")
    resp, err := model.GenerateContent(ctx, genai.Text("Explain quantum mechanics"))
    if err != nil { log.Fatal(err) }
    
    // ...
}

main.py

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLM_KIWI_KEY",
    base_url="https://api.llm.kiwi/v1"
)

response = client.chat.completions.create(
    model="minimax-m3",
    messages=[
        {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
)

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

index.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_LLM_KIWI_KEY',
  baseURL: 'https://api.llm.kiwi/v1'
});

const response = await client.chat.completions.create({
  model: 'minimax-m3',
  messages: [
    { role: 'user', content: 'Give me three tips for writing clean code.' }
  ]
});

console.log(response.choices[0].message.content);

terminal

curl https://api.llm.kiwi/v1/chat/completions \
  -H "Authorization: Bearer YOUR_LLM_KIWI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3",
    "messages": [
      {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.llm.kiwi/v1/models/minimax-m3:generateContent?key=$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("minimax-m3")
    resp, err := model.GenerateContent(ctx, genai.Text("Explain quantum mechanics"))
    if err != nil { log.Fatal(err) }
    
    // ...
}

main.py

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLM_KIWI_KEY",
    base_url="https://api.llm.kiwi/v1"
)

response = client.chat.completions.create(
    model="nemotron-3-ultra",
    messages=[
        {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
)

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

index.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_LLM_KIWI_KEY',
  baseURL: 'https://api.llm.kiwi/v1'
});

const response = await client.chat.completions.create({
  model: 'nemotron-3-ultra',
  messages: [
    { role: 'user', content: 'Give me three tips for writing clean code.' }
  ]
});

console.log(response.choices[0].message.content);

terminal

curl https://api.llm.kiwi/v1/chat/completions \
  -H "Authorization: Bearer YOUR_LLM_KIWI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-ultra",
    "messages": [
      {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.llm.kiwi/v1/models/nemotron-3-ultra:generateContent?key=$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("nemotron-3-ultra")
    resp, err := model.GenerateContent(ctx, genai.Text("Explain quantum mechanics"))
    if err != nil { log.Fatal(err) }
    
    // ...
}

main.py

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLM_KIWI_KEY",
    base_url="https://api.llm.kiwi/v1"
)

response = client.chat.completions.create(
    model="nemotron-3-super",
    messages=[
        {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
)

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

index.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_LLM_KIWI_KEY',
  baseURL: 'https://api.llm.kiwi/v1'
});

const response = await client.chat.completions.create({
  model: 'nemotron-3-super',
  messages: [
    { role: 'user', content: 'Give me three tips for writing clean code.' }
  ]
});

console.log(response.choices[0].message.content);

terminal

curl https://api.llm.kiwi/v1/chat/completions \
  -H "Authorization: Bearer YOUR_LLM_KIWI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-super",
    "messages": [
      {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.llm.kiwi/v1/models/nemotron-3-super:generateContent?key=$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("nemotron-3-super")
    resp, err := model.GenerateContent(ctx, genai.Text("Explain quantum mechanics"))
    if err != nil { log.Fatal(err) }
    
    // ...
}

main.py

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLM_KIWI_KEY",
    base_url="https://api.llm.kiwi/v1"
)

response = client.chat.completions.create(
    model="minimax-m2.5",
    messages=[
        {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
)

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

index.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_LLM_KIWI_KEY',
  baseURL: 'https://api.llm.kiwi/v1'
});

const response = await client.chat.completions.create({
  model: 'minimax-m2.5',
  messages: [
    { role: 'user', content: 'Give me three tips for writing clean code.' }
  ]
});

console.log(response.choices[0].message.content);

terminal

curl https://api.llm.kiwi/v1/chat/completions \
  -H "Authorization: Bearer YOUR_LLM_KIWI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.5",
    "messages": [
      {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
  }'

example.php

<?php
$apiKey = 'YOUR_API_KEY';
$url = "https://api.llm.kiwi/v1/models/minimax-m2.5:generateContent?key=$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("minimax-m2.5")
    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

Baseline rate limits (figures not published)

Daily Quota

Requests per day

Not published

Use Cases

Prototyping with an auto-routed free model

trying a coding model at no cost

Limitations & Considerations

Numeric limits not published

small new operator with no company details on the site

Community Hub

Live

Join the discussion, share tips, and rate LLM.kiwi.

Quick Reactions

Add Discussion

Display Name

Email (optional, to get notified when reviewed)

Comment

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Cookie Consent

LLM.kiwi

Overview

Provider Type

API Endpoint

Free Tier Highlights

Why Choose LLM.kiwi?

Quick Start Guide

Sign in at llm.kiwi/login with Google or GitHub

create an API key

set base URL https://api.llm.kiwi/v1 with model "auto"

Available Models

Integration Examples

Select Model

Free Tier Pricing & Limits

Rate Limit

Daily Quota

Use Cases

Limitations & Considerations

Community Hub

Quick Reactions

Add Discussion

Recent Activity

Ready to Get Started?

Cookie Consent

LLM.kiwi

Overview

Provider Type

API Endpoint

Free Tier Highlights

Why Choose LLM.kiwi?

Quick Start Guide

Sign in at llm.kiwi/login with Google or GitHub

create an API key

set base URL https://api.llm.kiwi/v1 with model "auto"

Available Models

Integration Examples

Select Model

Free Tier Pricing & Limits

Rate Limit

Daily Quota

Use Cases

Limitations & Considerations

Community Hub

Quick Reactions

Add Discussion

Recent Activity

Suggest an Edit

Report an Issue

Ready to Get Started?