---
title: Inkling 2 Mini API – Pricing & Playground | ModelsLab
description: Inkling 2 Mini API by Thinking Machines, 1M context. $0.09375/1M input, $0.375/1M output tokens. API & playground on ModelsLab.
url: https://modelslab.com/models/thinkingmachines/thinkingmachines-inkling-2-mini.md
canonical: https://modelslab.com/models/thinkingmachines/thinkingmachines-inkling-2-mini
type: product
component: Playground/LLM/Index
generated_at: 2026-11-22T22:24:59.657969Z
---

Thinking Machines: Inkling 2 Mini
---

 [LLMs.txt](https://modelslab.com/models/thinkingmachines/thinkingmachines-inkling-2-mini/llms.txt) [.md](https://modelslab.com/models/thinkingmachines/thinkingmachines-inkling-2-mini.md)

Thinking Machines: Inkling 2 Mini
---

Choose a prompt below to get started or type your own message

 Explain quantum computing in simple terms

 Write a Python function to sort a list

 Create a marketing email for a SaaS product

 Compare REST vs GraphQL APIs

images and text files

Send

### Thinking Machines: Inkling 2 Mini

thinkingmachines thinkingmachines-inkling-2-mini

Copy model ID

PricingInput $0.09375 / 1M tokens

Output $0.375 / 1M tokens

API EndpointsOpenAI Compatible

`https://modelslab.com/api/v7/llm/chat/completions`Endpoint

Anthropic Compatible

`https://modelslab.com/api/v7/llm/v1/messages`Messages

`https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens

`https://modelslab.com/api/v7/llm/v1/models`Models

Use with Claude Code

cURL Example

ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses.

Temperature0.7

Max Tokens4000

Top P0.9

Frequency Penalty0

Presence Penalty0

Thinkinglow

lowmediumhigh

Deeper thinking spends more of the Max Tokens budget before the answer starts.

Model Info

Support

Looking for something different?
---

Models that trade off differently against the one you are viewing

### Better quality

Newer flagship models that generally produce stronger results.

![GPT 5.1 API](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/fad83520-47a8-4059-b4b9-b32adf4d0be7.png)

[OpenAI](/models/openai)

 [GPT 5.1](/models/openai/gpt5.1)

![GPT-5.1-Codex-Max API](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/06356c4c-df09-4ccb-a5c0-629da670f75b.png)

[OpenAI](/models/openai)

 [GPT-5.1-Codex-Max](/models/openai/gpt-5.1-codex-max)

### Lower cost per run

Open-source models we host, unlimited on the $149/month plan.

![gpt-oss-20b API](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/8b2f0440-52cc-4f41-93eb-d31006ad71e2.webp)

[OpenAI](/models/openai)

 [gpt-oss-20b](/models/openai/openai-gpt-oss-20b)

![DeepSeek: DeepSeek V4 Flash 0423 API](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/267a7228-f392-4d3e-abb6-915fef640c49.png)

[DeepSeek](/models/open_router)

 [DeepSeek: DeepSeek V4 Flash 0423](/models/deepseek/deepseek-deepseek-v4-flash)

![Qwen3.5 9B FP8 API](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/475e7d51-3e69-4cbc-adb0-64e01535ac29.png)

[Qwen](/models/open_router)

 [Qwen3.5 9B FP8](/models/qwen/qwen-qwen3.5-9b)

![Qwen3 30B A3b API](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/e893c08b-9506-4b2e-a5e9-f0f2b3def135.png)

[Qwen](/models/open_router)

 [Qwen3 30B A3b](/models/qwen/qwen-qwen3-30b-a3b)

[Meta](/models/open_router)

 [Meta: Llama Guard 4 12B](/models/meta/meta-llama-llama-guard-4-12b)

![Gemma 3N E4B Instruct API](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/b5ad4a07-e4eb-4d39-85d1-58ec000a8a4f.png)

[Google](/models?feature=llmaster&provider=google)

 [Gemma 3N E4B Instruct](/models/google/google-gemma-3n-e4b-it)

Related Models
---

Discover similar models you might be interested in

 [View all LLM Models](https://modelslab.com/models?feature=llmaster)

[#### DeepSeek/DeepSeek: DeepSeek V3.1 Terminus

deepseek-deepseek-v3.1-terminus

From $0.79375/M tokens](/models/deepseek/deepseek-deepseek-v3.1-terminus)

[#### Ricursiveai/Ricursive: Ripple 65B Preview

ricursiveai-ripple-65b-preview

From $0.25/M tokens](/models/ricursiveai/ricursiveai-ripple-65b-preview)

[#### Qwen/Qwen: Qwen3 Coder 480B A35B

qwen-qwen3-coder

From $0.8125/M tokens](/models/qwen/qwen-qwen3-coder)

[#### OpenAI/OpenAI: GPT-4o (2024-05-13)

openai-gpt-4o-2024-05-13

From $12.50/M tokens](/models/openai/openai-gpt-4o-2024-05-13)

[#### Unbiased/Pareto 26.9

unbiased-pareto-26.9

From $6.25/M tokens](/models/unbiased/unbiased-pareto-26.9)

[#### Qwen/Qwen: Qwen3.8 Flash

qwen-qwen3.8-flash

From $0.3875/M tokens](/models/qwen/qwen-qwen3.8-flash)

[#### Amazon/Amazon: Nova 2 Lite

amazon-nova-2-lite-v1

From $1.75/M tokens](/models/amazon/amazon-nova-2-lite-v1)

[#### Google/Gemma-2 Instruct (27B)

google-gemma-2-27b-it

From $0.8125/M tokens](/models/google/google-gemma-2-27b-it)

[#### Google/Google: Gemini 4 Neon

google-gemini-4-neon

From $11.25/M tokens](/models/google/google-gemini-4-neon)

[#### Reflection/Reflection: Beam 1.0 501B A23B

reflection-beam-1.0-501b-a23b

From $0.78125/M tokens](/models/reflection/reflection-beam-1.0-501b-a23b)

[#### Google/Google: Gemini 2.5 Flash

google-gemini-2.5-flash

From $1.75/M tokens](/models/google/google-gemini-2.5-flash)

[#### Qwen/Qwen: Qwen3.6 35B A3B

qwen-qwen3.6-35b-a3b

From $0.625/M tokens](/models/qwen/qwen-qwen3.6-35b-a3b)

[#### Meta/Meta: Muse Wonder

meta-muse-wonder

From $15.00/M tokens](/models/meta/meta-muse-wonder)

[#### Google/Google: Gemini Pro Latest

google-gemini-pro-latest

From $7.50/M tokens](/models/google/google-gemini-pro-latest)

[#### Writer/Writer: Palmyra X5

writer-palmyra-x5

From $4.125/M tokens](/models/writer/writer-palmyra-x5)

[#### Mistral AI/Mistral: Ministral 3 14B 2512

mistralai-ministral-14b-2512

From $0.25/M tokens](/models/mistralai/mistralai-ministral-14b-2512)

[#### Meta/Meta: Llama 3.1 70B Instruct

meta-llama-llama-3.1-70b-instruct

From $0.90/M tokens](/models/meta/meta-llama-llama-3.1-70b-instruct)

[#### Z.ai/Z.ai: GLM 5.2

z-ai-glm-5.2

From $1.90/M tokens](/models/z-ai/z-ai-glm-5.2)

About Thinking Machines: Inkling 2 Mini
---

Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared...

### Thinking Machines: Inkling 2 Mini facts

ProviderThinking Machines

Input price$0.09375 per 1M tokens

Output price$0.375 per 1M tokens

Context length1,048,576 tokens

Max output65,536 tokens

Input / outputtext, image → text

Added to ModelsLabNovember 21, 2026

Model IDthinkingmachines-inkling-2-mini

### Key Features

- Chat completion and multi-turn conversation API
- Streaming response with token-by-token output
- Function calling and tool use support
- System prompts and role-based messaging
- JSON mode and structured output

### Quick Start

Integrate Thinking Machines: Inkling 2 Mini into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started.

PythonJavaScriptcURLPHP

```
<div>import requests</div>
<div>import json</div>
<div>
</div>
<div>url = "https://modelslab.com/api/v7/llm/chat/completions"</div>
<div>
</div>
<div>headers = {</div>
<div>    "Content-Type": "application/json"</div>
<div>}</div>
<div>
</div>
<div>data = {</div>
<div>        "model_id": "thinkingmachines-inkling-2-mini",</div>
<div>        "messages": [</div>
<div>            {</div>
<div>                "role": "user",</div>
<div>                "content": "Hello!"</div>
<div>            }</div>
<div>        ],</div>
<div>        "max_tokens": 1000,</div>
<div>        "key": "YOUR_API_KEY"</div>
<div>    }</div>
<div>
</div>
<div>try:</div>
<div>    response = requests.post(url, headers=headers, json=data)</div>
<div>    response.raise_for_status()  # Raises an HTTPError for bad responses (4XX or 5XX)</div>
<div>    result = response.json()</div>
<div>    print("API Response:")</div>
<div>    print(json.dumps(result, indent=2))</div>
<div>except requests.exceptions.HTTPError as http_err:</div>
<div>    print(f"HTTP error occurred: {http_err} - {response.text}")</div>
<div>except Exception as err:</div>
<div>    print(f"Other error occurred: {err}")</div>
```

const requestBody = {

 "model_id": "thinkingmachines-inkling-2-mini",

 "messages": [

 {

 "role": "user",

 "content": "Hello!"

 }

 ],

 "max_tokens": 1000,

 "key": "YOUR_API_KEY"

 };

async function makeApiRequest() {

 try {

 const response = await fetch(endpointUrl, {

 method: 'POST',

 headers: {

 'Content-Type': 'application/json',

 },

 body: JSON.stringify(requestBody)

 });

 if (!response.ok) {

 let errorResult;

 try {

 errorResult = await response.json();

 } catch (e) {

 errorResult = { error: { message: await response.text() } };

 }

 throw new Error(`API Error (${response.status}): ${errorResult.error?.message || response.statusText || 'Unknown error'}`);

 }

 const result = await response.json();

 console.log('API Response:', result);

 return result;

 } catch (error) {

 console.error('Error making API request:', error.message);

 throw error;

 }

}

makeApiRequest();

 -H "Content-Type: application/json" \

 -d '{

 "model_id": "thinkingmachines-inkling-2-mini",

 "messages": [

 {

 "role": "user",

 "content": "Hello!"

 }

 ],

 "max_tokens": 1000,

 "key": "YOUR_API_KEY"

}'

$url = 'https://modelslab.com/api/v7/llm/chat/completions';

$headers = [

 'Content-Type: application/json'

];

$data = [

 'model_id' => 'thinkingmachines-inkling-2-mini',

 'messages' => [{"role":"user","content":"Hello!"}],

 'max_tokens' => 1000,

 'key' => 'YOUR_API_KEY',

];

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);

curl_setopt($ch, CURLOPT_POST, true);

curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));

curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

curl_setopt($ch, CURLOPT_TIMEOUT, 30);

$response = curl_exec($ch);

$httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);

$curlError = curl_error($ch);

if ($curlError) {

 echo 'Curl error: ' . $curlError;

} else {

 echo "HTTP Status Code: " . $httpCode . "\n";

 $result = json_decode($response, true);

 if (json_last_error() !== JSON_ERROR_NONE) {

 echo "Error decoding JSON: " . json_last_error_msg() . "\n";

 echo "Raw response: " . $response . "\n";

 } else {

 echo "API Response:\n";

 print_r($result);

 }

}

?>

### Pricing

Thinking Machines: Inkling 2 Mini API costs $0.188 per million tokens. Plans start at $21/month, and open-source models are unlimited on the $149/month plan. [View pricing plans](https://modelslab.com/pricing)

### Use Cases

- AI chatbots and virtual assistants
- Code generation and developer tools
- Content writing and copywriting automation
- Data analysis, summarization, and extraction

### More from Thinking Machines

- [Thinking Machines: Inkling API](/models/thinkingmachines/thinkingmachines-inkling)
- [Thinking Machines: Inkling Small API](/models/thinkingmachines/thinkingmachines-inkling-small)
- [Thinking Machines: Inkling 2 Small API](/models/thinkingmachines/thinkingmachines-inkling-2-small)

[All Thinking Machines models](/models?feature=llmaster&provider=thinkingmachines)

[Browse LLM Models](https://modelslab.com/models?feature=llmaster) [View Pricing](https://modelslab.com/pricing)

Thinking Machines: Inkling 2 Mini FAQ
---

### What is Thinking Machines: Inkling 2 Mini?

Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared...

### How do I use the Thinking Machines: Inkling 2 Mini API?

You can integrate Thinking Machines: Inkling 2 Mini into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "thinkingmachines-inkling-2-mini" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation.

### How much does Thinking Machines: Inkling 2 Mini cost?

Thinking Machines: Inkling 2 Mini costs $0.09375/1M input, $0.375/1M output tokens. ModelsLab plans start at $21/month (Basic), and the $149/month Open Source plan includes unlimited generation on open-source models.

### What is the Thinking Machines: Inkling 2 Mini model ID?

The model ID for Thinking Machines: Inkling 2 Mini is "thinkingmachines-inkling-2-mini". Use this ID in your API requests to specify this model.

### Do I need a paid plan to use Thinking Machines: Inkling 2 Mini?

Yes. ModelsLab is subscription-based with no free tier — plans start at $21/month (Basic, 3,250 API calls). The $149/month Open Source Unlimited plan includes unlimited generation across open-source models; premium third-party models are billed per call from your wallet.

---

*This markdown version is optimized for AI agents and LLMs.*

**Links:**
- [Website](https://modelslab.com)
- [API Documentation](https://docs.modelslab.com)
- [Blog](https://modelslab.com/blog)

---
*Generated by ModelsLab - 2026-11-23*