API Documentation

An OpenAI-compatible chat completion LLM API to easily integrate AI into your applications.

➡️ Get your API key and credits

Quick Start

Buy API credits individually from the API settings.
Mammouth subscribers get monthly credits included (Starter $2, Standard $4, Expert $10).
You can use the API without a subscription by buying credits directly.

💡 For intensive usage (Mammouth Code, Cline), choose Starter + around $50 in API credits rather than Expert.

➡️ Get your API key and credits.

With the Mammouth API directly

Generates a chat completion response based on your prompt.

PythonJavaScriptcURL

python

import requests
url = "https://api.mammouth.ai/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "gpt-4.1",
    "messages": [
        {
            "role": "user",
            "content": "Explain the basics of machine learning"
        }
    ]
}
response = requests.post(url, headers=headers, json=data)
print(response.json())

javascript

const fetch = require("node-fetch");

async function callMammouth() {
  const url = "https://api.mammouth.ai/v1/chat/completions";
  const headers = {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  };

  const data = {
    model: "gpt-4.1",
    messages: [
      {
        role: "user",
        content: "Create an example JavaScript function",
      },
    ],
  };

  try {
    const response = await fetch(url, {
      method: "POST",
      headers: headers,
      body: JSON.stringify(data),
    });

    const result = await response.json();
    console.log(result.choices[0].message.content);
  } catch (error) {
    console.error("Error:", error);
  }
}

callMammouth();

bash

curl -X POST https://api.mammouth.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you doing?"
      }
    ]
  }'

➡️ Get your API key and credits.

With OpenAI Library

python

import openai

# Configure the client to use Mammouth.ai
openai.api_base = "https://api.mammouth.ai/v1"
openai.api_key = "YOUR_API_KEY"

response = openai.ChatCompletion.create(
    model="gpt-4.1",
    messages=[
        {"role": "user", "content": "What are the benefits of renewable energy?"}
    ]
)

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

Response Format

Successful Response

TextImage

json

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing very well, thank you for asking. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 19,
    "total_tokens": 31
  }
}

Streaming Response

When stream: true is set, responses are returned as Server-Sent Events:

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: [DONE]

json

{
  "id": "gen-1767710235-3VtWd1SuI9ilIspBmeWG",
  "created": 1767710235,
  "model": "google/gemini-2.5-flash-image",
  "object": "chat.completion",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Here's a beautiful sunset over mountains for you!",
        "role": "assistant",
        "images": [
          {
            "image_url": {
              "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAI..."
            }
          }
        ]
      }
    }
  ]
}

Models & Pricing

Mammouth Recommended

mammouth-recommended is a shortcut to whatever model Mammouth currently considers the best for its price.

Point your requests at it and you'll always get our current pick, without having to keep track of new releases yourself.

Current pick: glm-5.3-flash, with minimax-m3 as the fallback. This will change over time as new models come out.
How to use it: call it exactly like any other model. Set the model to mammouth-recommended, or use the shortcuts mammouth or recommended.
Pricing: you pay the same as the underlying model, with no markup, so check that model's row in the table below.

All models

Prices may vary and not be up to date in this table, please refer to the Model Explorer for the complete list of models !

Model	Input ($/M tokens)	Output ($/M tokens)
`claude-fable-5.1`	10	50
`claude-haiku-4-5`	1	5
`claude-opus-5-5`	4	20
`claude-sonnet-5`	2	10
`deepseek-v4-pro`	1.74	3.48
`deepseek-v4.1-flash`	0.22	0.66
`gemini-3.1-flash-image-preview`	image	/
`gemini-3.1-pro-preview`	2	12
`gemini-3.7-flash`	1.5	7.5
`gemini-3.8-flash`	0.75	3.75
`glm-5.3`	1.4	4.4
`glm-5.3-flash`	0.15	0.5
`gpt-5.4`	2.5	15
`gpt-5.4-mini`	0.75	4.5
`gpt-5.4-nano`	0.2	1.25
`gpt-5.5`	5	30
`gpt-6-astra`	10	50
`gpt-6-luna`	0.1	0.5
`gpt-6-sol`	2	10
`grok-4.7`	2	6
`kimi-k2.6`	0.73	3.49
`kimi-k3`	3	15
`llama-4-maverick`	0.15	0.6
`minimax-m3`	0.3	1.2
`mistral-medium-3-5`	1.5	7.5
`mistral-small-3.2-24b-instruct`	0.1	0.3
`qwen3.7-plus`	0.4	1.6
`qwen3.8-27b`	0.4	2.55
`qwen3.8-flash`	0.15	0.47
`sonar-deep-research`	2	8
`sonar-pro`	3	15

A note on pricing

The prices listed here are upper bounds.

What you actually pay is sometimes lower, since the price depends on provider availability.

You'll never be charged more than the price shown.

Embeddings

Generate vector embeddings for text to use in semantic search, clustering, and other NLP tasks.

Embedding Models & Pricing

Model	Input ($/M tokens)
`text-embedding-3-large`	0.13
`text-embedding-3-small`	0.02

Embedding Example

python

import requests

url = "https://api.mammouth.ai/v1/embeddings"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "text-embedding-3-large",
    "input": "Hello, world!"
}
response = requests.post(url, headers=headers, json=data)
print(response.json())

Embedding Response

json

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0152, ...]
    }
  ],
  "model": "text-embedding-3-large",
  "usage": {
    "prompt_tokens": 4,
    "total_tokens": 4
  }
}

📜 Usage and cost are logged in your settings.

💡 We added aliases aligned with the Mammouth app to facilitate your model selection: if you write mistral, it will use mistral-medium-3.1.

Error Codes

Code	Description
`400`	Bad Request - Missing or incorrect parameters
`401`	Unauthorized - Invalid API key
`429`	Too Many Requests - Rate limit exceeded
`500`	Internal Server Error - Server-side issue
`503`	Service Unavailable - Server temporarily unavailable

Tracking cost

If you want to know how much credits has been spent on a key, use this API endpoint:

bash

curl -X GET "https://api.mammouth.ai/key/info" -H "Authorization: Bearer $MAMMOUTH_API_KEY"

Parameters

Required Parameters

Parameter	Type	Description
`messages`	array	List of messages in the conversation
`model`	string	Model identifier to use

Optional Parameters

Parameter	Type	Default	Description
`temperature`	number	0.7	Controls creativity (0.0 to 2.0)
`max_tokens`	integer	2048	Maximum number of tokens to generate
`top_p`	number	1.0	Controls response diversity
`stream`	boolean	false	Real-time response streaming

Our API also supports provider-specific parameters and features, such as reasoning effort, tool calling, function calling, and thinking. Availability depends on the provider and model.

Optimization Tips

Message Structure

json

{
  "messages": [
    {
      "role": "system",
      "content": "You are an AI assistant specialized in programming."
    },
    {
      "role": "user",
      "content": "How to optimize a for loop in Python?"
    }
  ]
}

Role Types

system: Sets the behavior and context for the assistant
user: Represents messages from the user
assistant: Represents previous responses from the AI

Migration from OpenAI

If you're already using OpenAI's API, migrating to Mammouth.ai is simple:

Change the base URL from https://api.openai.com/v1 to https://api.mammouth.ai/v1
Update your API key
Keep all other parameters the same

OpenAI Python Library

python

import openai

# Before
openai.api_base = "https://api.openai.com/v1"
openai.api_key = "sk-openai-key"

# After
openai.api_base = "https://api.mammouth.ai/v1"
openai.api_key = "your-mammouth-key"

n8n, VS Code, Cline, OpenClaw, Make, CLI, etc.

You can use the Mammouth API with tools like n8n, VS Code, Cline, Make and more.

Make sure you are using the correct URL. If unsure, try each of them.

For base URL, https://api.mammouth.ai/v1 or https://api.mammouth.ai/
For https queries, https://api.mammouth.ai/v1/chat/completions will be required.

Tutorials on how to use the Mammouth API in your favorite tools

For automations:

For IDEs:

For CLI (Claude Code equivalent):

Mammouth Code !

Or via Opencode

Other

GitKraken

➡️ Get your API key and credits.

API Documentation ​

Quick Start ​

With the Mammouth API directly ​

With OpenAI Library ​

Response Format ​

Successful Response ​

Streaming Response ​

Models & Pricing ​

Mammouth Recommended ​

All models ​

Embeddings ​

Embedding Models & Pricing ​

Embedding Example ​

Embedding Response ​

Error Codes ​

Tracking cost ​

Parameters ​

Required Parameters ​

Optional Parameters ​

Optimization Tips ​

Message Structure ​

Role Types ​

Migration from OpenAI ​

OpenAI Python Library ​

n8n, VS Code, Cline, OpenClaw, Make, CLI, etc. ​

Tutorials on how to use the Mammouth API in your favorite tools ​

​

API Documentation

Quick Start

With the Mammouth API directly

With OpenAI Library

Response Format

Successful Response

Streaming Response

Models & Pricing

Mammouth Recommended

All models

Embeddings

Embedding Models & Pricing

Embedding Example

Embedding Response

Error Codes

Tracking cost

Parameters

Required Parameters

Optional Parameters

Optimization Tips

Message Structure

Role Types

Migration from OpenAI

OpenAI Python Library

n8n, VS Code, Cline, OpenClaw, Make, CLI, etc.

Tutorials on how to use the Mammouth API in your favorite tools