model_api_documentation_gitbook

Comprehensive API reference for all available AI models

Last Updated: 2026-01-19 Total Models: 107 (32 LLM + 75 Multimodal) Providers: 12 (Anthropic, DeepSeek, Google, Microsoft, MiniMax, Mistral AI, Nous Research, OpenAI, Qwen, Vidu, Vtrix, xAI)

---

Quick Start

Authentication Required

All API requests require authentication using a Bearer token in the Authorization header.

Headers

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Obtaining API Key

1

Sign Up

Sign up for an account at https://vtrix.ai

2

Navigate to Dashboard

Navigate to the API Keys section in your dashboard

3

Generate API Key

Generate a new API key

4

Secure Storage

Copy and securely store your API key

Base URLs

LLM Models

https://cloud.vtrix.ai/llm/chat/completions

Use this endpoint for all Language Learning Models (LLM) including Anthropic, DeepSeek, Google, Microsoft, Mistral AI, Nous Research, OpenAI, Qwen, and xAI models.

Multimodal Models

Important Notes

• Keep your API key secure and never share it publicly

• Rate limits apply to all endpoints

• Ensure sufficient account balance before making requests

---

API Reference

Anthropic

Claude Sonnet 4.5

Model ID: vtrix-claude-sonnet-4.5

Anthropic's most intelligent Sonnet model. Hybrid reasoning with fast and extended thinking modes. Excels at real-world coding, agents, and computer use with 200K context.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-claude-sonnet-4.5,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-claude-sonnet-4.5
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-64000	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-claude-sonnet-4.5,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Claude Opus 4.5

Model ID: vtrix-claude-opus-4.5

Anthropic's most capable model for complex software engineering and agentic workflows. 80.9% on SWE-bench Verified. Optimized for long-horizon computer use tasks.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-claude-opus-4.5,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-claude-opus-4.5
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-64000	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-claude-opus-4.5,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Claude 3.5 Haiku

Model ID: vtrix-claude-3.5-haiku

Fast and capable model surpassing Claude 3 Opus on most benchmarks. 40.6% on SWE-bench Verified. Best value for coding assistance and quick tasks.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-claude-3.5-haiku,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-claude-3.5-haiku
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-8192	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-claude-3.5-haiku,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Claude Haiku 4.5

Model ID: vtrix-claude-haiku-4.5

Anthropic's most efficient model matching Claude Sonnet 4 performance. >73% on SWE-bench Verified. Optimized for high-throughput coding and computer use tasks.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-claude-haiku-4.5,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-claude-haiku-4.5
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-64000	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-claude-haiku-4.5,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Claude Sonnet 4

Model ID: vtrix-claude-sonnet-4

Major upgrade to Sonnet 3.7 with 72.7% on SWE-bench Verified. Ideal balance of capability and efficiency for everyday coding and business tasks.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-claude-sonnet-4,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-claude-sonnet-4
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-64000	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-claude-sonnet-4,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Claude 3 Haiku

Model ID: vtrix-claude-3-haiku

Anthropic's fastest model for near-instant responses. Ideal for lightweight tasks, customer service, and content moderation at the lowest cost in the Claude family.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-claude-3-haiku,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-claude-3-haiku
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-4096	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-claude-3-haiku,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

DeepSeek

DeepSeek V3

Model ID: vtrix-deepseek-v3-0324

671B parameter MoE model with 37B active parameters. Supports thinking and non-thinking modes with FP8 training. Strong reasoning, coding, and Chinese language capabilities at extremely low cost.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-deepseek-v3-0324,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-deepseek-v3-0324
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-16384	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-deepseek-v3-0324,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

DeepSeek V3.1

Model ID: vtrix-deepseek-v3.1

Enhanced V3 with improved tool use and code generation. Two-phase long-context training for better coherence. Best-in-class efficiency at 671B/37B architecture.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-deepseek-v3.1,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-deepseek-v3.1
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-16384	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-deepseek-v3.1,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

DeepSeek R1

Model ID: vtrix-deepseek-r1

Open-source reasoning model matching OpenAI o1. 671B/37B MoE with MIT license. Transparent reasoning tokens for explainable AI applications.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-deepseek-r1,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-deepseek-r1
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-32768	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-deepseek-r1,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Google

Gemini 2.5 Flash

Model ID: vtrix-gemini-2.5-flash

Google's workhorse model with hybrid reasoning. Excels at coding, math, science with configurable thinking depth. 1M context, native tool use, and multimodal capabilities at an affordable price point.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-gemini-2.5-flash,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-gemini-2.5-flash
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-65535	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-gemini-2.5-flash,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Gemini 2.5 Pro

Model ID: vtrix-gemini-2.5-pro

Google's state-of-the-art reasoning model. #1 on LMArena leaderboard. Excels at coding, math, and science with 1M context and native multimodal understanding.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-gemini-2.5-pro,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-gemini-2.5-pro
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-65536	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-gemini-2.5-pro,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Gemini 3 Pro Preview

Model ID: vtrix-gemini-3-pro-preview

Google's frontier model for high-precision multimodal reasoning. Supports text, image, video, and audio inputs with 1M context. State-of-the-art on complex reasoning benchmarks.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-gemini-3-pro-preview,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-gemini-3-pro-preview
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-65536	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-gemini-3-pro-preview,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Gemini 2.0 Flash

Model ID: vtrix-gemini-2.0-flash

Google's fast multimodal model with native audio understanding. Significantly faster TTFT than Flash 1.5. Ideal for real-time applications and streaming.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-gemini-2.0-flash,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-gemini-2.0-flash
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-8192	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-gemini-2.0-flash,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

Microsoft

WizardLM-2 8x22B

Model ID: vtrix-wizardlm-2-8x22b

Microsoft's most advanced Wizard model based on Mixtral 8x22B. Strong performance on reasoning and instruction-following benchmarks.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-wizardlm-2-8x22b,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-wizardlm-2-8x22b
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-8192	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-wizardlm-2-8x22b,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

MiniMax

Hailuo 23 Image to Video

Model ID: minimax_hailuo_23_i2v

Hailuo 2.3 I2V generates high-quality animated videos from images with enhanced resolution and motion quality.

Authentication

POST https://cloud.vtrix.ai/model/v1/generation
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/model/v1/generation' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
  "model": "minimax_hailuo_23_i2v",
  "input": [
    {
      "params": {
        "first_frame_image": "example_first_frame_image",
        "prompt": "example_prompt",
        "duration": 6,
        "resolution": "768P",
        "prompt_optimizer": true,
        "fast_pretreatment": false
      }
    }
  ]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Description
model	string	✅	Model ID: minimax_hailuo_23_i2v
first_frame_image	string	✅	Input Image URL or Base64 Encoded (data:image/jpeg;base 64,xxx Format)
prompt	string	❌	Video generation prompt. Supports camera motion: [Pan left], [Zoom in], etc. Max 2000 characters.
duration	integer	❌	Video Duration (Seconds), Default 6 Seconds
resolution	string	❌	Video Resolution, Defaultas 768 P
prompt_optimizer	boolean	❌	Whether to Enable Promptoptimize, Defaultastrue

Response Format

{
  "type": "video",
  "url": "Generated content URL",
  "jobId": "Job identifier"
}

Error Codes Reference

Error Codes

Error Code	Description
401	API key is missing or invalid
403	Insufficient balance or permission denied
429	Rate limit exceeded
500	Internal server error

---

(Documentation continues for many models and their parameters, code examples, response formats, and error codes. Each model section follows the same structure: Model Name, Model ID, brief description, Authentication block, Code Examples (tabs), Parameters Reference (expandable), Response Format, and Error Codes (expandable).)

---

Mistral AI

(See above pattern for model sections: Mistral Small 3.2 24B, Mistral Nemo, Mistral Small 3.1 24B, Devstral 2512, Devstral 2512 (Free).)

---

Nous Research

(See Hermes 3 405B Instruct, Hermes 4 405B, Hermes 4 70B sections.)

---

OpenAI

(See GPT-4o, GPT-4.1, GPT-4o Mini, GPT-5, GPT-4.1 Mini, OpenAI o1, o3, GPT-4.1 Nano, Sora 2, and others. Each entry includes Authentication, Code Examples, Parameters, Response Format, and Error Codes.)

---

Qwen

(See Qwen3 235B A22B Instruct 2507 section.)

---

Vidu

(See Vidu model sections: Vidu Q2 Pro Start End, Vidu Q2 Turbo Start End, Vidu Q2, Vidu Q1 I2V, Vidu Q1, and many more. Each follows the same structured format.)

---

Vtrix

(See Vtrix model sections: Ultra Video Extend, Ultra Lipsync, Vtrix Edit Transform, Ultra I2V Master, Vtrix Multi Ip, Ultra Video Turbo, Vtrix Image 4.5 Blend, Vtrix Edit IP, Vtrix Edit Base, Vtrix Edit Portrait, Ultra I2V Pro, Ultra Video Pro, Vtrix Motion 1.5 Pro, Vtrix Motion Pro, Vtrix Motion Base, Film Avatar Motion, Film Avatar Omni, Ultra Image Omni, Film Actor, Ultra Video Omni, Ultra I2V Turbo, Ultra I2V 1.5, Ultra Video 1.5, Vtrix Image 4.5, Ultra Video Master 2.1, Vtrix Image 4.0, Vtrix Motion Turbo, Ultra Video Plus, Ultra I2V 1.6, Vtrix Motion I2V, Ultra I2V Master 2.1, Ultra I2V 2.1, Ultra Video Master, Vtrix Image 3.0, Vtrix Edit Style, Vtrix Edit 3D, Vtrix 3D, Vtrix Edit I2I, Ultra Effects Multi 1.6, Film Image Pro, Film Image Base, Ultra Effects Multi 1.5, Ultra Effects Multi 1.0, Ultra Effects Solo, Ultra I2V Base, Film I2I, Ultra Video Base.)

---

xAI

Grok 4

Model ID: vtrix-grok-4

xAI's flagship reasoning model with mandatory thinking mode. 256K context, parallel tool calling, and real-time web search integration. Excels at technical reasoning.

Authentication

POST https://cloud.vtrix.ai/llm/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Code Examples

cURL

curl --location 'https://cloud.vtrix.ai/llm/chat/completions' \\
--header 'Authorization: Bearer YOUR_API_KEY' \\
--header 'Content-Type: application/json' \\
--data '{
  model: vtrix-grok-4,
  messages: [{role: user, content: Hello!}]
}'

Parameters Reference

Parameters

Parameter	Type	Required	Default	Range	Description
model	string	✅	-	-	Model ID: vtrix-grok-4
messages	array	✅	-	-	Array of message objects
messages[].role	string	✅	-	user, assistant, system, developer	Message role
messages[].content	string/array	✅	-	-	Text string or multimodal array
max_tokens	integer	❌	-	1-32768	Maximum tokens to generate
temperature	number	❌	1.0	0.0-2.0	Sampling temperature
top_p	number	❌	1.0	0.0-1.0	Nucleus sampling parameter
stream	boolean	❌	false	true, false	Stream response incrementally

Response Format

{
  id: chatcmpl-abc123,
  object: chat.completion,
  created: 1699896916,
  model: vtrix-grok-4,
  choices: [
    {
      index: 0,
      message: {
        role: assistant,
        content: Hello! How can I help you today?
      },
      finish_reason: stop
    }
  ],
  usage: {
    prompt_tokens: 10,
    completion_tokens: 20,
    total_tokens: 30
  }
}

Error Codes Reference

Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Insufficient balance or permission denied
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	An internal server error occurred

---

If you want, I can:

• Convert selected model sections into separate GitBook pages.

• Create a condensed reference table for Model IDs and endpoints.

• Extract and produce quick curl snippets for a chosen subset of models.