SLNG.
SLNG. API

Open Source @ SLNG

Endpoint:https://api.slng.ai

Llama 4 Scout

POST
https://api.slng.ai
/v1/llm/slng/llama-4-scout

OpenAI-compatible chat completions endpoint for Llama-4 Scout 17B-16E Instruct model.

Llama 4 Scout › Headers

  • Authorizationstring · required

    The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Llama 4 Scout › Request Body

  • messagesobject[] · required

    Array of messages in OpenAI chat format

  • modelstring

    Model name (defaults to llama-4-scout)

    Default: llama-4-scout
  • max_tokensinteger

    Maximum number of tokens to generate

  • temperaturenumber

    Sampling temperature (0-2)

  • top_pnumber

    Nucleus sampling parameter

  • presence_penaltynumber

    Presence penalty (-2 to 2)

  • frequency_penaltynumber

    Frequency penalty (-2 to 2)

  • stopstring[]

    Stop sequences

  • streamboolean

    Whether to stream the response

    Default: false

Llama 4 Scout › Responses

Chat completion response in OpenAI format

  • idstring

    Unique identifier for the completion

  • objectstring

    Object type (chat.completion)

  • createdinteger

    Unix timestamp when the completion was created

  • modelstring

    Model used for the completion

  • choicesobject[]
  • usageobject

Kimi K2 Instruct

POST
https://api.slng.ai
/v1/llm/slng/kimi-k2

OpenAI-compatible chat completions endpoint for Kimi K2 Instruct model.

Kimi K2 Instruct › Headers

  • Authorizationstring · required

    The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Kimi K2 Instruct › Request Body

  • messagesobject[] · required

    Array of messages in OpenAI chat format

  • modelstring

    Model name (defaults to kimi-k2)

    Default: kimi-k2
  • max_tokensinteger

    Maximum number of tokens to generate

    Default: 1000
  • temperaturenumber

    Sampling temperature (0-2)

    Default: 1
  • top_pnumber

    Nucleus sampling parameter

    Default: 1
  • presence_penaltynumber

    Presence penalty (-2 to 2)

    Default: 0
  • frequency_penaltynumber

    Frequency penalty (-2 to 2)

    Default: 0
  • stopstring[]

    Stop sequences

    Default: []
  • streamboolean

    Whether to stream the response

    Default: false
  • stream_optionsobject

    Streaming options

Kimi K2 Instruct › Responses

Chat completion response in OpenAI format

  • idstring

    Unique identifier for the completion

  • objectstring

    Object type (chat.completion)

  • createdinteger

    Unix timestamp when the completion was created

  • modelstring

    Model used for the completion

  • choicesobject[]
  • usageobject
Proprietary