arch2devs
HomeHomePage
Docs
  • Scaler
  • documentation
  • Stoplight
HomeHomePage
Docs
  • Scaler
  • documentation
  • Stoplight
  1. AI
  • Arch.2 Devs
  • Tools
    • Compiles and executes code
      POST
    • Fetches clips based on search text.
      GET
  • Image
    • Discovers content using Google Lens API.
      GET
  • music
    • find songs using audio powered by sazzam
      GET
  • Image Processing
    • changes clothes on a person with a given cloth image(out of comission)
      GET
    • Applies photo effects .
      GET
    • Expands an image using a Diffusers
      GET
    • Upscales an image
      GET
    • Removes the background of an image using an image URL.
      GET
    • Transforms an image into a zombie-like image
      GET
  • Media
    • Parses media URLs using download4.cc API.
      GET
  • AI
    • arch copilot ai.
      POST
    • Llama-70B a top level LLM model
      POST
    • DeepSeek-R1-Distill-Llama-70B a top level resoning model
      POST
    • fetches latest information from online.
      GET
    • o3-mini
      GET
    • conversation apis
      POST
    • A proxy unoffial API
      GET
    • Interacts with the Blackbox.ai API.
      GET
    • gpt4o api.
      GET
  • LLM
    • Arch.2 coder light weight version
      GET
    • Sends a chat completion request to the Deepinfra API.
      POST
    • CHATGPT AI
      GET
    • Communicates with the chat API,
      GET
    • arch.2 coder , coding agent (full access for premium users)
      GET
    • CHATGPT AI
      POST
  • NSFW
    • Fetches hentai content from 2dhentai.club.
  • Audio
    • Generates speech
    • Generates speech using Streamlabs Polly API and streams the audio.
    • Generates speech using StreamElements Kappa API and streams the audio.
    • Generates speech using Voiceforge TTS API.
    • Generates speech using Acapela Group API and streams the audio.
    • Generates speech using Lazypy TTS API.
  • Weather
    • Fetches Weather of a given location.
  • Maker
    • Generates an image from code .
    • Generates a code snippet image from ray.so.
    • Generate memes .
    • Generates a fake image with given text, username, and avatar.
    • Fetches a dynamic logo
  • IMAGE-GENERATORS
    • Generates an image .
    • Imgen
    • prodia sdxl models
    • gen img based on a prompt.
    • flux DEV
    • flux snell .
    • sdxl light image generator
    • unlimited Prodia API with specified prompt and model.
    • Generates an anime-style image based on provided text
    • Generates an image.
    • flux style image generator
  • system
    • Retrieve OpenAPI (Swagger) JSON specification
    • Server uptime and start time information
    • Redirects to the Arch2Devs website.
    • Comprehensive server and API metrics report
    • api list
    • API to display call statistics
  • Anime
    • Generates an image 2 anime.
  1. AI

DeepSeek-R1-Distill-Llama-70B a top level resoning model

POST
http://www.arch2devs.ct.ws/api/deepseek-70b
Last modified:2025-02-27 08:25:16
Maintainer:Not configured
OperationId:postApideepseekr1

Request

Body Params application/json
messages
array[string]
optional
Array of message objects (role and content).
Example:
[{"role":"user","content":"hi"},{"role":"assistant","content":"<think>\nOkay, the user wrote \"hi\". That's pretty straightforward. I should respond in a friendly and welcoming manner. Maybe say hello and ask how I can assist them today. Keep it open-ended to encourage them to ask whatever they need help with. Let me make sure the tone is warm and approachable.Hmm, should I use any emojis? Maybe a smiley face to keep it friendly. But not too many. Just one would be enough. Also, check for any typos. Alright, that should do it.\n</think>\n\nHello! How can I assist you today? 😊"}]
max_tokens
number 
optional
Maximum number of tokens to generate.
Example:
512
temperature
number 
optional
Sampling temperature.
Example:
0.7
top_p
number 
optional
Top p sampling parameter.
Example:
0.7
top_k
number 
optional
Top k sampling parameter.
Example:
50
repetition_penalty
number 
optional
Repetition penalty.
Example:
1
stop
array[string]
optional
Array of stop sequences.
Example:
["<|end of sentence|>"]
stream
boolean 
optional
Enable or disable streaming.
Example:
true
Example
{
    "messages": [
        {
            "role": "user",
            "content": "hi"
        },
        {
            "role": "assistant",
            "content": "<think>\nOkay, the user wrote \"hi\". That's pretty straightforward. I should respond in a friendly and welcoming manner. Maybe say hello and ask how I can assist them today. Keep it open-ended to encourage them to ask whatever they need help with. Let me make sure the tone is warm and approachable.Hmm, should I use any emojis? Maybe a smiley face to keep it friendly. But not too many. Just one would be enough. Also, check for any typos. Alright, that should do it.\n</think>\n\nHello! How can I assist you today? 😊"
        }
    ],
    "max_tokens": 512,
    "temperature": 0.7,
    "top_p": 0.7,
    "top_k": 50,
    "repetition_penalty": 1,
    "stop": [
        "<|end of sentence|>"
    ],
    "stream": true
}

Request samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST 'http://www.arch2devs.ct.ws/api/deepseek-70b' \
--header 'Content-Type: application/json' \
--data-raw '{
    "messages": [
        {
            "role": "user",
            "content": "hi"
        },
        {
            "role": "assistant",
            "content": "<think>\nOkay, the user wrote \"hi\". That'\''s pretty straightforward. I should respond in a friendly and welcoming manner. Maybe say hello and ask how I can assist them today. Keep it open-ended to encourage them to ask whatever they need help with. Let me make sure the tone is warm and approachable.Hmm, should I use any emojis? Maybe a smiley face to keep it friendly. But not too many. Just one would be enough. Also, check for any typos. Alright, that should do it.\n</think>\n\nHello! How can I assist you today? 😊"
        }
    ],
    "max_tokens": 512,
    "temperature": 0.7,
    "top_p": 0.7,
    "top_k": 50,
    "repetition_penalty": 1,
    "stop": [
        "<|end of sentence|>"
    ],
    "stream": true
}'

Responses

🟢200OK
application/json
Successful response
Body
object {0}
Example
{
    "message": "Success"
}
🔴500Server Error
Modified at 2025-02-27 08:25:16
Previous
Llama-70B a top level LLM model
Next
fetches latest information from online.
Built with