DeepSeek, OpenRouter, Mistral, Groq and Perplexity without code

DeepSeek, OpenRouter, Mistral, Groq and Perplexity connect to nana800 without code through one block: choose the service, paste its key and type the model name. OpenRouter gives hundreds of models with one key, and the custom option connects your own server or another service with the OpenAI request format. Each block run costs $0.002 in nana800, and the tokens are paid for in the chosen service.

Build it in the builder
  • Block run: $0.002
  • Free every month: $3.50
  • No card needed

What you can do

  • Use DeepSeek and Mistral models directly with your own key
  • Reach hundreds of models from different companies through OpenRouter with one key, for example openai/gpt-5.2 or anthropic/claude-sonnet-4.6
  • Run llama-3.3-70b-versatile and openai/gpt-oss-120b on Groq for fast answers
  • Get Perplexity answers together with the full service response that holds the source links
  • Connect your own model server or any other service with the OpenAI request format
  • Get the answer as JSON and put its fields into a table or CRM, when the model supports this mode

Blocks in the builder

  • OpenAI-compatible request

    Action · $0.002 per run

    Sends a text task to OpenRouter, DeepSeek, Mistral, Groq, Perplexity or your own API address with your key. The answer comes back as text or JSON. This block does not take images.

How to set it up

  1. 1

    Get a key from the service

    Create the key in your account with the service: OpenRouter under Settings, Keys, DeepSeek and Mistral under API keys, Groq under Keys in its console, Perplexity in its API settings. If the service charges for requests, keep money on its balance.

  2. 2

    Create a scheme and add a trigger

    Create a scheme in the builder and choose what starts it: Telegram message from user to bot for a bot, webhook for website forms, or button to run it by hand and test.

  3. 3

    Add the OpenAI-compatible AI block

    In the service field choose openrouter, deepseek, mistral, groq, perplexity or custom. For custom, enter the API address up to the /chat/completions part. Internal network addresses such as localhost or 192.168.x.x are rejected. Paste the API key.

  4. 4

    Type the model and the task

    Write the model name exactly as the service does, for example deepseek-v4-pro or mistral-large-latest. Write the task in the prompt field with data from the trigger, and set the role and tone in the system instruction.

  5. 5

    Pass the answer on

    Add a block that delivers the result: Telegram message send, send email message or google sheet record. The answer text is in text_response, the parsed JSON is in json_response.

  6. 6

    Turn the scheme on and test it

    Turn the scheme on, press the button trigger and check the answer in the run history of the scheme. The button itself is free. If it looks right, keep the scheme on. While the scheme is on, it costs $0.0042 per hour.

Frequently asked questions

A block run costs $0.002 whatever the answer length. The chosen service counts and charges the model tokens at its own prices. An enabled scheme costs $0.0042 per hour. Your nana800 balance is topped up to $3.50 for free every month, no card needed. A scheme kept on around the clock for a month spends most of that on scheme hours.

The list has OpenRouter, DeepSeek, Mistral, Groq and Perplexity, with their API addresses already filled in. The custom option is for your own server or another service with the OpenAI request format, as long as it is reachable from the internet.

Exactly as the service writes it. On OpenRouter the name is company/model, for example openai/gpt-5.2. Examples for other services: deepseek-flash, mistral-small-latest, llama-3.3-70b-versatile, perplexity/sonar. If the name is wrong, the reason shows up in error_message.

Yes. Choose json_object in the answer format field and describe the fields you need in the prompt. The parsed object is in json_response. Not every model supports this mode: if the service returns an error, switch back to text.

No, this block works with text only. To describe a photo or compare two images, use the OpenAI, Claude or Gemini blocks.

Build your first scheme for free

Sign-up is free and needs no card. Every month the balance is topped up to $3.50 for free, enough for about 3,500 runs of basic blocks.

Build it in the builder