Quickstart

A key, a request, a response. Five minutes if you already have Python or Node.js.

On this page

Three steps
Read the response
Next steps

Three steps

Get a key

API keys are available to Team workspaces and partners. Write to us, we create the key with you and you receive it once.
All about keys
Keep it out of your code

Put it in an environment variable on your server. The examples in this documentation read it from there.
Shell
```
export LEARNYA_API_KEY="lya_svc_…"
```

Send the request

With the OpenAI SDK or a plain HTTP request. The values in amber are the ones you change.

curl https://api.learnya.ai/v1/chat/completions \
  -H "Authorization: Bearer $LEARNYA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flash",
    "messages": [
      {
        "role": "user",
        "content": "Summarise Swiss data protection law."
      }
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.learnya.ai/v1",
    api_key=os.environ["LEARNYA_API_KEY"],
)

response = client.chat.completions.create(
    model="flash",
    messages=[
        {
            "role": "user",
            "content": "Summarise Swiss data protection law.",
        }
    ],
)
print(response.choices[0].message.content)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.learnya.ai/v1",
  apiKey: process.env.LEARNYA_API_KEY,
})

const response = await client.chat.completions.create({
  model: "flash",
  messages: [
    {
      role: "user",
      content: "Summarise Swiss data protection law.",
    },
  ],
})
console.log(response.choices[0].message.content)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.learnya.ai/v1",
  apiKey: process.env.LEARNYA_API_KEY,
})

const response: OpenAI.ChatCompletion =
  await client.chat.completions.create({
    model: "flash",
    messages: [
      {
        role: "user",
        content: "Summarise Swiss data protection law.",
      },
    ],
  })
const answer: string | null =
  response.choices[0].message.content
console.log(answer)

Response

{
  "id": "chatcmpl-5d0c9e2a41b7",
  "object": "chat.completion",
  "created": 1791633600,
  "model": "learnya-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. Personal data is processed lawfully, in good faith and for a stated purpose.\n2. Data protection is built in by design and by default.\n3. People can access their data and have it corrected or deleted."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 21, "completion_tokens": 52, "total_tokens": 73 }
}

Read the response

The response text is in the first choice, its message, its content. The token count is in the usage field.

Where	What you find there
`choices[0].message.content`	The response text
`choices[0].finish_reason`	Why the model stopped: natural end or length limit reached
`usage`	The tokens the model read and wrote
`x-learnya-slot`	Response header: the Learnya model that answered

Next steps

GuideChatInstructions, multi-turn exchanges and reasoning.GuideStreamingShow the response as it is written.GuideToolsLet the model call your functions.

Three steps

Get a key

Keep it out of your code

Send the request

Read the response

Next steps