Quick Start

Authentication

The Neyra AI API employs API keys for authentication. You can generate API keys either at a user level or for service accounts. Each API key can be restricted to specific scopes, allowing for tailored access control.

Get your API keys

Your API requests are authenticated using API keys. Any request that doesn't include an API key will return an error. You can generate an API key from your Dashboard.

All API requests should include your API key in an Authorization HTTP header as follows:

Authorization: Bearer NEYRA_API_KEY

Install the library

Our platform utilizes the OpenAI libraries to make the interaction as easy as possible. The best way to interact with our API is to use the official libraries:

# Install via pip
pip install openai

You can interact with the Neyra API through HTTP requests from any language, via official OpenAI Python bindings, official Node.js library, or a community-maintained library.

from openai import OpenAI
from os import getenv

# gets API Key from environment variable NEYRA_API_KEY
client = OpenAI(
  base_url="https://api.neyratech.com/api/v1",
  api_key=getenv("NEYRA_API_KEY"),
)

completion = client.chat.completions.create(
  model="neyra/1D",
  stream=True,
  messages=[
    {
      "role": "user",
      "content": "Hi",
    },
  ],
)

for chunk in completion:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

from openai import OpenAI
from os import getenv

# gets API Key from environment variable NEYRA_API_KEY
client = OpenAI(
  base_url="https://api.neyratech.com/api/v1",
  api_key=getenv("NEYRA_API_KEY"),
)

completion = client.chat.completions.create(
  model="neyra/1D",
  stream=False,
  messages=[
    {
      "role": "user",
      "content": "Hi",
    },
  ],
)
print(completion.choices[0].message.content)

curl https://api.neyratech.com/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEYRA_API_KEY" \
  -d '{
  "model": "neyra/1D",
  "stream": false,
  "messages": [
    {"role": "user", "content": "What is the meaning of life?"}
  ]
}'

import OpenAI from "openai"

const openai = new OpenAI({
  baseURL: "https://api.neyratech.com/api/v1",
  apiKey: $NEYRA_API_KEY,
})
async function main() {
  const completion = await openai.chat.completions.create({
    model: "neyra/1D",
    messages: [
      { role: "user", content: "Say this is a test" }
    ],
  })

  console.log(completion.choices[0].message)
}
main()

Create new conversation

POST https://api.neyratech.com/v1/chat/completions

Creates a new conversation.

Request Body

Name

Type

Description

messages*

array

A list of messages comprising the conversation so far.

model*

string

ID of the model to use.

stream

bool

If set, partial message deltas will be sent

stop

string / array

Up to 10 sequences where the API will stop generating further tokens.

max_tokens

integer

The maximum number of tokens that can be generated in the chat completion.

temperature

float

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

top_p

float

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

{
    "id": "chatcmpl-abc123",
    "object": "chat.completion",
    "created": 1677858242,
    "model": "neyra/1D",
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "\n\nThis is a test!"
            },
            "logprobs": null,
            "finish_reason": "stop"
        }
    ]
}

PreviousGet API key NextAPI membership

Last updated 1 year ago