Chat

Instructions, a question, an answer. Then the rest of the exchange, sending the history back on every turn.

On this page

Messages
Multiple turns
Useful parameters
Reasoning

Messages

A conversation is a list of messages, each with a role.

Role	Who is speaking
`system`	Your instructions: tone, language, what the model should do or avoid
`user`	The person or your application
`assistant`	The model’s previous responses
`tool`	The result of one of your functions

Multiple turns

The model keeps nothing between calls. To continue an exchange, send the whole conversation again with the new message.

messages = [
    {
        "role": "system",
        "content": "Answer in French, in plain words.",
    },
    {
        "role": "user",
        "content": "What must a privacy notice contain?",
    },
]
first = client.chat.completions.create(
    model="flash", messages=messages
)

# No memory between calls: send the whole conversation again.
messages.append(first.choices[0].message)
messages.append(
    {
        "role": "user",
        "content": "Write one for a bakery with a web shop.",
    }
)
second = client.chat.completions.create(
    model="flash", messages=messages, temperature=0.4
)
print(second.choices[0].message.content)

const messages = [
  {
    role: "system",
    content: "Answer in French, in plain words.",
  },
  {
    role: "user",
    content: "What must a privacy notice contain?",
  },
]
const first = await client.chat.completions.create({
  model: "flash",
  messages,
})

// No memory between calls: send the whole conversation again.
messages.push(first.choices[0].message)
messages.push({
  role: "user",
  content: "Write one for a bakery with a web shop.",
})
const second = await client.chat.completions.create({
  model: "flash",
  messages,
  temperature: 0.4,
})
console.log(second.choices[0].message.content)

import type OpenAI from "openai"

const messages: OpenAI.ChatCompletionMessageParam[] = [
  {
    role: "system",
    content: "Answer in French, in plain words.",
  },
  {
    role: "user",
    content: "What must a privacy notice contain?",
  },
]
const first = await client.chat.completions.create({
  model: "flash",
  messages,
})

// No memory between calls: send the whole conversation again.
messages.push(first.choices[0].message)
messages.push({
  role: "user",
  content: "Write one for a bakery with a web shop.",
})
const second = await client.chat.completions.create({
  model: "flash",
  messages,
  temperature: 0.4,
})
console.log(second.choices[0].message.content)

Useful parameters

temperaturenumber: Lower gives more consistent responses, higher gives more varied ones. If unset, the model receives the value we chose for it.
max_tokensinteger: The maximum length of the response, capped at the model’s limit if it exceeds it.
response_formatobject: Asks for a response in JSON, so your code can read it directly.
stoparray: Character sequences that stop the response.

Reasoning

For a hard question, ask the model to think before answering. Effort ranges from none to high. The reasoning arrives separately, in reasoning_content.

response = client.chat.completions.create(
    model="max",
    reasoning_effort="high",
    messages=[
        {
            "role": "user",
            "content": "Compare these contracts.",
        }
    ],
)
message = response.choices[0].message
# How the model got there, then the answer.
print(getattr(message, "reasoning_content", None))
print(message.content)

const response = await client.chat.completions.create({
  model: "max",
  reasoning_effort: "high",
  messages: [
    { role: "user", content: "Compare these contracts." },
  ],
})
const message = response.choices[0].message
// How the model got there, then the answer.
console.log(message.reasoning_content)
console.log(message.content)

import type { ChatCompletionMessage } from "openai/resources"

// Learnya adds the reasoning next to the answer,
// a field the OpenAI types do not declare.
type LearnyaMessage = ChatCompletionMessage & {
  reasoning_content?: string
}

const response = await client.chat.completions.create({
  model: "max",
  reasoning_effort: "high",
  messages: [
    { role: "user", content: "Compare these contracts." },
  ],
})
const message: LearnyaMessage = response.choices[0].message
// How the model got there, then the answer.
console.log(message.reasoning_content)
console.log(message.content)

curl https://api.learnya.ai/v1/chat/completions \
  -H "Authorization: Bearer $LEARNYA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "max",
    "reasoning_effort": "high",
    "messages": [
      {"role": "user", "content": "Compare these contracts."}
    ]
  }'