Advanced Usage

stream = client.chat.completions.create(
    model="meta-llama/llama-3.1-70b-instruct",
    messages=[
        {"role": "user", "content": "Write a short story about a robot."}
    ],
    stream=True
)

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

curl -X POST https://api.pinference.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $PRIME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.1-70b-instruct",
    "messages": [{"role": "user", "content": "Tell me a story"}],
    "stream": true
  }'

const response = await fetch('https://api.pinference.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.PRIME_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'meta-llama/llama-3.1-70b-instruct',
    messages: [{ role: 'user', content: 'Tell me a story' }],
    stream: true
  })
});

const reader = response.body.getReader();
const decoder = new TextDecoder();

while (true) {
  const { done, value } = await reader.read();
  if (done) break;

  const chunk = decoder.decode(value);
  process.stdout.write(chunk);
}