Seed 2.1 Turbo Text Generation

curl -X POST "https://api.apiyi.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dola-seed-2-1-turbo-260628",
    "messages": [
      {"role": "user", "content": "Introduce yourself in one sentence"}
    ],
    "max_tokens": 500,
    "thinking": {"type": "disabled"}
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

response = client.chat.completions.create(
    model="dola-seed-2-1-turbo-260628",
    messages=[
        {"role": "user", "content": "Analyze the time complexity of this code and suggest optimizations"}
    ],
    max_tokens=3000,
    reasoning_effort="high",  # low / medium / high
)

msg = response.choices[0].message
print(msg.content)
# Reasoning text is in msg.reasoning_content (via model_extra with the OpenAI SDK)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.apiyi.com/v1'
});

const stream = await client.chat.completions.create({
  model: 'dola-seed-2-1-turbo-260628',
  messages: [{ role: 'user', content: 'Write a short poem about summer' }],
  max_tokens: 1500,
  stream: true,
  stream_options: { include_usage: true }
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

curl -X POST "https://api.apiyi.com/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dola-seed-2-1-turbo-260628",
    "input": "Introduce yourself in one sentence",
    "max_output_tokens": 1500
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

# Turn 1: enable explicit caching
r1 = client.responses.create(
    model="dola-seed-2-1-turbo-260628",
    input=[
        {"role": "system", "content": "A long, fixed background document goes here..."},
        {"role": "user", "content": "First question"},
    ],
    max_output_tokens=1500,
    extra_body={"caching": {"type": "enabled"}, "store": True},
)
print(r1.output_text)

# Turn 2: carry the previous id - the whole prior context hits the cache (~2x faster measured)
r2 = client.responses.create(
    model="dola-seed-2-1-turbo-260628",
    input="Second question",
    previous_response_id=r1.id,
    max_output_tokens=1500,
    extra_body={"caching": {"type": "enabled"}},
)
print(r2.output_text)
print(r2.usage.input_tokens_details.cached_tokens)  # cache hits