GPT-6 Astra Text Generation

from openai import OpenAI

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

response = client.responses.create(
    model="gpt-6-astra",
    reasoning={"effort": "high"},   # low / medium / high / xhigh
    instructions="You are a senior backend engineer. Be concise.",
    input="Migrate this repo from Python 3.9 to 3.13 and list every file that needs changes, with reasons",
    max_output_tokens=4000,
)
print(response.output_text)
print(response.usage.output_tokens_details.reasoning_tokens)

from openai import OpenAI
import json

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.apiyi.com/v1")
tools = [
    {"type": "web_search"},
    {"type": "function", "name": "get_weather", "description": "Current weather for a city",
     "parameters": {"type": "object", "properties": {"city": {"type": "string"}},
                    "required": ["city"], "additionalProperties": False}, "strict": True},
]
r = client.responses.create(model="gpt-6-astra", tools=tools, reasoning={"effort": "low"},
                            input="Check the current weather in Beijing and Shanghai.")
for item in r.output:
    if item.type == "function_call":
        print(item.name, json.loads(item.arguments))

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.apiyi.com/v1")
history = [{"role": "user", "content": "Multiply 17 by 23. Answer with the number only."}]

r1 = client.responses.create(
    model="gpt-6-astra", input=history, store=False,
    reasoning={"effort": "medium"}, include=["reasoning.encrypted_content"],
)
# Replay the previous turn's full output (including the encrypted reasoning item); works on all three lines, no server-side storage needed
history += [item.model_dump(exclude_none=True) for item in r1.output]
history.append({"role": "user", "content": "Now add 1 to the result. Number only."})

r2 = client.responses.create(
    model="gpt-6-astra", input=history, store=False,
    reasoning={"effort": "medium"}, include=["reasoning.encrypted_content"],
)
print(r2.output_text)   # 392

curl https://api.apiyi.com/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "reasoning": {"effort": "low"},
    "input": [{"role": "user", "content": [
      {"type": "input_text", "text": "How many colored blocks are in this image?"},
      {"type": "input_image", "image_url": "data:image/png;base64,iVBORw0KGgo..."}
    ]}]
  }'

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-6-astra",
    reasoning_effort="high",
    max_completion_tokens=4000,      # not the legacy max_tokens (400)
    messages=[
        # system works on the official lines; Codex_Reverse drops it, and developer works everywhere
        {"role": "developer", "content": "You are a senior backend engineer. Be concise."},
        {"role": "user", "content": "Explain Python 3.13's free-threaded mode"},
    ],
)
print(response.choices[0].message.content)

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: 'gpt-6-astra',
  reasoning_effort: 'low',
  messages: [{ role: 'user', content: 'Describe the Great Wall in three sentences' }],
  stream: true,
  stream_options: { include_usage: true },
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}