Reasoning-Effort

from openai import OpenAI

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

response = client.chat.completions.create(
    model="Kimi-K3-3BIT-REAP",
    reasoning_effort="low",
    messages=[{"role": "user", "content": "Is 221 a prime number?"}],
)

message = response.choices[0].message
print("Reasoning:", getattr(message, "reasoning_content", None))
print("Answer:", message.content)
print("Reasoning tokens:", response.usage.completion_tokens_details.reasoning_tokens)

import OpenAI from "openai";

const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://api.shannon-ai.com/v1" });

const response = await client.chat.completions.create({
  model: "Kimi-K3-3BIT-REAP",
  reasoning_effort: "low",
  messages: [{ role: "user", content: "Is 221 a prime number?" }],
});

const message = response.choices[0].message;
console.log("Reasoning:", message.reasoning_content);
console.log("Answer:", message.content);
console.log("Reasoning tokens:", response.usage.completion_tokens_details.reasoning_tokens);

curl https://api.shannon-ai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Kimi-K3-3BIT-REAP",
    "reasoning_effort": "low",
    "messages": [
      {"role": "user", "content": "Is 221 a prime number?"}
    ]
  }'

{
  "model": "Kimi-K3-3BIT-REAP",
  "reasoning_effort": "low",
  "messages": [{"role": "user", "content": "Is 221 a prime number?"}]
}

{
  "model": "Kimi-K3-3BIT-REAP",
  "reasoning": {"effort": "low"},
  "input": "Is 221 a prime number?"
}

{
  "model": "Kimi-K3-3BIT-REAP",
  "max_tokens": 1024,
  "thinking": {"type": "enabled", "budget_tokens": 2048},
  "messages": [{"role": "user", "content": "Is 221 a prime number?"}]
}

{
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "No. 221 = 13 x 17, so it is not prime.",
        "reasoning_content": "Try small primes. 221 / 13 = 17, so 221 = 13 x 17."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 43,
    "total_tokens": 57,
    "prompt_tokens_details": {"cached_tokens": 0},
    "completion_tokens_details": {"reasoning_tokens": 27}
  }
}

{
  "output": [
    {
      "id": "rs_6f0a2c4e8b1d4f3a9c7e5b3d1f8a6c4e",
      "type": "reasoning",
      "summary": [
        {
          "type": "summary_text",
          "text": "Try small primes. 221 / 13 = 17, so 221 = 13 x 17."
        }
      ]
    },
    {
      "id": "msg_1b3d5f7a9c2e4b6d8f0a2c4e6b8d0f1a",
      "type": "message",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "No. 221 = 13 x 17, so it is not prime.",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 14,
    "input_tokens_details": {"cached_tokens": 0},
    "output_tokens": 43,
    "output_tokens_details": {"reasoning_tokens": 27},
    "total_tokens": 57
  }
}

{
  "content": [
    {
      "type": "thinking",
      "thinking": "Try small primes. 221 / 13 = 17, so 221 = 13 x 17."
    },
    {"type": "text", "text": "No. 221 = 13 x 17, so it is not prime."}
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 14,
    "cache_read_input_tokens": 0,
    "cache_creation_input_tokens": 0,
    "output_tokens": 43
  }
}

from openai import OpenAI

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

stream = client.chat.completions.create(
    model="Kimi-K3-3BIT-REAP",
    reasoning_effort="medium",
    stream=True,
    messages=[{"role": "user", "content": "Is 221 a prime number?"}],
)

for chunk in stream:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    reasoning = getattr(delta, "reasoning_content", None)
    if reasoning:
        print(reasoning, end="", flush=True)      # the reasoning text comes first
    if delta.content:
        print(delta.content, end="", flush=True)  # then the answer

import OpenAI from "openai";

const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://api.shannon-ai.com/v1" });

const stream = await client.chat.completions.create({
  model: "Kimi-K3-3BIT-REAP",
  reasoning_effort: "medium",
  stream: true,
  messages: [{ role: "user", content: "Is 221 a prime number?" }],
});

for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta ?? {};
  if (delta.reasoning_content) process.stdout.write(delta.reasoning_content); // the reasoning text comes first
  if (delta.content) process.stdout.write(delta.content);                     // then the answer
}

curl -N https://api.shannon-ai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Kimi-K3-3BIT-REAP",
    "reasoning_effort": "medium",
    "stream": true,
    "messages": [
      {"role": "user", "content": "Is 221 a prime number?"}
    ]
  }'