Reasoning

• Qwen/Qwen3-32B
• Qwen/Qwen3.6-27B
• Qwen/Qwen3.5-397B-A17B
• kimi-k2.6

​

Core Capabilities

• Structured thinking: Break complex problems into smaller and clearer steps through chain-of-thought (CoT).
• Knowledge fusion: Combine general knowledge with domain-specific context to improve coverage and accuracy.
• Self-correction: Add validation and reflection during generation to improve result reliability.
• Multimodal processing: Some models support mixed inputs, such as text, code, and formulas. For details, refer to the corresponding model details.

​

Usage Notes

• Before moving to production, check each model’s context limits, whether it supports thinking_budget, pricing, and concurrency limits.
• Not every model emits a reasoning field. General-purpose chat models, such as DeepSeek-V4-Flash, answer directly without exposing a separate chain-of-thought.

​

Key Parameters

​

Parameter Description

• Request parameters
  • thinking_budget: Token budget for internal reasoning. It can be used to balance reasoning depth and response latency.
  • max_completion_tokens: Total generation budget, including reasoning tokens and visible output tokens. Use it to control the maximum amount generated by the request.
• Context context_length is not a request parameter. The maximum context length supported by each model can be viewed in Models.
• Response fields
  • reasoning: Chain-of-thought content, at the same level as content in the response object.
  • content: The final answer content shown to end users.

​

Recommendations

• thinking_budget is a hint, not a hard limit. Some models use it to adjust the amount of reasoning, while others may only partially apply it or even ignore it. Do not treat it as an exact limit.
• The reasoning process and final answer share the max_completion_tokens budget. If max_completion_tokens is set too low, reasoning content may consume the budget, causing content to be empty with finish_reason: length. Increase max_completion_tokens appropriately or control reasoning length through thinking_budget to leave enough room for the final answer.
• If the output exceeds max_completion_tokens, or the total input exceeds context_length, the response will be truncated and finish_reason will be set to length.

​

Notes

• Streaming vs. non-streaming: Use streaming when you need long output or real-time feedback; use non-streaming when you need to receive the complete result at once.
• Latency and stability: Tune thinking_budget, max_completion_tokens, and client timeout settings to reduce the risk of 504 errors and request timeouts.
• Quota and concurrency: Configure rate limiting strategies with pricing in mind, based on Models. Implement exponential backoff on the client side when necessary.

​

Billing

• Formula: Cost = input tokens x input unit price + output tokens x output unit price Output tokens include reasoning tokens and visible output tokens. Even if reasoning tokens are not returned as visible content, they are included in platform usage statistics and billed at the model’s output unit price. If the request hits or writes Prompt Caching, cache read tokens and cache write tokens are billed at the corresponding cache unit prices.
• Pricing: Input and output unit prices may vary by model. Check the model detail page in Models for details.
• Note: For the relationship between reasoning tokens, output tokens, and max_completion_tokens, see Token Usage and Billing.

​

Examples

export API_KEY="YOUR_API_KEY"

​

Streaming Request

import os
from openai import OpenAI

BASE_URL = "https://api.scitix.ai/model-api"
API_KEY = os.environ["API_KEY"]

client = OpenAI(base_url=BASE_URL, api_key=API_KEY)

messages = [{"role": "user", "content": "Which is the largest anime website in China?"}]

content = ""
reasoning = ""

resp = client.chat.completions.create(
    model="Qwen/Qwen3-32B",
    messages=messages,
    stream=True,
    max_completion_tokens=4096,
    extra_body={"thinking_budget": 1024},
)

for chunk in resp:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if getattr(delta, "content", None):
        content += delta.content
        print(delta.content, end="", flush=True)
    if getattr(delta, "reasoning", None):
        reasoning += delta.reasoning

# Optionally persist the reasoning text for debugging/audit

# Round 2 (continue the conversation)
messages.append({"role": "assistant", "content": content})
messages.append({"role": "user", "content": "Continue"})

resp2 = client.chat.completions.create(
    model="Qwen/Qwen3-32B",
    messages=messages,
    stream=True,
)

for chunk in resp2:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if getattr(delta, "content", None):
        print(delta.content, end="", flush=True)

​

Non-Streaming Request

import os
from openai import OpenAI

BASE_URL = "https://api.scitix.ai/model-api"
API_KEY = os.environ["API_KEY"]

client = OpenAI(base_url=BASE_URL, api_key=API_KEY)

messages = [{"role": "user", "content": "Which is the largest anime website in China?"}]

resp = client.chat.completions.create(
    model="Qwen/Qwen3.5-397B-A17B",
    messages=messages,
    stream=False,
    max_completion_tokens=4096,
    extra_body={"thinking_budget": 1024},
)

content = resp.choices[0].message.content
reasoning = getattr(resp.choices[0].message, "reasoning", "")
finish_reason = resp.choices[0].finish_reason

# Round 2 (continue the conversation)
messages.append({"role": "assistant", "content": content})
messages.append({"role": "user", "content": "Continue"})

resp2 = client.chat.completions.create(
    model="Qwen/Qwen3.5-397B-A17B",
    messages=messages,
    stream=False,
)

print(resp2.choices[0].message.content)

​

FAQ