// DeepSeek API

DeepSeek API for global developers and coding agents.

XinoAPI provides OpenAI-compatible access to DeepSeek V4-Flash and DeepSeek V4-Pro for chat, coding, long-context review, and agent workflows outside mainland China.

Choose the right DeepSeek API model

DeepSeek V4-Flash

Use deepseek-v4-flash for fast chat, extraction, coding loops, and high-throughput agent steps. It supports 1M context and up to 384K output.

DeepSeek V4-Pro

Use deepseek-v4-pro when planning, code review, or difficult reasoning matters more than turnaround time. It also supports 1M context and up to 384K output.

Time-of-use pricing

DeepSeek requests use the published Beijing-time peak or off-peak rate, locked when the request starts. Check the current DeepSeek API pricing before production rollout.

Use explicit V4 model IDs in new integrations instead of relying on legacy aliases. The same https://api.xinoapi.com/v1 base URL works with the OpenAI SDK and compatible agent tools.

Quick start

from openai import OpenAI

client = OpenAI(
    api_key="xino-your-key-here",
    base_url="https://api.xinoapi.com/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello from XinoAPI"}],
)

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

Use explicit model IDs. Avoid legacy aliases in new integrations.

Common questions

What DeepSeek model ID should I use?

Use deepseek-v4-flash for fast general tasks and deepseek-v4-pro for planning, reasoning, and code review.

Is XinoAPI compatible with the OpenAI SDK?

Yes. Set the base URL to https://api.xinoapi.com/v1 and use your XinoAPI key.

Can I use DeepSeek with CC Switch or Codex?

Yes. Configure XinoAPI as a custom OpenAI-compatible provider and select deepseek-v4-flash or deepseek-v4-pro.

Next steps

Review pricing, choose a model, and test with a small request before moving production traffic.

Chat with us