DeepSeek models are temporarily unavailable — use Qwen, GLM, Kimi and other Chinese models
cocodot has no DeepSeek model available to call right now. With the same key and the same OpenAI-compatible API, set the model field to Qwen, GLM, Kimi or another Chinese model and keep the rest of your code. We will update this page when DeepSeek is back.
Same key, nothing to redo
Your cocodot key and balance keep working. Switching models means changing one field — base_url and the rest of your code stay the same.
Chinese models you can use now
Qwen, GLM, Kimi and more — and Claude, GPT and Gemini on the same key. The pricing page lists every model ID and its rate.
What a DeepSeek request returns
A request that names a DeepSeek model returns HTTP 400 saying DeepSeek models are temporarily unavailable. It is not charged, and it is never quietly switched to another model.
Switch in one line
OpenAI-compatible — change the model name, keep the rest.
from openai import OpenAI
client = OpenAI(
base_url="https://cocodot.co/api/ai/v1",
api_key="YOUR_COCODOT_KEY",
)
resp = client.chat.completions.create(
model="qwen-flash", # or qwen3.6-plus · glm-5.2 (GLM) · kimi-k2.6 (Kimi)
messages=[{"role": "user", "content": "hi"}],
)
print(resp.choices[0].message.content)FAQ
Can I still call DeepSeek on cocodot?
Not right now — DeepSeek models are temporarily unavailable. Requests that name a DeepSeek model return HTTP 400 and are not charged. We will update this page when DeepSeek is back.
How do I switch?
Same OpenAI-compatible API. Keep base_url https://cocodot.co/api/ai/v1 and your cocodot key, and set the model (e.g. qwen-flash). Nothing else changes.
Which Chinese models can I use instead?
Qwen, GLM, Kimi and more — plus Claude, GPT and Gemini on the same key. The pricing page lists every model ID and its rate.