DeepSeek API through one OpenAI-compatible endpoint

Q: How do I call DeepSeek models through Mimxo AI?

Use any OpenAI SDK with base URL https://mimxo.com/v1 and your Mimxo AI key, then set model to one of the IDs below, e.g. deepseek-v4-flash.

Use 5 DeepSeek models with the same key and base URL you use for every other model on Mimxo AI.

Get an API key

DeepSeek models and prices

Model	Provider	Input / 1M	Output / 1M	Cache read / 1M	List input / output
`deepseek-v4-flash`	DeepSeek	$0.0126	$0.0252	$0.00252	$0.042 / $0.084
`deepseek-v4-flash-0731`	DeepSeek	$0.00324	$0.384	$0.00324	$0.0108 / $1.28
`deepseek-v4-pro`	DeepSeek	$0.0626	$0.1253	$0.00522	$0.2088 / $0.4176
`deepseek-v4-pro-0813`	DeepSeek	$0.396	$1.188	$0.0132	$1.32 / $3.96
`deepseek-v4.1-flash`	DeepSeek	$0.009	$0.15	$0.00769	$0.03 / $0.5

Prices in USD per 1M tokens, read live from /api/pricing. "List" is the reference list price; Mimxo AI bills the first columns.

Example

curl https://mimxo.com/v1/chat/completions \
  -H "Authorization: Bearer $MIMXO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello"}]}'

from openai import OpenAI

client = OpenAI(base_url="https://mimxo.com/v1", api_key="YOUR_MIMXO_API_KEY")
resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Write a haiku about APIs"}],
)
print(resp.choices[0].message.content)

FAQ

How do I call DeepSeek models through Mimxo AI?

Use any OpenAI SDK with base URL https://mimxo.com/v1 and your Mimxo AI key, then set model to one of the IDs below, e.g. deepseek-v4-flash.

How much does the DeepSeek API cost on Mimxo AI?

0.3× the reference list price per 1M tokens. Current prices are in the table above.

Is this the official API?

No. Mimxo AI is an independent gateway that relays requests to the official DeepSeek API through OpenRouter.

Other providers: OpenAI API · Claude API · Gemini API · Grok API · Qwen API · GLM API · Kimi API · MiniMax API