Keys you control
Create a key for each project. Track its usage and revoke it when you no longer need it.
Loading Inferum…
MiniMax, DeepSeek, and GLM through one OpenAI-compatible API. Built for applications, coding tools, and AI agents.

Three open models for text, code, and reasoning. One clear token price.
| Model | Input / 1M tokens | Output / 1M tokens | Details |
|---|---|---|---|
MiniMax M2.7 MiniMax | $0.0200 | $0.0200 | |
DeepSeek V4 Flash 0731 DeepSeek | $0.0200 | $0.0200 | |
GLM 5.3 Flash Z.ai | $0.0200 | $0.0200 |
Use the OpenAI SDK with your Inferum endpoint and key. Send requests, stream responses, and track usage in your dashboard.
Read the API guideimport os
from openai import OpenAI
client = OpenAI(
base_url="https://inferum.ai/v1",
api_key=os.environ["INFERUM_API_KEY"]
)
response = client.chat.completions.create(
model="MiniMaxAI/MiniMax-M2.7",
messages=[
{"role": "user", "content": "Hello from Inferum"}
]
)
print(response.choices[0].message.content)Create a key for each project. Track its usage and revoke it when you no longer need it.
Review model usage, input and output tokens, costs, and errors in one place.
Use your free tokens first, then your prepaid balance. See what you have used and what remains.
One fixed rate across supported models. Track your token usage and spending as you build.
10,000,000 total input + output tokens.
One-time bonus per mailbox after verification.
Try the models with your own application.
Start with 10M free tokens and see how Inferum fits your setup.