5 Free AI Models Through One OpenAI-Compatible API (Chat, Vision, Image Gen, Video Gen)

#machinelearning #python #ai #api

Disclosure: I run NovAI (aiapi-pro.com), the gateway described below. This is a first-party announcement, not an independent review.

We just made 5 models completely free on our OpenAI-compatible API — covering chat, vision reasoning, image generation and video generation. Here's what they are and how to call each one.

The 5 free models

Model ID	Type	Endpoint	Price
`glm-4.7-flash`	Chat LLM	`/v1/chat/completions`	$0
`glm-4.1v-thinking-flash`	Vision + reasoning	`/v1/chat/completions`	$0
`glm-4.6v-flash`	Vision	`/v1/chat/completions`	$0
`cogview-3-flash`	Image generation	`/v1/images/generations`	$0
`cogvideox-flash`	Video generation	`/v1/video/generations`	$0

All five are Zhipu (Z.ai) GLM-family "flash" variants. Zhipu offers them free upstream and we pass that through with zero markup. The trade-off is capability (flash models are smaller than flagships), not hidden fees.

Free chat: glm-4.7-flash

from openai import OpenAI

client = OpenAI(api_key="sk-novai-xxx", base_url="https://aiapi-pro.com/v1")

resp = client.chat.completions.create(
    model="glm-4.7-flash",
    messages=[{"role": "user", "content": "Summarize this in one sentence: ..."}],
)
print(resp.choices[0].message.content)

Free vision reasoning: glm-4.1v-thinking-flash

resp = client.chat.completions.create(
    model="glm-4.1v-thinking-flash",
    messages=[{"role": "user", "content": [
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}},
        {"type": "text", "text": "What trend does this chart show?"},
    ]}],
)

The "thinking" variant reasons step-by-step over images — charts, documents, screenshots. For plain image description, glm-4.6v-flash uses the same request format.

Free image generation: cogview-3-flash

img = client.images.generate(
    model="cogview-3-flash",
    prompt="minimalist logo of a paper plane, flat design",
)
print(img.data[0].url)

Free video generation: cogvideox-flash

import requests

r = requests.post(
    "https://aiapi-pro.com/v1/video/generations",
    headers={"Authorization": "Bearer sk-novai-xxx"},
    json={"model": "cogvideox-flash", "prompt": "a paper plane flying over a city at sunset"},
)
print(r.json())

Video generation is asynchronous — you get a task ID and poll for the result.

What are flash models actually good for?

Prototyping — build and demo an AI feature before spending anything
CI / integration tests — run pipeline tests against a real API at $0
Light production work — summaries, tagging, alt-text, thumbnails
Learning — try vision, image gen and video gen APIs without a budget

When you outgrow them, the same API key works for the paid catalog (DeepSeek, Qwen, Kimi, Doubao Seedance video, Seedream image, etc.).

FAQ

Do I need a Chinese phone number? No — email signup; paid models (if you ever need them) accept PayPal.

Is there a catch? No hidden fees. Flash models are just smaller than flagship models.

Questions about the free tier? Happy to answer in the comments.

DEV Community