The AI arena is free today

Open Superagent
ZAIReleased on Jan 14, 2026

GLM-Image: Pricing, Performance & Examples

GLM-Image is a image generation model from ZAI, released in January 2026.

GLM-Image is a high-quality text-to-image generation model from Zhipu AI. It excels at generating detailed, coherent images from text prompts with strong prompt adherence and artistic quality.

Input
Text
Output
Image

GLM-Image examples

Recent arena outputs from GLM-Image, picked from the highest-ranked matchups.

GLM-Image API

POST/v1/generations

Set for image-to-image / editing models.

Run a request to see the response

Use it in your code

OpenAI-compatible endpoint through the LLM Stats gateway.

import requests

# Create the generation. wait="auto" long-polls (up to 60s) so most short
# jobs return as "completed" in a single round-trip.
res = requests.post(
    "https://gateway.llm-stats.com/v1/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "glm-image",
        "input": {"prompt": "A beautiful sunset over mountains"},
        "wait": "auto",
    },
)
job = res.json()

# If it didn't finish inside the wait window, poll the same resource.
while job["status"] in ("queued", "running"):
    res = requests.get(
        f"https://gateway.llm-stats.com/v1/generations/{job['id']}",
        params={"wait": 60},
        headers={"Authorization": "Bearer YOUR_API_KEY"},
    )
    job = res.json()

if job["status"] == "completed":
    print("image:", job["output"]["media"][0]["url"])
else:
    print("Failed:", job["error"]["message"])

Need an API key? Create one above in the playground, or read the API documentation.

GLM-Image pricing

Providers

GLM-Image starts at $0.0300 per generated image via ZAI. See all 2 providers below with their per-image pricing, latency, and modality support.

ProviderPrice $/imageLatency sModalities in / out
ZAI logoZAI
$0.0300
/
Fal logoFal
$0.0500
/

GLM-Image latency

GLM-Image time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

GLM-Image benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Performance by category and language

Where GLM-Image is strongest across prompt themes and languages. Conservative TrueSkill score (μ − 3σ), only axes with 3+ votes.

Quality Tracker

GLM-Image Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Fri Aug 28 2026

Similar Models

How GLM-Image compares to its closest neighbors on each image arena it competes in.

Notice missing or incorrect data?

GLM-Image license

GLM-Image is released under the MIT license, which permits commercial use, has 16.0B parameters.

License
MIT
Commercial use allowed
Parameters
16.0B

MIT License - allows commercial use

GLM-Image resources

Official sources for GLM-Image: api documentation, official playground, official launch post.

Models like GLM-Image

Other image models ranked closest to GLM-Image.

FAQ

Common questions about GLM-Image.

When was GLM-Image released?

GLM-Image was released on January 14, 2026 by ZAI. This is the official GLM-Image release date tracked on LLM Stats.

Is GLM-Image available via API?

Yes, GLM-Image is available via API. See the official documentation for authentication and endpoint details. It is served by 2 providers tracked on LLM Stats.

How big is GLM-Image?

GLM-Image has 16 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created GLM-Image?

GLM-Image was created by ZAI.

What is the license for GLM-Image?

GLM-Image is released under the MIT license. This is an open-source / open-weight license that permits self-hosting.

Where can I use GLM-Image?

GLM-Image is available through 2 providers including ZAI, Fal.

Where is the GLM-Image paper or technical report?

GLM-Image has a paper or technical report available at https://z.ai/blog/glm-image. Use that source for architecture, training, release and evaluation details.