GLM Image - AI Image Generation API: Pricing, Documentation

GLM Image is a versatile interface that allows developers to integrate advanced image generation and editing capabilities into their applications. By leveraging a specialized model architecture, it can transform natural language prompts into high-quality visuals with a particular focus on accurate text rendering and complex scene composition. The API supports various performance tiers to balance speed and detail, making it suitable for a wide range of use cases from rapid prototyping to final asset creation.

Get API Key

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

GLM Image v1 API Documentation

https://gateway.pixazo.ai/glm-image/v1/glm-image-request

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

GLM Image generate request - GLM Image

Request Code

POST https://gateway.pixazo.ai/glm-image/v1/glm-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "An elegant watercolor menu card painted on textured cream paper, soft turquoise washes, golden accents, dreamy bokeh background, editorial photography style",
  "image_size": "square_hd",
  "num_inference_steps": 30,
  "guidance_scale": 1.5,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg"
}

import requests

url = "https://gateway.pixazo.ai/glm-image/v1/glm-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "An elegant watercolor menu card painted on textured cream paper, soft turquoise washes, golden accents, dreamy bokeh background, editorial photography style",
    "image_size": "square_hd",
    "num_inference_steps": 30,
    "guidance_scale": 1.5,
    "num_images": 1,
    "enable_safety_checker": true,
    "output_format": "jpeg"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/glm-image/v1/glm-image-request';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'An elegant watercolor menu card painted on textured cream paper, soft turquoise washes, golden accents, dreamy bokeh background, editorial photography style',
  image_size: 'square_hd',
  num_inference_steps: 30,
  guidance_scale: 1.5,
  num_images: 1,
  enable_safety_checker: true,
  output_format: 'jpeg'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/glm-image/v1/glm-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "An elegant watercolor menu card painted on textured cream paper, soft turquoise washes, golden accents, dreamy bokeh background, editorial photography style",
    "image_size": "square_hd",
    "num_inference_steps": 30,
    "guidance_scale": 1.5,
    "num_images": 1,
    "enable_safety_checker": true,
    "output_format": "jpeg"
  }'

Output

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Try Now

Request Parameters - GLM Image generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the image to generate. Detailed, descriptive prompts produce the best results.
image_size	No	string or object	square_hd	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, portrait_3_2, landscape_3_2, portrait_hd, landscape_hd — or a custom {"width": 1280, "height": 720} object (1–14142 px per side)	Output image size. Use one of the preset aspect-ratio values, or pass a custom object with width and height in pixels.
num_inference_steps	No	integer	30	10–100	Number of diffusion denoising steps. More steps generally produce higher-quality images but take longer.
guidance_scale	No	float	1.5	1–10	Classifier-free guidance scale (prompt adherence). Higher values follow the prompt more closely; lower values allow more creative variation.
seed	No	integer	—	Any integer	Random seed for reproducibility. Reuse the same seed with identical settings to reproduce the same image; leave it empty for a different output each time.
num_images	No	integer	1	1–4	Number of images to generate in a single request.
enable_safety_checker	No	boolean	true	true, false	Enables NSFW safety checking on the generated images. Leave enabled unless you have a specific reason to disable it.
output_format	No	string	jpeg	jpeg, png	Output image format.
sync_mode	No	boolean	false	true, false	If true, the image is returned directly as a base64 data URI instead of a hosted URL. Handy for quick tests; for normal use leave it off to get a download link.
enable_prompt_expansion	No	boolean	false	true, false	If true, your prompt is automatically expanded and enriched by an LLM before generation for more detailed, higher-quality results.

Minimum Request

{
  "prompt": "An elegant watercolor menu card painted on textured cream paper, soft turquoise washes, golden accents, dreamy bokeh background, editorial photography style"
}

Full Request (all options)

{
  "prompt": "An elegant watercolor menu card painted on textured cream paper, soft turquoise washes, golden accents, dreamy bokeh background, editorial photography style",
  "image_size": "square_hd",
  "num_inference_steps": 30,
  "guidance_scale": 1.5,
  "seed": 42,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "sync_mode": false,
  "enable_prompt_expansion": true
}

Response

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Response Fields - GLM Image generate request

Field	Type	Description
images	array	Array of generated image objects.
file_name	string	Name of the generated image file.
content_type	string	MIME type of the image (e.g., image/png, image/jpeg).
url	string	Public URL to access the generated image.
description	string	Empty string placeholder for compatibility.

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for GLM Image generate request.

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Error Responses

{
  "error": {
    "code": "INVALID_PARAMETER",
    "message": "Invalid image_size value: invalid_size"
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "Missing or invalid Ocp-Apim-Subscription-Key header"
  }
}

{
  "error": {
    "code": "INSUFFICIENT_FUNDS",
    "message": "Insufficient wallet balance to process request"
  }
}

{
  "error": {
    "code": "RATE_LIMIT_EXCEEDED",
    "message": "Rate limit exceeded. Retry after 60 seconds."
  }
}

{
  "error": {
    "code": "INTERNAL_ERROR",
    "message": "Internal server error. Please retry later."
  }
}

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field for details
ERROR	System error — request was not processed and not charged

Status Flow

QUEUED → PROCESSING → (COMPLETED / FAILED / ERROR)

Typical Workflow

Submit a request to /glm-image-request to get a request_id
Wait 2–3 seconds, then send a GET request to /v2/requests/status/{request_id}
Repeat polling every 2–3 seconds until status is COMPLETED, FAILED, or ERROR
If COMPLETED, use output.media_url[0] to retrieve the generated image
Implement exponential backoff for ERROR or 500 responses

GLM Image check status - GLM Image

Request Code

POST https://gateway.pixazo.ai/v2/requests/status/glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "request_id": "glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

import requests

url = "https://gateway.pixazo.ai/v2/requests/status/glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
headers = {
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "request_id": "glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/v2/requests/status/glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx';
const headers = {
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  request_id: 'glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/v2/requests/status/glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "request_id": "glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
  }'

Output

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Request Parameters - GLM Image check status

Parameter	Required	Type	Default	Allowed values / range	Description
request_id	Yes	string	—	—	The unique identifier returned from the initial /glm-image-request call.

Minimum Request

{
  "request_id": "glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Full Request

{
  "request_id": "glm-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Response

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Response Fields - GLM Image check status

Field	Type	Description
images	array	Array of generated image objects.
file_name	string	Name of the generated image file.
content_type	string	MIME type of the image (e.g., image/png, image/jpeg).
url	string	Public URL to access the generated image.
description	string	Empty string placeholder for compatibility.

Request Headers

Header	Value
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for GLM Image check status.

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
404	Not Found
429	Too Many Requests
500	Internal Server Error

Notes & Tips

Poll the status endpoint every 2–3 seconds until COMPLETED, FAILED, or ERROR is returned.
Implement exponential backoff for retry logic on ERROR or 500 responses.
Use detailed, descriptive prompts with specific styles, lighting, and composition cues for optimal results.
Set a seed value to reproduce identical outputs for iterative refinement.
Use enable_prompt_expansion: true for complex scenes to improve detail and coherence.
Prefer output_format: "png" for images requiring transparency or lossless quality.
Avoid overly long prompts exceeding 500 characters for best performance.
Processing time typically ranges from 5–15 seconds depending on complexity.
Multiple images (num_images > 1) may increase processing time proportionally.

GLM Image v1 API Pricing

Your request will cost $0.05 per image.

Image to Image

GLM Image v1 API Documentation

https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

GLM Image (Image to Image) generate request - GLM Image (Image to Image)

Request Code

POST https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Make the dress red.",
  "image_urls": [
    "https://example.com/example_inputs/catwalk.png"
  ]
}

import requests

url = "https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Make the dress red.",
    "image_urls": [
        "https://example.com/example_inputs/catwalk.png"
    ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = "https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};
const data = {
  prompt: "Make the dress red.",
  image_urls: [
    "https://example.com/example_inputs/catwalk.png"
  ]
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error("Error:", error));

curl -X POST "https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Make the dress red.",
    "image_urls": [
      "https://example.com/example_inputs/catwalk.png"
    ]
  }'

Output

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Try Now

Request Parameters - GLM Image (Image to Image) generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the desired edit or transformation of the input image(s).
image_urls	Yes	string[]	—	1–4 image URLs	URL(s) of the condition image(s) used for image-to-image generation. Supports up to 4 URLs for multi-image references.
image_size	No	string or object	square_hd	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, portrait_3_2, landscape_3_2, portrait_hd, landscape_hd — or a custom {"width": 1280, "height": 720} object (1–14142 px per side)	Output image size. Use one of the preset aspect-ratio values, or pass a custom object with width and height in pixels.
num_inference_steps	No	integer	30	10–100	Number of diffusion denoising steps. More steps generally produce higher-quality images but take longer.
guidance_scale	No	float	1.5	1–10	Classifier-free guidance scale (prompt adherence). Higher values follow the prompt more closely; lower values allow more creative variation.
seed	No	integer	—	Any integer	Random seed for reproducibility. Reuse the same seed with identical settings to reproduce the same image; leave it empty for a different output each time.
num_images	No	integer	1	1–4	Number of images to generate in a single request.
enable_safety_checker	No	boolean	true	true, false	Enables NSFW safety checking on the generated images. Leave enabled unless you have a specific reason to disable it.
output_format	No	string	jpeg	jpeg, png	Output image format.
sync_mode	No	boolean	false	true, false	If true, the image is returned directly as a base64 data URI instead of a hosted URL. Handy for quick tests; for normal use leave it off to get a download link.
enable_prompt_expansion	No	boolean	false	true, false	If true, your prompt is automatically expanded and enriched by an LLM before generation for more detailed, higher-quality results.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	—	JPG, PNG, WEBP	Image(s) to transform.

Minimum Request

{
  "prompt": "Make the dress red.",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png"
  ]
}

Full Request (all options)

{
  "prompt": "Make the dress red.",
  "image_urls": [
    "https://example.com/example_inputs/catwalk.png"
  ],
  "image_size": "square_hd",
  "num_inference_steps": 30,
  "guidance_scale": 1.5,
  "seed": 42,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "sync_mode": false,
  "enable_prompt_expansion": false
}

Response

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Response Fields - GLM Image (Image to Image) generate request

Field	Type	Description
images	array	Array of generated images, each with file_name, content_type, and url.
file_name	string	Name of the generated image file.
content_type	string	MIME type of the image (e.g., image/png, image/jpeg).
url	string	URL to download the generated image.
description	string	Empty string placeholder for compatibility.

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for GLM Image (Image to Image) generate request.

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Error Responses

400 Validation Error

{
  "error": "Missing required parameter: prompt",
  "code": "VALIDATION_ERROR"
}

404 Not Found

{
  "error": "Operation not found",
  "code": "NOT_FOUND"
}

Status Handling

Polling status values for GLM Image (Image to Image) generate request.

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field for details
ERROR	System error — request was not processed and not charged

Status Flow

QUEUED → PROCESSING → (COMPLETED or FAILED or ERROR)

Typical Workflow

Submit request to /glm-image-image-to-image-request and receive a request_id.
Poll the status endpoint /glm-image-image-to-image-request-result every 2–3 seconds using the request_id.
Continue polling until response status is COMPLETED, FAILED, or ERROR.
When COMPLETED, extract the image URL from the response and download the result.

GLM Image (Image to Image) check status - GLM Image (Image to Image)

Request Code

POST https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request-result
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "request_id": "glm-image-image-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

import requests

url = "https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request-result"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "request_id": "glm-image-image-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = "https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request-result";
const headers = {
  "Content-Type": "application/json",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};
const data = {
  request_id: "glm-image-image-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error("Error:", error));

curl -X POST "https://gateway.pixazo.ai/glm-image-image-to-image/v1/glm-image-image-to-image-request-result" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "request_id": "glm-image-image-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
  }'

Output

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Try Now

Request Parameters - GLM Image (Image to Image) check status

Parameter	Required	Type	Default	Allowed values / range	Description
request_id	Yes	string	—	—	The unique identifier returned from the initial request to /glm-image-image-to-image-request.

Minimum Request

{
  "request_id": "glm-image-image-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Full Request (all options)

{
  "request_id": "glm-image-image-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Response

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Response Fields - GLM Image (Image to Image) check status

Field	Type	Description
images	array	Array of generated images, each with file_name, content_type, and url.
file_name	string	Name of the generated image file.
content_type	string	MIME type of the image (e.g., image/png, image/jpeg).
url	string	URL to download the generated image.
description	string	Empty string placeholder for compatibility.

Request Headers

Header	Value
Content-Type	application/json
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for GLM Image (Image to Image) check status.

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Notes & Tips

Poll the status endpoint every 2–3 seconds until COMPLETED, FAILED, or ERROR is returned.
Implement exponential backoff for retrying failed or timed-out requests.
Use detailed, descriptive prompts with specific color, texture, and style references for best results.
For multi-image conditioning, ensure all reference images are high-resolution and clearly depict the elements to be preserved.
Use enable_prompt_expansion for ambiguous prompts to improve generation quality.
Prefer output_format: png for edits requiring transparency or lossless quality.
Set a seed value when reproducibility is required across multiple runs.

GLM Image v1 API Pricing

Your request will cost $0.05 per image.