Create Image - TokenLab

Overview

For coding agents, discover the current recommended image shortlist first with GET /v1/models?recommended_for=image, then send the selected model explicitly to this endpoint. gpt-image-2 is a token-priced GPT Image model. TokenLab follows OpenAI’s official usage breakdown for text input, image input, reported cached input, and image output tokens; it is not billed as a fixed per-image model. For gpt-image-2 image generation, supported public parameters are prompt, n, size, quality, response_format, async, background, output_format, output_compression or compression, moderation, partial_images, and user. Omit size or quality to let TokenLab use auto; custom size values must use the flexible WIDTHxHEIGHT contract documented below. Compatibility note: if input_fidelity is sent with gpt-image-2, TokenLab removes it before forwarding because GPT Image 2 already handles image inputs at high fidelity.

Model behavior notes

Google Gemini image-family models do not share the same selector contract:

gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, nano-banana-2, and nano-banana-pro support aspect_ratio plus resolution (1k, 2k, 4k) for text-to-image generation.
gemini-2.5-flash-image, nano-banana, and nano-banana-edit support aspect_ratio but do not expose public resolution selection.
gemini-2.0-flash-preview-image-generation is documented here as prompt-only text-to-image.
For nano-banana, nano-banana-2, and nano-banana-pro reference-image requests, use this endpoint (/v1/images/generations) with operation: "image-to-image" and image_urls. Do not send Nano Banana reference-image requests to /v1/images/edits.
For Nano Banana image-to-image requests, omit resolution. nano-banana-2 and nano-banana-pro expose resolution only for text-to-image, and nano-banana does not expose it.
Reference images on this endpoint can be supplied as JSON image_url / image_urls, or as a multipart image file. images[] and file_id are not accepted on /v1/images/generations; create /v1/files references only for /v1/images/edits models that document images[].file_id.

For Google image families, prefer aspect_ratio and only send resolution when the model explicitly supports it. xAI Grok Imagine image models (grok-imagine-image, grok-imagine-image-quality, and legacy grok-imagine-image-pro) support aspect_ratio plus resolution (1k, 2k). grok-imagine-image-pro is retained as a compatibility ID and routes upstream to grok-imagine-image-quality.

Request Body

Synchronous request timeout: Some routed image providers return the final image inline and wait for generation to finish. High-resolution or high-quality requests can take close to a minute or longer, so set your HTTP client timeout to at least 120s. If the create response includes status: "pending", task_id, or poll_url, follow the returned poll_url instead.

model

string

default:"dall-e-3"

Model to use (e.g., gpt-image-2, dall-e-3, flux-pro, midjourney).

prompt

string

required

Text description of the desired image.

image_url

string

Public HTTPS reference image URL for image-to-image generation. For Nano Banana family requests, set operation to image-to-image and omit resolution unless the model explicitly supports it for that operation.

image_urls

string[]

Public HTTPS reference image URLs. Use this for one or more reference images in JSON requests. file_id and images[] are not supported on this endpoint.

reference_image_urls

string[]

Additional model-specific reference image URLs for providers that distinguish primary input images from references.

image

file

Multipart reference image file for image-to-image generation. Use this when the source image is private or header-protected. This is different from a /v1/files file_id, which is not accepted on this endpoint.

integer

default:"1"

Number of images to generate (1-10, model dependent).

size

string

default:"1024x1024"

Image size. Use this for OpenAI-style image families and other models that accept exact pixel sizes.For gpt-image-2, size accepts auto or WIDTHxHEIGHT. Custom dimensions must both be multiples of 16, the longest edge must be at most 3840px, the long/short ratio must be at most 3:1, and total pixels must be between 655,360 and 8,294,400. aspect_ratio and resolution are not part of the current TokenLab public contract for gpt-image-2.For Google Gemini image families, size is treated as a compatibility alias that maps onto the model’s public aspect_ratio and, where supported, resolution contract. Prefer sending aspect_ratio directly for those models.

aspect_ratio

string

Model-dependent aspect ratio selector.Common Google image-family values include 1:1, 16:9, 9:16, 3:2, and 2:3.

resolution

string

Model-dependent output resolution selector.Supported on gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, nano-banana-2, nano-banana-pro, and similar high-resolution families. Typical values are 1k, 2k, and 4k. Do not send this parameter to ratio-only Gemini image families unless the model explicitly documents it. For xAI Grok Imagine image models, use 1k or 2k.

quality

string

default:"standard"

Image quality. DALL-E models use standard or hd; GPT Image models such as gpt-image-2 use auto, low, medium, or high.

response_format

string

default:"url"

Response format: url or b64_json. The default is url.For Azure Official or Azure-compatible gpt-image-2 routes, TokenLab does not forward response_format upstream. The gateway always receives upstream image data as b64_json; for url requests it uploads every image to the CDN and returns data[].url. If CDN storage is unavailable or upload fails, the request fails instead of falling back to Base64. For b64_json, the raw Base64 is returned.

async

boolean

default:"false"

Set to true with gpt-image-2 or official FLUX/BFL image models to create a task first. Completed async image tasks return URLs regardless of the requested response_format; use synchronous requests when you need b64_json.

style

string

default:"vivid"

Style for DALL-E 3: vivid or natural.

user

string

A unique identifier for the end-user.

Response

Inline Response

created

integer

Unix timestamp of creation.

data

array

Array of generated images.Each object contains:

url (string): URL of the generated image
b64_json (string): Base64-encoded image (if requested)
revised_prompt (string): The prompt used (DALL-E 3)

Async Task Response

Set async: true with gpt-image-2 or official FLUX/BFL image models to create a task instead of waiting for the final image in the create request. The response includes status: "pending", task_id, and poll_url. Poll /v1/tasks/{task_id} until the task reaches completed or failed. Async image tasks return final image URLs only. If you need raw b64_json image data, use a synchronous request. Billing may reserve the estimated amount when the task is created. Completed tasks are billed by actual usage, and failed or timed-out tasks are released or refunded.

created

integer

Unix timestamp of creation.

task_id

string

Unique task identifier for polling.

status

string

Initial status: pending.

poll_url

string

Relative URL to poll for results, for example /v1/tasks/{id}.

data

array

Empty while the task is pending. Completed image tasks return generated image URLs in data[].url.

When you receive status: "pending", use poll_url or GET /v1/tasks/{task_id} to retrieve the result.

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "prompt": "A cinematic portrait of a white cat sitting on a rainy windowsill",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "n": 1
  }'

{
  "created": 1706000000,
  "data": [
    {
      "url": "https://...",
      "revised_prompt": "A fluffy white cat with bright eyes sitting peacefully on a wooden windowsill, watching raindrops stream down the glass window..."
    }
  ]
}

Available Models

Model	Type	Features
`dall-e-3`	Usually inline	Best quality, prompt enhancement
`dall-e-2`	Usually inline	Faster, more affordable
`flux-pro`	Often task-based	Photorealistic, high quality
`flux-schnell`	Usually inline	Very fast
`midjourney`	Often task-based	Artistic style
`ideogram-v3`	Often task-based	Best text rendering
`stable-diffusion-3`	Usually inline	Open source, customizable

Do not hard-code a model as always synchronous or always asynchronous. If the create response returns status: "pending", follow poll_url and poll until completion.

Handling Task-Based Responses

For image models, always check whether the response contains status: "pending":

import requests
import time

def generate_image(prompt, model="midjourney"):
    # Create image request
    response = requests.post(
        "https://api.tokenlab.sh/v1/images/generations",
        headers={"Authorization": "Bearer sk-your-api-key"},
        json={"model": model, "prompt": prompt}
    )
    data = response.json()

    # Check if task-based
    if data.get("status") == "pending":
        task_id = data["task_id"]
        poll_url = data.get("poll_url")
        print(f"Image task started: {task_id}")

        # Poll for result
        while True:
            status_resp = requests.get(
                f"https://api.tokenlab.sh{poll_url}" if poll_url else f"https://api.tokenlab.sh/v1/tasks/{task_id}",
                headers={"Authorization": "Bearer sk-your-api-key"}
            )
            status_data = status_resp.json()

            if status_data["status"] == "completed":
                return status_data["data"][0]["url"]
            elif status_data["status"] == "failed":
                raise Exception(status_data.get("error", "Generation failed"))

            time.sleep(3)
    else:
        # Inline response
        return data["data"][0]["url"]

# Usage
url = generate_image("a beautiful sunset over mountains", model="midjourney")
print(f"Generated image: {url}")

Documentation Index

​Overview

​Model behavior notes

​Request Body

​Response

​Inline Response

​Async Task Response

​Available Models

​Handling Task-Based Responses

Overview

Model behavior notes

Request Body

Response

Inline Response

Async Task Response

Available Models

Handling Task-Based Responses