Runway: Runway Gen-4 Image
runway-gen-4-image- Price
- From $0.08
- Modalities
- Image
About Runway Gen-4 Image
Runway Gen-4 Image is the still-image model of Runway's Gen-4 family, built to produce frames that stay visually consistent with each other. It generates from a text prompt and can also take reference images so a character, object, or location carries across a set of pictures. Its main role is feeding look-matched stills into video pipelines; the Turbo version trades some deliberation for speed.
Where it works well
- Reference images steer the result, so a character or product keeps its identity across several generated stills.
- Runway's Gen-4 material stresses consistent characters, locations, and objects across scenes, which suits storyboards and shot lists.
- Prompts can set composition and style together, giving fine control over the look of a frame.
- Stills line up with Runway's video models, which keeps a pipeline from still to motion in one visual style.
When to choose another model
- It is aimed at consistency inside Runway's own pipeline; for pure photorealism or readable typography another image model may do better.
- Quick idea exploration is cheaper and faster with the Turbo version of the same model.
- Output is a still; motion needs a separate video model.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Image editingText to imageTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "image-to-image", "model": "runway-gen-4-image", "prompt": "A minimalist product photo of matte black headphones on a soft blue background.", "image_url": "https://example.com/source.png" }'
Parameters
Image editing
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
height | Not provided | 1024 | Use an integer. |
image | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_url | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_urls | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
images | Inputs: ≥ 1, ≤ 3 | Not provided | Limits apply when this input is supplied. Image aliases are combined into one input image list; the limit applies to the combined list. |
n | 1 | 1 | Use an integer. |
operationRequired | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 1 characters. Maximum length: 1000 characters. |
width | Not provided | 1024 | Use an integer. |
Text to image
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
height | Not provided | 1024 | Use an integer. |
images | Not provided | Not provided | Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests. |
n | 1 | 1 | Use an integer. |
operationRequired | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 1 characters. Maximum length: 1000 characters. |
width | Not provided | 1024 | Use an integer. |
Fields outside this contract are rejected.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Image editing
per image- Official price
- $0.08
- Verified price
- —
- Discount
- —
Text to image
per image- Official price
- $0.08
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Image editing | $0.08 | — | — |
| Text to image | $0.08 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Runway Gen-4 Image in Console with a prompt ready to edit or send.
Help me create an image with runway-gen-4-image using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Storyboards with a fixed cast
Generate a sequence of frames where the same character appears in different locations by passing the same reference each time.
First frames for video
Create the opening still for an image-to-video job so the clip starts from a composition you approved.
Product in varied scenes
Place one product reference into several environments and lighting setups for campaign mockups.
Style-matched asset sets
Produce a group of images sharing one palette and treatment for a deck, game concept, or pitch.
Prompt examples
The woman from the reference image sits in a night-train cabin, reading under a warm reading lamp, cinematic still, muted teal palette.
The sneaker from the reference stands on wet cobblestone at dawn, low angle, soft backlight, editorial product photo.
Wide establishing shot of a desert research outpost at golden hour, flat illustrated style, long shadows, no people.
FAQ
What is Runway Gen-4 Image?
It is Runway's text-to-image model in the Gen-4 family. It generates stills from prompts and optional reference images, with a focus on keeping characters, objects, and style consistent from one image to the next so they can seed video work.
Can I edit an existing image with it?
Yes. Pass your picture as a reference and describe the change or new scene; the model builds a new image guided by that reference rather than editing pixels in place.
What are reference images for?
They tell the model what a person, object, or place should look like. Runway's Gen-4 pages describe generating consistent characters and objects across scenes from references, without any fine-tuning or extra training on your side.
How does it differ from Gen-4 Image Turbo?
The standard model is the higher-quality tier; Turbo is the faster option meant for quick visual iteration. Use Turbo to test ideas and framing, then rerun the chosen direction on the standard model for the final still.
Does it produce video?
No. It outputs still images. To animate a result, send the still to a Runway video model such as Gen-4.5, which accepts an image as the starting frame.
How much does Runway Gen-4 Image cost?
On TokenLab, Runway Gen-4 Image costs $0.08 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should Runway Gen-4 Image use?
Use https://api.tokenlab.sh/v1/images/edits for Runway Gen-4 Image. The request example below shows the matching code shape.
Which operations does Runway Gen-4 Image support?
Runway Gen-4 Image supports Image editing, Text to image. Select an operation above to see its endpoint and request example.
Compare Runway Gen-4 Image
Sources
Reviewed Oct 2, 2026