Runway: Runway Gen-4 Image Turbo
runway-gen-4-image-turbo- Price
- From $0.02
- Modalities
- Image
About Runway Gen-4 Image Turbo
Runway Gen-4 Image Turbo is the faster version of Runway's Gen-4 image model, meant for rapid visual iteration. It builds images from a prompt together with reference images, keeping the key style and composition control of the standard model. It works as a reference-guided image editor, so it fits testing many directions cheaply before committing to a final render.
Where it works well
- Generation is quicker than on the standard Gen-4 Image, which suits trying many prompts in one session.
- Reference images guide who or what appears, carrying a character or object into each new frame.
- Style and composition control from the Gen-4 family is retained rather than stripped for speed.
- Output stills drop straight into Runway's video models as starting frames.
When to choose another model
- It is the draft tier; final hero images may need a rerun on the standard Gen-4 Image for more refined results.
- It works from reference images rather than a bare text prompt.
- It outputs stills only; animation 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 editingTokenLab 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-turbo", "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. |
operation | 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
- $0.02
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Image editing | $0.02 | — | — |
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 Turbo in Console with a prompt ready to edit or send.
Help me create an image with runway-gen-4-image-turbo using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Exploring looks fast
Run a dozen variations of a scene with different lighting or lens descriptions and pick the direction worth refining.
Reference-guided edits
Send a photo of a person or product as reference and ask for it in a new setting to see if the identity holds.
Draft storyboards
Block out a shot list with approximate frames quickly, then upgrade selected frames.
Thumbnail and mockup tests
Check composition and crop options for key art before spending time on polished versions.
Prompt examples
Using the reference portrait, show the same man in a workshop, leaning on a bench, warm tungsten light, documentary style.
Place the reference backpack on a mountain trail at sunrise, three-quarter view, shallow focus, clean outdoor retail look.
Same character as the reference, now in a rain-lit alley, wide shot, cinematic color grade.
FAQ
What is Runway Gen-4 Image Turbo?
It is the speed-oriented sibling of Gen-4 Image. It generates images from text prompts and reference images while holding on to style and composition control, and it is aimed at teams that need many quick iterations.
When should I pick Turbo over Gen-4 Image?
Pick Turbo while exploring: testing prompts, framing, and which reference works. Switch to the standard Gen-4 Image once you know the direction and want the final still, because the standard model is the higher-quality tier.
Does it need a reference image?
Yes. Turbo is an image-edit model, so send at least one reference image with your prompt. For a text-only request, use Gen-4 Image, which generates from text.
Can it keep a character consistent?
Reference images are the mechanism. Runway describes Gen-4 as able to keep characters, locations, and objects consistent from references without retraining. Use the same reference across requests and describe only what changes.
Can I turn the result into a video?
Yes, as a second step. Use the still as the starting frame of an image-to-video request on a video model like Runway Gen-4.5. The image model itself returns pictures only.
How much does Runway Gen-4 Image Turbo cost?
On TokenLab, Runway Gen-4 Image Turbo costs $0.02 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 Turbo use?
Use https://api.tokenlab.sh/v1/images/edits for Runway Gen-4 Image Turbo. The request example below shows the matching code shape.
Which operations does Runway Gen-4 Image Turbo support?
Runway Gen-4 Image Turbo supports Image editing. Select an operation above to see its endpoint and request example.
Compare Runway Gen-4 Image Turbo
Sources
Reviewed Oct 2, 2026