Wirestack
Runway API adds Kling 4.0 Flash, GPT Image 2.6 Flare and Sunburst, and Gemini Omni 1.2 Flash (November 5, 2026)
Four new Runway API models: two video, two image. GPT Image 2.6 starts at 1 credit per image; Kling 4.0 Flash is 9.4 credits a second.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- Runway API secretRUNWAYML_API_SECRETGet key
Create or pick a project, then open the API Keys tab. Add credits in the Billing tab first
3 of 3 free copies left this month.Unlimited with Pro
What you get
On November 5, 2026 Runway added four third-party models to its API, Runway Dev:
- Kling 4.0 Flash (
kling_4_flash): 3 to 20 seconds of 720p video with audio. Default length is 5 seconds. It works from text, a first frame, image or video references, or a source video to edit. Price: 9.4 credits per output second without input video, with a 29-credit minimum. Runway's example: a 5-second clip costs 47 credits. With input video it is 6.3 credits per output second plus 6.3 credits per second of the longer of input and output. The Kling 4.0 discount does not apply to Flash. - GPT Image 2.6 Flare (
gpt_image_2_6_flare) and GPT Image 2.6 Sunburst (gpt_image_2_6_sunburst): PNG images from prompts up to 32,000 characters. Up to 16 reference images,outputCount1 to 10, and transparent backgrounds.qualityandreasoningEfforttakelow,mediumorhigh, both defaulthigh. Price: 1 to 19 credits per image by quality, size and shape, plus 1 credit per reference image per generated image. A 1K 16:9 image (1920:1088) athighcosts 5 credits. Reasoning effort does not change the price. - Gemini Omni 1.2 Flash (
gemini_omni_flash_1.2): 3 to 15 seconds of video at 360p, 720p, 1080p or 4K, from a prompt up to 4,000 characters. It defaults to 720p andduration: "auto". Price: 2, 7, 10 or 21 credits per second by resolution, plus 1 credit per reference image or keyframe and 1 credit per second of input video. Minimum 6 credits per request.
The two video models use POST /v1/text_to_video, /v1/image_to_video and /v1/video_to_video. The two image models use POST /v1/text_to_image.