Runway API Updates & Release Notes

October 13th, 2026 - Kling is now available on Runway Dev.

Kling 2.5 Turbo Pro

Kling 2.5 Turbo Pro (kling2.5_turbo_pro) generates from text or a start frame, with an optional last frame, at 5 or 10 seconds (default 5). Text-to-video ratio is 1920:1080 (the default), 1440:1440, or 1080:1920 (1280:720, 720:720, and 720:1280 are still accepted). Image-to-video follows the input image. Billed at 12 credits per second.

Kling 3.0

Kling 3.0 Standard (kling3.0_standard), Kling 3.0 Pro (kling3.0_pro), and Kling 3.0 4K (kling3.0_4k) generate from text or first and last frames for 3–15 seconds (default 5), with optional audio (audio defaults to true) and multishot prompts via providerSettings.multiPrompt (up to 6 segments, 3–15 seconds total).

Text-to-video ratio is 1280:720, 720:1280, or 960:960 (Standard), 1920:1080, 1080:1920, or 1440:1440 (Pro), and 3840:2160, 2160:3840, or 2880:2880 (4K).

Billed at 9 credits per second without audio and 13 with audio (Standard), 12 and 17 (Pro), and 43 either way (4K).

Kling O3

Kling O3 Standard (klingO3_standard), Kling O3 Pro (klingO3_pro), and Kling O3 4K (klingO3_4k) use those same ratios and durations, and also accept up to 7 reference images on image-to-video (keyframes count toward that total) and video-to-video edits of a clip up to 10 seconds.

O3 is billed at 13, 17, and 43 credits per second, including when audio is false. Kling O3 video-to-video is billed per second of the input video.

Additional details

cfgScale (0–1, default 0.5) is available on Kling 2.5 Turbo Pro and Kling 3.0.

Use the text to video, image to video, and video to video endpoints to get started.

October 12th, 2026 - Ideogram 4.5 (ideogram_4_5) is now available on Runway Dev.

Generate images with legible typography and layout from a prompt of up to 10,000 characters, with up to 5 reference images and outputCount from 1–8. ratio is a width:height size across 1K and 2K (for example 1024:1024, 2560:1440, 1440:2880), or auto (the default) to let the model choose. Set preciseEdit: true to edit the first reference image while preserving its composition and dimensions, or pass a black-and-white maskUri to edit only the black areas. quality is very_low, low, medium, or high, billed at 1, 4, 8, and 25 credits per image, multiplied by outputCount; it defaults to medium with reference images and high otherwise.

Use the text to image endpoint to get started.

October 12th, 2026 - Ideogram 4.0 (ideogram_4_0) is now available on Runway Dev.

Generate images with legible typography from a prompt of up to 4,000 characters, or remix a single reference image, with outputCount from 1–4. ratio is one of nine 2K width:height sizes (2048:2048 by default, plus 2560:1440, 1440:2560, 2304:1728, 1728:2304, 2496:1664, 1664:2496, 3072:1280, 1280:3072). quality is low, medium (the default), or high, billed at 4, 7, and 11 credits per image, multiplied by outputCount.

Use the text to image endpoint to get started.

October 6th, 2026 - Nano Banana 2.1 (nano_banana_2.1) is now available on Runway Dev. Generate images from a prompt of up to 5,500 characters, with up to 14 reference images (optional prompt-referenceable tags) and outputCount from 1–4. ratio is a width:height size across 1K, 2K, and 4K — 42 sizes covering 14 aspect ratios (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1). thinkingLevel is minimal, medium (the default), or high. Billed at 4 credits per 1K image, 6 per 2K, and 12 per 4K, multiplied by outputCount. Use the text to image endpoint to get started.

October 1st, 2026 - Grok Imagine Video 1.5 Lite (grok_imagine_1_5_lite) is now available on Runway Dev

A faster, lower-cost version of Grok Imagine Video 1.5 for generating videos from text or a start-frame image. Text-to-video takes ratio as width:height sizes across 480p, 720p, and 1080p (for example 848:480, 1280:720, 1904:1072). Image-to-video uses a single first frame (promptImage) with ratio of auto_480p, auto_720p, or auto_1080p; output aspect ratio follows the input image. 1080p is rendered at 720p and upscaled. Durations are 1–15 seconds. Image and audio references are not supported — use grok_imagine_1_5 for those. Billed at 2 credits per second at 480p, 3 at 720p, and 14 at 1080p, plus 1 credit for an image-to-video start frame. Use the text to video and image to video endpoints to get started.

September 12th, 2026 - The hdr_exr_acescg_sequence_1_3 and hdr_exr_acescg_sequence_2_0 outputs of /v1/video_to_hdr are now built from the source plate: the plate brought into ACEScg through the inverse ACES SDR (Rec.709) Output Transform, with the highlight detail Ruby recovers added on top. Read with the stock ACES - ACEScg input transform, the ACES SDR view reproduces the source and the ACES HDR views render the same scene with the recovered highlights. Previously these sequences were the HDR10 picture inverted through the ACES 1000-nit Output Transform, which matched hdr10 in an HDR view but lifted midtones and desaturated the image in any SDR view. The colorimetry.json sidecar now records construction: plate-referenced. Gen-4.5 ACEScg outputs are unchanged.

September 11th, 2026 - Ruby now preserves the alpha channel of a source video on /v1/video_to_hdr. Sources with alpha (ProRes 4444, WebM with alpha, RGBA codecs) are detected automatically; no request parameter is needed. The EXR deliveries (hdr_exr_sequence, hdr_exr_acescg_sequence_1_3, hdr_exr_acescg_sequence_2_0) write the alpha as the A channel, and hdr_prores is delivered as ProRes 4444 regardless of proresProfile, the only tier with an alpha plane. The alpha is passed through unchanged and is not premultiplied. hdr10 and hlg cannot carry alpha and deliver the video without it. Pricing is unchanged.

September 8th, 2026 - OpenAI’s GPT Image 2.5 Flare (gpt_image_2_5_flare) and GPT Image 2.5 Sunburst (gpt_image_2_5_sunburst) are now available on Runway Dev. Both generate images from a prompt of up to 32,000 characters, accept up to 16 reference images (with optional prompt-referenceable tags), support 30 width:height ratios across 1K, 2K, and 4K tiers plus an auto resolution, and take outputCount from 1–10. quality is low, medium, high (the default), xhigh, or max. Sunburst can return transparent backgrounds with background: "transparent"; Flare supports opaque and auto only. Billed at 1–76 credits per image by quality and resolution, plus 1 credit per reference image per generated image. Use the text to image endpoint to get started.

September 3rd, 2026 - MiniMax H3 Max (h3_max) is now available on Runway Dev. Generate videos from a text prompt or a start-frame image, with an optional last-frame keyframe. Durations are 5–15 seconds at 480p or 768p. Use promptExpansionMode to keep the prompt as written (disabled), apply a short rewrite (balanced, the default), or spend extra time rewriting (quality). Billed at 5 credits per second at 480p and 8 credits per second at 768p. Use the text to video and image to video endpoints to get started.

August 31st, 2026

HDR outputs can now be delivered as scene-referred ACEScg OpenEXR sequences — in both ACES 1.3 and ACES 2.0 variants, with outputFormat: "hdr_exr_acescg_sequence_1_3" or outputFormat: "hdr_exr_acescg_sequence_2_0" matching your pipeline’s config version — on /v1/video_to_hdr and on Gen-4.5 HDR generations. The delivered picture is inverted through the matching ACES Output Transform (Rec.2100 PQ, 1000-nit) into the ACEScg working space, so the frames drop straight into ACES-configured comps: read them with the stock ACES - ACEScg input transform and your ACES viewing pipeline reproduces the delivered picture, with the same zip contract as hdr_exr_sequence (colorimetry and provenance sidecars, audio.wav when the source has audio) and the same 20 / 40 credits-per-second rate as the other HDR profiles.

August 26th, 2026 - WAN 3.0 (wan3) is now available on Runway Dev.

Generate up to 30 seconds of video with native audio from a text prompt or a start-frame image.

WAN 3.0 is built for reference-driven shots — pass images, video, or audio to keep characters and style consistent, or use first and last keyframes to lock the edit.

Output at 480p, 720p, or 1080p.

Billed at 5 credits per second at 480p, 10 at 720p, and 20 at 1080p.

Use the text to video and image to video endpoints to get started.