Runway AI Release Notes

August 20th, 2026

Ruby (ruby) is now available via the Runway API.

Convert any SDR video — uploads or generations from any model — into true HDR, delivered as 10-bit HEVC in HDR10 (outputFormat: "hdr10", the default) or HLG ("hlg") with BT.2020 signaling and measured HDR10 metadata, as a BT.2020 + PQ ProRes.mov editorial mezzanine ("hdr_prores"; tier selectable with proresProfile — 422, 422 HQ, or 4444, defaulting to 422 HQ), or as a .zip of half-float OpenEXR frames carrying the upconverted signal as linear BT.2020 light for compositing ("hdr_exr_sequence"; the zip includes colorimetry and provenance sidecars, plus audio.wav when the source has audio).

The conversion preserves the source’s own pixels and audio: brightness is extended into HDR headroom with a bounded, color-preserving grade, and nothing is re-rendered.

Inputs must be SDR (HDR-tagged videos are rejected), at most 40 seconds, and under 4096 pixels per side.

Billed at 20 credits per second, or 40 credits per second when the source is larger than 4 megapixels (roughly 4K).

Use the /v1/video_to_hdr endpoint to get started.

August 20th, 2026 - Gen-4.5 text to video and image to video can now deliver directly in HDR and post-production formats via outputFormat: hdr10 and hlg streaming HDR, sdr_rec709_10bit for 10-bit SDR grading, and mastering-grade hdr_pq_12bit_master (12-bit lossless), hdr_prores (ProRes 422 HQ), hdr_png_sequence (bit-exact 16-bit frames), and hdr_exr_sequence (half-float OpenEXR frames as linear BT.2020 light, compositor-native). HDR outputs are true HDR renders — graded into BT.2020 with measured HDR10 metadata — not tone-mapped afterward. Aleph 2.0 adds sdr_rec709_10bit for 10-bit SDR delivery; to deliver an Aleph edit in HDR, chain it through /v1/video_to_hdr. These formats are being enabled progressively per account. Non-mp4 formats add 5 credits per second for prores and png_sequence, or 20 credits per second for 10-bit and deeper profiles (including EXR), rising to 40 credits per second when the output is larger than 4 megapixels (roughly 4K). See Professional and HDR output formats to get started.

August 11th, 2026 - Grok Imagine Image 2 (grok_imagine_image_2) is now available via the Runway API.

Generate images from text with optional reference images, an edit mode for direct image editing or combining references, quality of low or medium (default medium), outputCount from 1–4, and fixed width:height ratios across 1K and 2K plus auto_1k and auto_2k.

Up to 3 reference images. Billed at 4–8 credits per image by quality and resolution, plus 1 credit per reference image charged once per request (not per output). Use the text to image endpoint to get started.

August 7th, 2026

Grok Imagine Video 1.5 (grok_imagine_1_5) is now available via the Runway API. Generate videos from text or a start-frame image with optional native audio, prompt-addressable image references, and audio references. Text-to-video supports ratio values 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3, with resolution of 480p, 720p, or 1080p (default 480p). Durations are 1–15 seconds. Up to 7 image references and 3 audio references (each 3–15 seconds); audio references require at least one image reference, and requests with image references are capped at 720p. Image-to-video uses a single first frame (promptImage); output aspect ratio follows the input image. Billed at 10 credits per second at 480p, 16 at 720p, and 29 at 1080p, plus 1 credit per image or audio reference (including an image-to-video start frame). Use the text to video and image to video endpoints to get started.

August 7th, 2026 - Seedance 2.5 (seedance2_5) is now available via the Runway API.

Generate cinematic videos from text, images, or video with optional generated audio, larger reference budgets, and durations from 4–30 seconds at 480p or 720p. Text-to-video can run from references alone (omit promptText when at least one image, video, or audio reference is provided). Video-to-video accepts mode: "reference" (default) or mode: "extend" — extend requires promptText and matches the input aspect ratio, so ratio may not be provided. Reference limits: up to 30 images, 10 videos, and 10 audio clips (combined reference video and audio duration must stay under 30 seconds; video-to-video reserves one video slot for promptVideo). Input videos must be at least 480p. At 480p, ratios 864:496 and 496:864 deliver standard 854×480 / 480×854 output rather than the literal pixel counts. Billed at 30 credits per second of output at 720p and 20 at 480p, plus 15 (720p) or 10 (480p) credits per second of input and reference video; reference images and audio are free. Minimum 80 credits per generation. Use the text to video, image to video, and video to video endpoints to get started.

August 5th, 2026 - Hailuo 3.0 (hailuo3) is now available via the Runway API. Generate videos from text, images, or video with support for keyframe control, reference images, reference videos, and reference audio. Hailuo 3.0 supports text-to-video, image-to-video, and video-to-video generation modes, with durations from 5–15 seconds and output at 768P or 2K. Billed at 10 credits per second at 768P and 15 credits per second at 2K, plus 2 credits per reference image; reference video is billed at the same per-second rate as output (capped at 15 seconds). Use the text to video, image to video, and video to video endpoints to get started.

July 28th, 2026 - Organizations on an enterprise plan can now export per-generation credit usage and audit log history for the Runway web app workspaces linked to their API project.

/v1/organization/webapp/usage returns one row per generation with the credits it cost, and /v1/organization/webapp/audit_logs returns audit entries that can be filtered by actions, actorEmails, and workspaceIds, with a companion endpoint for the full detail of a single event.

See the workspace reporting guide and the Organization API reference to get started.

July 23rd, 2026 - Model Router is now available in the Runway API.

Create a saved routing configuration once and reference it by configId to route video, image, and audio generations to the best model for your use case — the router filters to eligible models and selects one based on your optimization preference (cost, latency, or quality), so you never have to name a model. Configure model allow and deny lists and optional per-modality credit ceilings (video, image, audio), and preview routing decisions with dryRun before generating. See Model Routers and the Model Router API reference to get started.

July 10th, 2026 - Seedream 5.0 Lite (seedream5_lite) is now available via the Runway API. Generate images from text with optional reference images for multi-image fusion and interactive editing. Supports prompts up to 4,000 characters, up to 14 reference images, outputCount from 1–4, optional outputFormat (png or jpeg, default png), and 16 ratio values across 2K and 3K at eight aspect ratios (1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9). Billed at 4 credits per image at any resolution, multiplied by outputCount. Use the text to image endpoint to get started.

July 8th, 2026 - Seedream 5.0 Pro (seedream5_pro) is now available via the Runway API.

Generate images from text with optional reference images for multi-image fusion and interactive editing. Supports prompts up to 4,000 characters, up to 10 reference images, outputCount from 1–4, optional outputFormat (png or jpeg, default png), and 14 fixed ratio values across 1K and 2K at seven aspect ratios (1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3), plus auto_1k and auto_2k to let the model pick aspect ratio at a fixed resolution tier. Billed at 5 credits per 1K image and 9 credits per 2K image, multiplied by outputCount. Use the text to image endpoint to get started.