Runway Gen-4 Turbo API: Pricing, Specs, How to Access

Runway Gen-4 is the AI video generator Runway released on March 31, 2025. Give it one input image and a text prompt and it returns a 5- or 10-second 720p video at 24fps, with the character and scene consistency that made it Runway's breakout model. It is no longer the newest model in the lineup (Gen-4.5 took that spot in December 2025), but Gen-4 Turbo is still the cheapest image-to-video model on Runway's API. This post covers what Gen-4 does, how Runway bills it, how to call the Runway API, and which comparable models you can call pay-per-use today.

TL;DR: Runway Gen-4 is image-to-video only: one input image plus a text prompt in, a 5- or 10-second 720p video at 24fps out. In Runway's app it is billed in credits that come with a monthly plan; on Runway's developer API you buy credits directly, and Gen-4 Turbo costs well under half as much per second as the newer Gen-4.5. Runway models are not available on UnificAlly. The closest live alternatives here are Veo 3.1, Kling 3.0, SeeDance 2.0, and Wan 2.6, all pay-per-use with no subscription.

What is Runway Gen-4?

Gen-4 launched on March 31, 2025 as Runway's flagship video model, with the faster Gen-4 Turbo following days later. Its selling point was consistency: keep the same character, object, or location across separate generations from a single reference image, with no fine-tuning. That solved the biggest complaint about AI video at the time, and it is why "runway gen 4" is still one of the most-searched video model names in 2026.

The model is strictly image-to-video. Every generation starts from a required input image that becomes the first frame, and the text prompt should describe the motion, not the scene. There is no text-to-video mode on Gen-4; that arrived with Gen-4.5.

A few things around the edges: outputs can be upscaled to 4K as a separate action in the app, a fixed seed setting reproduces similar motion across runs, and Gen-4 outputs video without sound. Audio is a separate tool in Runway's suite, not part of the generation.

The Gen-4 family also covers two related tools. Gen-4 References handles consistent characters and objects in image generation (the API model gen4_image takes reference images). Act-Two is performance capture: record yourself acting and drive a character with your movement and expression.

Runway Gen-4 Turbo release date and features: where it stands in 2026

The short version for anyone searching "runway gen-4 turbo release date": Gen-4 shipped on March 31, 2025 and Gen-4 Turbo followed in early April 2025 as the faster, cheaper version of the same model. There has been no new Gen-4 Turbo release in 2026. Runway's help center now files Gen-4 under its older generation, and the 2026 additions to Runway's API have been other models (Gen-4.5 in December 2025, Aleph 2.0, and third-party models such as Kling 2.5 Turbo Pro, added to Runway Dev on October 13, 2026 per Runway's release notes).

What Gen-4 Turbo does, from Runway's spec sheets and help articles:

• Same inputs as Gen-4: one required image plus a text prompt describing the motion, 5 or 10 seconds, 720p class across six aspect ratios, 24fps, silent output.
• Speed: Runway positions Turbo as the model for quickly iterating ideas, and third-party hosts report a 5 second clip in roughly 30 seconds, about five times faster than base Gen-4 (Segmind's listing).
• Cost in credits: well under half of base Gen-4 per second, which is why it remains the model Runway recommends for drafts.
• API name: gen4_turbo, the only Gen-4 route on dev.runwayml.com; base Gen-4 is app-only.
• What it lacks against 2026 models: no text-to-video, no native audio, no reference images beyond the first frame, no 4K without a separate upscale.

Runway Gen-4 Turbo vs Veo 3.1 vs Kling 4.0

The two pay-per-use video APIs people search alongside Gen-4 Turbo. Runway's column is from its public specs; the other two are live on UnificAlly, with our rates.

What the alternative gives you: a real image-to-video test

To make the comparison concrete we ran a Gen-4-style job, one product image plus a motion prompt, on Veo 3.1 Lite Relaxed through the UnificAlly MCP on October 19, 2026. The start frame came from Grok Imagine 1.0 Image ($0.01); the video cost $0.075.

• Start frame prompt (Grok Imagine 1.0 Image, 16:9): "Product photo of a matte black wireless over-ear headphone on a walnut desk beside a steaming ceramic mug, warm morning window light from the left, shallow depth of field, photorealistic".
• Video prompt (Veo 3.1 Lite Relaxed, 720p, 4 s, 16:9, seed 66363): "Slow dolly-in on the headphones as steam rises from the mug, morning light shifts gently across the desk, the headphones rotate a few degrees on their stand. Cinematic product shot. AUDIO: quiet room tone, soft ceramic clink."

The steam animates continuously and the window light shifts across the four seconds, with the product, desk and framing held exactly as in the still, which is the first-frame fidelity Gen-4 is known for. The dolly-in is barely perceptible and the headphones never rotate, so Lite Relaxed treated the hero object as locked. For a product shot that is the safe failure; for a turntable move, state it as the only motion and move to Fast.

Is Gen-4 still Runway's latest model?

No. Runway announced Gen-4.5 on December 1, 2025, and its help center now files Gen-4 under "an older generation" of models. At launch, Gen-4.5 topped the crowd-voted Video Arena leaderboard, ahead of Google's Veo and OpenAI's Sora 2 Pro.

The practical differences, from Runway's own spec sheets:

• Gen-4.5 does text-to-video. No input image needed, 16:9 at 720p. Image-to-video works too, across the same six aspect ratios as Gen-4.
• Flexible durations. 2 to 10 seconds, against Gen-4's fixed 5 or 10.
• Same in-app price as base Gen-4. It costs the same credits per second, with a Standard plan or higher required in the app.
• Better motion and prompt following. Gen-4.5 handles sequenced instructions in one prompt: camera choreography, timed events, atmosphere changes.

So why would anyone still use Gen-4? One reason: Gen-4 Turbo costs well under half as many credits per second as Gen-4.5, and it is still the model Runway recommends for testing ideas before spending on a final pass. For video-to-video editing, Runway's current answer is Aleph 2.0. On UnificAlly, the editing models are HappyHorse 1.0 Video Edit for reference-image swaps and restyles, and the Kling O1 Edit API when you also need to change the aspect ratio.

Runway Gen-4 pricing: credits and plans

Runway bills everything in credits. In the app, credits come bundled with a subscription. On the developer API, you buy them directly at a flat rate per credit.

The app plans are Free (a one-time credit grant), Standard, Pro, Max, and Enterprise; current prices and monthly credit allowances are on runway.com/pricing. Max replaced the old Unlimited plan, which Runway now labels legacy. Extra credits can be bought on any paid plan, and they do not expire.

Per second, base Gen-4 and Gen-4.5 cost the same number of credits, and Gen-4 Turbo costs well under half of that. Base Gen-4 is app-only; on the API you get Gen-4 Turbo and Gen-4.5. Because a plan's credits are spent per second of output, a ten-second video costs twice a five-second one on every model.

Does Runway have an API?

Yes. The developer platform lives at dev.runwayml.com, with docs at docs.dev.runwayml.com. It runs on its own credit purchases; no subscription needed. Note that base Gen-4 is app-only. On the API, the Gen-4 route is gen4_turbo.

Runway's own models on the API:

The same API also carries third-party models under Runway's credit system (Veo 3.1, SeeDance 2, Hailuo 3, ElevenLabs audio, and others), at higher per-second rates than Runway's own models.

Official SDKs are @runwayml/sdk for Node and runwayml for Python. A Gen-4 Turbo call looks like this:

from runwayml import RunwayML

client = RunwayML()  # reads RUNWAYML_API_SECRET

task = client.image_to_video.create(
    model="gen4_turbo",
    prompt_image="https://example.com/first-frame.jpg",
    prompt_text="Slow dolly-in as the subject turns toward the window",
    ratio="1280:720",
    duration=5,
).wait_for_task_output()

print(task.output)

Generation is asynchronous: the API returns a task, and the SDK helper polls until the video is ready. API keys are issued in the developer portal after sign-up.

Runway Gen-4 vs alternatives you can call today

Runway's models are not available on UnificAlly, and we are not going to pretend otherwise. To call Gen-4 or Gen-4.5, go through Runway's own API or app as described above.

If what you want is strong image-to-video billed pay-per-use, with no subscription and no credit packs, these are the closest models live on UnificAlly today:

• Veo 3.1: up to 8 seconds, 720p to 4K, with synchronized dialogue, ambient sound, and effects generated in the same call. From $0.075 per video. Gen-4 outputs silent video, so native audio is the clearest capability gap.
• Kling 3.0: multi-shot generation with 2 to 6 scenes per call, 3 to 15 seconds single-shot, a 4K mode, and lip-sync. From $0.0756 per second.
• SeeDance 2.0: up to 9 image, video, and audio references against Gen-4's single input image, 4 to 15 seconds, up to 4K on Pro, with Mini and Fast at 480p or 720p. The Mini variant starts at $0.022 per second.
• Wan 2.6: text-, image-, or reference-to-video with up to 5 references, 720p or 1080p, 2 to 15 seconds, with automatic audio. The Flash variant starts at $0.0175 per second at 720p.

All four run through one API key with pay-per-use billing and no monthly fee. New accounts start with a $0.50 balance; on video models that covers only a few seconds, so treat it as a smoke test rather than a trial. Live rates for every model are on the pricing page, and the full catalog is at /models.

Runway Gen-4 Turbo FAQ

How much does Runway Gen-4 cost?

Runway bills Gen-4 in credits per second of output, and Gen-4 Turbo costs well under half as many credits as base Gen-4. In the app, credits come with a monthly plan; on Runway's API you buy them directly, and only Gen-4 Turbo is available there. Runway lists current plan and credit prices at runway.com/pricing.

Is Runway Gen-4 free?

Partly. Runway's Free plan includes a one-time credit grant, enough for a handful of short Gen-4 Turbo videos, and it does not refill monthly. After that you need a paid plan or API credits.

What is the difference between Gen-4 and Gen-4 Turbo?

Same task, same specs. Turbo generates faster and costs well under half as many credits per second as Gen-4. Runway recommends drafting in Turbo and switching to Gen-4 only when Turbo's results fall short. The API offers only the Turbo version, as gen4_turbo.

Does Runway Gen-4 do text-to-video?

No. Gen-4 and Gen-4 Turbo require an input image that becomes the first frame; the prompt describes the motion. For text-to-video from Runway, use Gen-4.5, which generates 16:9 720p video from a prompt alone.

What resolution is Runway Gen-4?

720p class, in six aspect ratios: 1280×720, 720×1280, 960×960, 1104×832, 832×1104, and 1584×672, all at 24fps. The app can upscale a finished video to 4K as a separate step.

Was Runway Gen-4 Turbo updated in 2026?

No. Gen-4 Turbo is the April 2025 model, unchanged; Runway's 2026 work went into Gen-4.5, Aleph 2.0 and hosting third-party models on its API. It remains available as gen4_turbo and as the draft model in the app.

How good is Runway Gen-4 in 2026?

Still strong on its one job, first-frame consistency from a single image, and dated everywhere else: no text-to-video, no audio, 720p class output. Runway's own help center files it under its older generation and points new work at Gen-4.5. If you need image-to-video with sound today, Veo 3.1 and Kling 4.0 do it pay-per-use; the test above shows what that looks like.

Which AI video model is the most realistic?

By crowd vote, it changes monthly. On the Arena image-to-video board as of June 2026, Seedance 2.0 led, with Gemini Omni Flash 1.1 and Grok Imagine 1.5 Video next, ahead of every Veo 3.1 variant; Runway's Gen-4.5 topped the Video Arena at its December 2025 launch. Treat any ranking as a snapshot and run your own prompt on two or three models before choosing.

Can I use the Runway API without a subscription?

Yes. The developer API at dev.runwayml.com bills its own credits, bought directly, with no plan required. Subscriptions only cover the app at runway.com.

We will update this post when Runway changes API credit rates, when Gen-4.5's promised additional input types arrive, or if Gen-4 Turbo leaves the API. If Runway models ever come to UnificAlly, this comparison section is where we will say so.