Runway
Developer of Gen-4 and Aleph, with an API offering Runway models alongside partner image, video and audio models.
Models on Runway 10
A curated selection, with links to other providers for the same model.
Explore imported models by type. Image and video categories refer to generation; image understanding is available under Vision.
Artificial Analysis Intelligence Index ↗ · Higher is better · Checked 2026-10-02
Rank among verified models in this catalog. Best published configuration per model; equal scores share a rank. Scores are rounded by the source. Unverified and non-language models appear last without a rank. Methodology ↗10 models
| Rank | Model | Intelligence | Best price | Input → output | Providers |
|---|---|---|---|---|---|
| — | Aleph 2Runway | —Not comparable | From $0.28USD / secondRunway aleph2 · Starting tariff; final cost depends on the selected settings. 28 credits per second (56 credit minimum per generation) Compare prices → | video, text, image → video | Runway |
| — |  Eleven Multilingual v2ElevenLabs | —Not comparable | From $0.08USD / 1,000 charactersElevenLabs Pay as you go · Starting tariff; final cost depends on the selected settings. Published pay-as-you-go character rate. Subscription allowances and taxes are separate. Compare prices → | text → audio | ElevenLabsRunway |
| — | Eleven Text to Sound v2ElevenLabs | —Not comparable | Price not collected | text → audio | Runway |
| — | Eleven v3ElevenLabs | —Not comparable | From $0.08USD / 1,000 charactersElevenLabs Pay as you go · Starting tariff; final cost depends on the selected settings. Published pay-as-you-go character rate. Subscription allowances and taxes are separate. Compare prices → | text → audio | ElevenLabsfal.aiRunway |
| — | Gen-4 ImageRunway | —Not comparable | From $0.05USD / imageRunway 720p · Starting tariff; final cost depends on the selected settings. 5 credits per 720p image, or 8 credits per 1080p image Compare prices → | text, image → image | Runway |
| — | Gen-4 Image TurboRunway | —Not comparable | From $0.02USD / imageRunway gen4_image_turbo · Starting tariff; final cost depends on the selected settings. 2 credits per image, any resolution Compare prices → | text, image → image | Runway |
| — | Gen-4 TurboRunway | —Not comparable | From $0.05USD / secondRunway gen4_turbo · Starting tariff; final cost depends on the selected settings. 5 credits per second Compare prices → | image → video | Runway |
| — | Gen-4.5Runway | —Not comparable | From $0.12USD / secondRunway gen4.5 · Starting tariff; final cost depends on the selected settings. 12 credits per second Compare prices → | text, image → video | Runway |
| — |  Nano Banana 2Google | —Not comparable | $0.5 in / $3 outUSD / 1M tokensOpenRouter Router catalog · Lowest listed input price; output is from the same tariff. OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Compare prices →From $0.067USD / imageReplicate target resolution=1K · Starting tariff; final cost depends on the selected settings. per output image Compare prices → | text, image, video, PDF → image, text | fal.aiGoogle Gemini APIOpenRouterReplicateRunway |
| — |  Veo 3.1Google | —Not comparable | From $0.2USD / secondRunway veo3.1 (no audio) · Starting tariff; final cost depends on the selected settings. 20 credits per second Compare prices → | text, image → video, audio | Google Gemini APIRunwayTogether AI |
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Benchmark scores are a dated snapshot, not a live feed or a universal measure of quality. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.