Runway • videoFeatured
Runway flagship video model with very high fidelity and strong creative control for professional visual teams.
Context Window
—
Input Price/1M
—
Output Price/1M
—
Parameters
—
Runway Gen-4.5 results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SWEN Video API Readiness | 93.0 | 100.0 | SWEN Video Registry v2026-06-22. Editorial multimodal ranking with modality-specific scoring based on product capability, control, speed, value and integration readiness. |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SWEN Video Control | 95.0 | 100.0 | SWEN Video Registry v2026-06-22. Editorial multimodal ranking with modality-specific scoring based on product capability, control, speed, value and integration readiness. |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SWEN Video Quality | 96.0 | 100.0 | SWEN Video Registry v2026-06-22. Editorial multimodal ranking with modality-specific scoring based on product capability, control, speed, value and integration readiness. |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SWEN Video Speed | 88.0 | 100.0 | SWEN Video Registry v2026-06-22. Editorial multimodal ranking with modality-specific scoring based on product capability, control, speed, value and integration readiness. |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SWEN Video Value | 78.0 | 100.0 | SWEN Video Registry v2026-06-22. Editorial multimodal ranking with modality-specific scoring based on product capability, control, speed, value and integration readiness. |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SWEN Video Composite | 94.4 | 100.0 | SWEN Video Registry v2026-06-22. Editorial multimodal ranking with modality-specific scoring based on product capability, control, speed, value and integration readiness. |
Runway Gen-4.5 is an AI model developed by Runway, classified as a video model. It is a multimodal model, capable of processing text, images, and potentially other media types. As a proprietary model, it is available via Runway's cloud API.
Runway Gen-4.5 does not have public per-token pricing available at this time. Some models offer access via enterprise plans or research programs. Check Runway's official website for up-to-date availability and pricing.
Runway Gen-4.5 was evaluated on 6 different benchmarks, covering categories like API Readiness, Control, Quality, Speed, Value, video. Results show exceptional performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Runway Gen-4.5 specializes in video, offering advanced capabilities for creating and processing video content.
In the 2026 AI model ecosystem, Runway Gen-4.5 competes directly with similarly capable models. Runway competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Runway flagship video model with very high fidelity and strong creative control for professional visual teams.
Runway Gen-4.5 does not have public per-token pricing available at this time. Check Runway's official website for up-to-date information.
In available benchmarks, Runway Gen-4.5 scored: SWEN Video API Readiness: 93/100, SWEN Video Control: 95/100, SWEN Video Quality: 96/100. See the full table above for a detailed comparison.
No, Runway Gen-4.5 is a proprietary model from Runway. It is available via cloud API. For open source alternatives, check our open source model ranking.
Runway Gen-4.5 excels at multimodal tasks including text and vision.
Last updated: June 22, 2026 • View methodology →