gen4

gen4 is a frontier-tier language model from Runway. gen4 is a proprietary model available exclusively through Runway's API. The Gen-4 family is Runway's model series for this capability tier.

gen4 is priced at $0.1 per second. This is a video model billed per second rather than per token — token input/output pricing does not apply.

Its 0-token context window is standard for this tier — adequate for most chat and completion tasks, but may require chunking for long-document workloads. Median latency (P50 time-to-first-token) is approximately 90000ms — better suited to batch or async workloads where latency is less critical.

gen4 is best suited to video-generation, quality, cinematic. Supported capabilities include vision inputs (images alongside text). Vision support enables document analysis, screenshot understanding, diagram interpretation, and visual question answering — images are converted to tokens at the standard input rate based on resolution. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how gen4 compares to similar models across these dimensions.

gen4 sits in the frontier tier — the highest-capability models available, used when quality is the primary constraint and cost is secondary. Unlike open-weights alternatives, gen4 is only available via Runway's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing gen4 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (0/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.