Google: Veo 3.1
google/veo-3.1
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to its OpenRouter catalog entry, google/veo-3.1 (canonical ID google/veo-3.1-20260320) is a Google video generation model that accepts text or image prompts and produces video output. The catalog describes it as aimed at high-fidelity production use, generating 1080p video with native synchronized audio, and lists sampling controls including temperature, top_p, seed, max_tokens and response_format. No independent model card or measured benchmark results were included in this source pack, so reported capabilities come from the catalog alone and real-world quality should be validated on your own workloads.[1]
Strengths
- Accepts both text and image inputs and produces video output, per the OpenRouter catalog modality listing.[1]
- The catalog reports 1080p video generation with native synchronized audio, positioned for final production cuts.[1]
- Exposes generation parameters including seed, temperature, top_p, max_tokens and response_format, which may aid reproducibility and output control.[1]
Limitations
- Evidence is catalog-only: an independent model card was not available in this source pack, so capability claims are vendor-reported rather than measured.[1]
- No benchmark scores or evaluation data were supplied; stated quality targets such as 1080p output and synchronized audio require workload-specific validation.[1]
- Context length, licensing terms, safety properties and hardware requirements are not documented in the evidence and remain unknown.[1]
Where to use it
- Editorially suggested for text-to-video generation of short clips for prototyping, storyboards or marketing drafts; evaluate output quality on your prompts.[1]
- May suit image-to-video animation where synchronized audio is desired, based on the catalog's reported capabilities; test before production use.[1]
- Potentially useful in pipelines needing seed-based reproducibility or structured response formats, given the listed supported parameters.[1]
Sources
- [1] OpenRouter catalog · Google: Veo 3.1Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —...
Specifications
- Model ID
- google/veo-3.1
- Canonical ID
- google/veo-3.1-20260320
- Creator
- Added to OpenRouter
- 23.03.2026
- Context length
- 0
- Modality
- text+image->video
- Input modalities
- text, image
- Output modalities
- video
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | output: video |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| 0 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026