Observed Signal · Jun 18, 2026 · Technical Release · Source: DEV Community · Impact: 3/5 · Sentiment: Positive
Generate Veo 3.1 AI Video via Google Flow API
A technical guide explains how to generate AI video with Google’s Veo 3.1 models using a third-party Google Flow API provided by useapi.net. The article describes supported Veo models (veo-3.1-fast/quality/lite and omni-flash), credit/duration constraints, and a pricing model where users pay their normal Google Flow credits plus a flat $15/month useapi.net subscription rather than per-call Gemini API metering. It details a two-call asynchronous workflow (POST to create a job, GET to poll job status) that returns signed MP4 URLs (valid ~24 hours) and typical completion times (60–180s). The guide covers image-to-video (startImage/endImage), reference-to-video (up to 3 references on 8s clips; omni-flash supports more), automated batch generation via a Node.js script on GitHub, captcha handling via a built-in solver, and links to examples and code samples. Publication date: 2026-06-18.
The guide enables cheaper, automated access to Google’s Veo 3.1 video models via a subscription-driven Flow workflow, lowering per-clip cost and simplifying batch video asset generation—useful for teams producing short-form video creatives, though it is a third-party tutorial rather than an official platform policy or platform-level release.
Track Google Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- useapi.net provides a third-party Google Flow API that drives a user’s Google Flow account to access Veo 3.1 video models without a Google Cloud project.
- useapi.net charges a flat $15/month subscription for API access; video generations consume the user's Google Flow credits rather than per-second Gemini API billing.
- Supported Veo models include veo-3.1-lite, veo-3.1-fast (default), veo-3.1-quality, and omni-flash; durations and credit costs vary by model and tier.
- Generation workflow is asynchronous: POST https://api.useapi.net/v1/google-flow/videos returns a jobid and status, then GET https://api.useapi.net/v1/google-flow/jobs/{jobId} returns response.media[].videoUrl when completed (typical 60–180s).
- Image-to-video (startImage/endImage) and reference-to-video (referenceImage_1..3 on 8s clips) modes are supported; Omni Flash supports additional features (up to 7 references, 10s clips).
Connected Companies & Entities
6 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Google Unveils Veo 3.1: AI Video Enhancements
Google has released Veo 3.1, the successor to Veo 3, a generative AI video model designed to produce higher‑fidelity videos with audio and improved scene understanding. The update is delivered through Flow, which adds editing and composition options, including inserting reference images, and new features such as Frames to Video, Ingredients to Video, and Extend to lengthen clips. Veo 3.1 also enables object insertion and planned removal capabilities, aiming to deliver better image‑to‑video output and richer sound design. The rollout spans the Google Gemini ecosystem, including the Gemini App, Flow, Gemini API, Google AI Studio, and Vertex AI, with EU and Germany having access. Google positions Veo 3.1 as a response to OpenAI’s Sora 2, and example videos demonstrate diverse scenes from time‑lapse to day/night sequences. A free test is available with usage limits. The update broadens creator tooling for AI video generation across Google platforms.
Google Launches Veo 3.1 Lite, Cheaper AI Video
Google has released Veo 3.1 Lite, a lower-cost variant of its Veo 3.1 AI video generation model aimed at developers and creators. Veo 3.1 Lite is priced at $0.05 per second for 720p and $0.08 per second for 1080p (4K not available) and offers selectable durations (4, 6 or 8 seconds), flexible framing (16:9 and 9:16), and support for text-to-video and image-to-video workflows. Google says Lite matches the speed of the existing Veo 3.1 Fast tier and is available via the Gemini API and Google AI Studio; templates and integrations (including Nano Banana) simplify creative production. The launch is positioned in the context of OpenAI’s recent shutdown of its Sora video product, with Google signalling continued investment in making video generation more accessible. Google DeepMind staff also indicated further updates are planned.
Developer Builds Lightweight AI Video Tool with Veo 3.1 Lite
A developer describes building VeoLite, a minimalist AI video generator, after Google released Veo 3.1 and the lower-cost Veo 3.1 Lite APIs. The author says the Lite APIs lowered cost and inference time, making text-to-video and image-to-video workflows practical for solo developers and small projects. VeoLite focuses on fast iteration and a simple UI (no complex editing or timelines). The post highlights lessons: small, focused use-cases, speed over perfection, and simplicity. Remaining limitations include inconsistent generation quality, limited prompt control, and unpredictable outputs. The author frames the experiment as evidence that accessible video-generation APIs enable rapid prototyping by individuals.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.