The Orchestrator › Models › Google
Google: Gemini Omni Flash Preview
Gemini Omni Flash (Preview) is a multimodal model designed for video, image, and text tasks. It is optimized for video generation, offering video output alongside text responses in a single model.
Specifications
| Provider | |
| Model ID | google/gemini-omni-flash-preview |
| Context window | 1M tokens (1,000,000) |
| Modalities | text + image + pdf + video → text + video |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2026-06-30 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | google/gemini-omni-flash-preview | $1.50 | $9.00 | 1M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.50 | $9.00 | 1M |
Capabilities
Vision (image input)Video inputStructured outputs1M+ context windowControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, reasoning, include_reasoning, response_format, structured_outputs