impulse

Gemini Omni Flash V1.2 Upscale

Frontier labVideo
API id upscale
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

1 host serve Gemini Omni Flash V1.2 Upscale. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
upscale
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Video
Produces
Video

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Google models

No similar Google model keeps its key capabilities.

Other frontier labs

No similar match from another frontier lab.

Open-weight picks

No similar open-weight match.

Call it

Using fal's API.

Python
from litellm import completion

response = completion(
    model="fal_ai/upscale",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Gemini Omni Flash V1.2 Upscale?

Gemini Omni Flash V1.2 Upscale runs on 1 API: fal.

Is Gemini Omni Flash V1.2 Upscale being retired?

No retirement date is scheduled for it on any API we track.

What is Gemini Omni Flash V1.2 Upscale's API model id?

Use upscale with fal.

Sources

Raw catalog entry for upscale on fal
{
  "litellm_provider": "fal_ai",
  "metadata": {
    "comment": "per second of upscaled output video by target resolution; the 1080p tier and output_cost_per_second take the higher source-dependent rate ($0.0819 from a 360p source) because the catalog selects by target resolution alone and the source resolution has no field, so a 720p source upscaled to 1080p ($0.041 per second) is overcounted, the same convention as fal_ai/blackforestlabs/flux-video-upscale"
  },
  "mode": "video_generation",
  "output_cost_per_second": 0.0819,
  "output_cost_per_second_1080p": 0.0819,
  "output_cost_per_second_4k": 0.1638,
  "output_cost_per_second_720p": 0.041,
  "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/upscale",
  "supported_endpoints": [
    "/v1/videos"
  ],
  "supported_modalities": [
    "video"
  ],
  "supported_output_modalities": [
    "video"
  ]
}