Cosmos 3 Super API Pricing
fal_ai/nvidia/cosmos-3-super/text-to-image- Price
- $0.04 per image
As of November 21, 2026, Cosmos 3 Super costs $0.04 per image on fal.
Cosmos 3 Super pricing by provider
2 listings across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
What Cosmos 3 Super costs in practice
Generating 1,000 images
| fal | $40.00 |
Use Cosmos 3 Super with LiteLLM
Call Cosmos 3 Super through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/images/generations. LiteLLM tracks the cost of every request at these prices.
from litellm import image_generation
response = image_generation(
model="fal_ai/nvidia/cosmos-3-super/text-to-image",
prompt="A cute baby sea otter",
)model_list:
- model_name: cosmos-3-super
litellm_params:
model: fal_ai/nvidia/cosmos-3-super/text-to-image
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/images/generations \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "cosmos-3-super",
"prompt": "A cute baby sea otter",
"n": 1,
"size": "1024x1024"
}'Cosmos 3 Super price history
| Date | Price |
|---|---|
| November 10, 2026 | $0.05 per second |
| November 11, 2026 | $0.04 per image |
Cosmos 3 Super FAQ
How much does Cosmos 3 Super cost?
Cosmos 3 Super costs $0.04 per image on fal.
Which providers offer Cosmos 3 Super?
Cosmos 3 Super is available from fal through LiteLLM, using the model name fal_ai/nvidia/cosmos-3-super/text-to-image.
How do I call Cosmos 3 Super with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="fal_ai/nvidia/cosmos-3-super/text-to-image", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/images/generations from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
When did LiteLLM add Cosmos 3 Super?
Cosmos 3 Super was added to LiteLLM's model price file on November 10, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: fal.
Provider pages: fal.