LiteLLMLiteLLM/ MODELS

Sana API Pricing

1 providerfal_ai/fal-ai/sana
Price
$0.001 per image

As of November 21, 2026, Sana costs $0.001 per image on fal.

Prices updated Checked

Sana pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Sana prices by provider in US dollars, token prices per 1M tokens, as of November 21, 2026. Source: LiteLLM model price file.
ProviderModel name in LiteLLMPer imageContext
falfal_ai/fal-ai/sana$0.001–

What Sana costs in practice

Generating 1,000 images

fal$1.00

Use Sana with LiteLLM

Call Sana 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.

Python SDK
from litellm import image_generation

response = image_generation(
    model="fal_ai/fal-ai/sana",
    prompt="A cute baby sea otter",
)
Proxy config.yaml
model_list:
  - model_name: sana
    litellm_params:
      model: fal_ai/fal-ai/sana
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "sana",
    "prompt": "A cute baby sea otter",
    "n": 1,
    "size": "1024x1024"
  }'

Sana FAQ

How much does Sana cost?

Sana costs $0.001 per image on fal.

Which providers offer Sana?

Sana is available from fal through LiteLLM, using the model name fal_ai/fal-ai/sana.

How do I call Sana with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="fal_ai/fal-ai/sana", 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 Sana?

Sana 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.