LiteLLMModels

V3 API Pricing

As of October 10, 2026, V3 costs $0.0398 per image on fal.

Model ID fal_ai/fal-ai/recraft/v3/text-to-imagePrices updated Checked
Per image
$0.0398
Providers
1
Added to LiteLLM
October 2025

V3 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.

ProviderModel name in LiteLLMPer imageContext
falfal_ai/fal-ai/recraft/v3/text-to-image$0.0398–
falfal_ai/fal-ai/ideogram/v3$0.06–

What V3 costs in practice

Generating 1,000 images

fal$39.80

Use V3 with LiteLLM

Call V3 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/recraft/v3/text-to-image",
    prompt="A cute baby sea otter",
)
Proxy config.yaml
model_list:
  - model_name: v3
    litellm_params:
      model: fal_ai/fal-ai/recraft/v3/text-to-image
      # 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 sk-1234" \
  -d '{
    "model": "v3",
    "prompt": "A cute baby sea otter",
    "n": 1,
    "size": "1024x1024"
  }'

V3 FAQ

How much does V3 cost?

V3 costs $0.0398 per image on fal.

Which providers offer V3?

V3 is available from fal through LiteLLM, using the model name fal_ai/fal-ai/recraft/v3/text-to-image.

How do I call V3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="fal_ai/fal-ai/recraft/v3/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 V3?

V3 was added to LiteLLM's model price file in October 2025.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.

LiteLLM docs: fal.

Provider pages: fal.