impulse

Nano Banana

Frontier labImage
API id nano-banana
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Where to run it

2 hosts serve Nano Banana. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
nano-banana
-
ReplicateInference
nano-banana
-

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
Text
Produces
Images

Similar models

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

Smaller Google models

Other frontier labs

Open-weight picks

No similar open-weight match.

Call it

Using fal's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Nano Banana?

Nano Banana runs on 2 APIs: fal and Replicate.

Is Nano Banana being retired?

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

What is Nano Banana's API model id?

Use nano-banana with fal.

Sources

Raw catalog entry for nano-banana on fal
{
  "litellm_provider": "fal_ai",
  "mode": "image_generation",
  "output_cost_per_image": 0.0398,
  "source": "https://fal.ai/models/fal-ai/nano-banana",
  "supported_endpoints": [
    "/v1/images/generations"
  ]
}