Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
Workload (per month)
Google: Nano Banana 2.1
timm/efficientnet_b3.ra2_in1k
Difference
Customer-support chatbot
50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens)
$263
n/a
—
RAG search over documents
20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens)
$255
n/a
—
Coding / tool-using agent
2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens)
Doesn't fit context
n/a
—
Batch summarisation
10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens)
$165
n/a
—
Long-document analysis
500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens)
Doesn't fit context
n/a
—
Capabilities side by side
Capability
Google: Nano Banana 2.1
timm/efficientnet_b3.ra2_in1k
What it lets you do
Tool / function calling
✓ Yes
—
call your APIs and run agent loops
Structured output (JSON schema)
✓ Yes
—
return JSON that validates against your schema
Reasoning / thinking mode
✓ Yes
—
spend extra tokens thinking before answering hard problems
Image input
✓ Yes
—
read screenshots, charts and scanned pages
Audio input
—
—
take speech or audio directly
File / PDF input
—
—
accept documents without your own parsing step
Image output
✓ Yes
✓ Yes
generate images, not just text
Built-in web search
✓ Yes
—
answer from live web results
Seed (reproducible sampling)
✓ Yes
—
repeat a generation for tests and evals
Log-probabilities
—
—
read token confidence for classification and scoring
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Price history
Google: Nano Banana 2.1: price unchanged since we started tracking it on 2026-10-07.
Which should you choose?
Choose Google: Nano Banana 2.1 if…
you need tool / function calling — to call your APIs and run agent loops; timm/efficientnet_b3.ra2_in1k does not advertise it
you need structured output (JSON schema) — to return JSON that validates against your schema; timm/efficientnet_b3.ra2_in1k does not advertise it
you need reasoning / thinking mode — to spend extra tokens thinking before answering hard problems; timm/efficientnet_b3.ra2_in1k does not advertise it
you need image input — to read screenshots, charts and scanned pages; timm/efficientnet_b3.ra2_in1k does not advertise it
you need built-in web search — to answer from live web results; timm/efficientnet_b3.ra2_in1k does not advertise it
you need seed (reproducible sampling) — to repeat a generation for tests and evals; timm/efficientnet_b3.ra2_in1k does not advertise it
Choose timm/efficientnet_b3.ra2_in1k if…
No advantage on the data we track — pick it for provider preference or output quality on your own prompts.
Frequently asked questions
Is Google: Nano Banana 2.1 better than timm/efficientnet_b3.ra2_in1k?
Google: Nano Banana 2.1 comes out ahead on the data we track: 6 advantages and none for timm/efficientnet_b3.ra2_in1k.
Do Google: Nano Banana 2.1 and timm/efficientnet_b3.ra2_in1k support function calling and JSON output?
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...