Gemini API image APIs - verified October 18, 2026

Gemini API image generation API pricing

Google (Gemini API): 5 image models with 24 price rows, priced per image and per 1M image tokens, read from the provider's own pages on October 18, 2026. 1 model is retiring or retired: gemini-2.5-flash-image (retiring 2027-03-15).

Read from ai.google.dev. Compare every image generation API

Models: 5
Price rows: 24
Active: 4
Retiring or retired: 1

What Gemini API's pricing page says

Imagen is no longer available on the Gemini API (imagen-4.0-* shut down 2026-08-17)
“Imagen is shut down and no longer available through the Gemini API.”
ai.google.dev

Models

Gemini Nano Banana 2.1

gemini-nano-banana-2.1

Current

Prices (provider's own wording)

$30 per 1,000,000 image output tokens (Standard); $15 per 1,000,000 (Batch)
Per 1M image tokens - Standard and Batch
Batch rate
Image output tokens
“Image output is priced at $30 per 1,000,000 tokens (Standard) and $15 per 1,000,000 tokens (Batch).”
ai.google.dev
$1.50 per 1M input tokens (text/image/video)
Text and input tokens
Input tokens
“| Input price | Not available | $1.50 (text/image/video) |”
ai.google.dev
$0.0336 per 1K (1024x1024) image
Per image - 1K - Standard
Per image 1K, Standard
“Output images at 1K (1024x1024px) consume 1120 tokens and are equivalent to $0.0336 per image.”
ai.google.dev
$0.0504 per 2K (2048x2048) image
Per image - 2K - Standard
Per image 2K, Standard
“Output images at 2K (2048x2048px) consume 1680 tokens and are equivalent to $0.0504 per image.”
ai.google.dev
$0.113 per 4K (4096x4096) image
Per image - 4K - Standard
Per image 4K, Standard
“Output images at 4K (4096x4096px) consume 3780 tokens and are equivalent to $0.113 per image.”
ai.google.dev
$0.0168 per 1K image (Batch)
Per image - 1K - Batch
Batch rate
Per image 1K, Batch
“Equivalent to $0.0168 per 1K image”
ai.google.dev

Status: GA (released 2026-10-06; no shutdown date)
“| gemini-nano-banana-2.1 | October 6, 2026 | No shutdown date announced |”
ai.google.dev
Max resolution: 4K (4096x4096 at 1:1)
“| 1:1 | 1024x1024 | 1120 | 2048x2048 | 1680 | 4096x4096 | 2520 |”
ai.google.dev
Editing: Yes
“built for high-efficiency image generation and conversational editing with improved visual quality, multi-turn character consistency, accurate text rendering”
ai.google.dev
Image input: Up to 4 characters and up to 10 objects
“gemini-nano-banana-2.1 and gemini-3.1-flash-image support character resemblance of up to 4 characters and the fidelity of up to 10 objects in a single workflow.”
ai.google.dev
Text rendering: accurate text rendering (provider claim)
“built for high-efficiency image generation and conversational editing with improved visual quality, multi-turn character consistency, accurate text rendering”
ai.google.dev

The provider's pages disagree about this model: its status, note or deprecations row says how.

Pricing page says a 4K image consumes 3780 tokens; the image generation guide's Nano Banana 2.1 table lists 2520 tokens at 4K. Free tier: not available.

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

gemini-3.1-flash-lite-image

Current

Prices (provider's own wording)

$30 per 1,000,000 image output tokens
Per 1M image tokens - Standard
Image output tokens
“Image output is priced at $30 per 1,000,000 tokens. Output images at 1K (1024x1024px) consume 1120 tokens and are equivalent to $0.0336 per image.”
ai.google.dev
$0.0336 per 1K resolution image
Per image - 1K - Standard
Per image 1K, Standard
“Equivalent to $0.0336 per 1K resolution image”
ai.google.dev
$0.0168 per 1K resolution image (Batch)
Per image - 1K - Batch
Batch rate
Per image 1K, Batch
“Equivalent to $0.0168 per 1K resolution image”
ai.google.dev

Status: GA (released 2026-06-30; no shutdown date)
“| gemini-3.1-flash-lite-image | June 30, 2026 | No shutdown date announced |”
ai.google.dev
Max resolution: 1K only
“Gemini 3.1 Flash Lite Image only supports 1K resolution.”
ai.google.dev
Editing: Yes
“Designed as the efficiency specialist of the image generation family, the Gemini 3.1 Flash Lite Image model is designed for ultra-low latency and cost-effective image generation and editing.”
ai.google.dev
Image input: Supported but not optimized for multiple references
“Not optimized for multiple reference inputs or multi-turn sequential editing.”
ai.google.dev
Text rendering: Not stated

Gemini 3.1 Flash Image (Nano Banana 2)

gemini-3.1-flash-image

Legacy

Deprecations tracker: deprecated, no shutdown date, replacement gemini-nano-banana-2.1. No shutdown date announced; the deprecations page names a recommended replacement while the models page still lists it as stable. See the row

Prices (provider's own wording)

$60 per 1,000,000 image output tokens
Per 1M image tokens - Standard
Image output tokens
“Image output is priced at $60 per 1,000,000 tokens.”
ai.google.dev
$0.045 per 0.5K (512px) image
Per image - 0.5K - Standard
Per image 0.5K, Standard
“Output images at 0.5K (512px) consume 747 tokens and are equivalent to $0.045 per image.”
ai.google.dev
$0.067 per 1K (1024x1024) image
Per image - 1K - Standard
Per image 1K, Standard
“Output images at 1K (1024x1024px) consume 1120 tokens and are equivalent to $0.067 per image.”
ai.google.dev
$0.101 per 2K (2048x2048) image
Per image - 2K - Standard
Per image 2K, Standard
“Output images at 2K (2048x2048px) consume 1680 tokens and are equivalent to $0.101 per image.”
ai.google.dev
$0.151 per 4K (4096x4096) image
Per image - 4K - Standard
Per image 4K, Standard
“Output images at 4K (4096x4096px) consume 2520 tokens and are equivalent to $0.151 per image.”
ai.google.dev
$0.034 per 1K image (Batch)
Per image - 1K - Batch
Batch rate
Per image 1K, Batch
“$0.034 per 1K image”
ai.google.dev

Status: GA, superseded (replacement named, no shutdown date)
“| gemini-3.1-flash-image | May 28, 2026 | No shutdown date announced | gemini-nano-banana-2.1 |”
ai.google.dev
Max resolution: 512px to 4K
“Gemini 3 image models generate 1K images by default but can also output 2K, 4K, and 512px (05.K) (Gemini 3.1 Flash Image only) images.”
ai.google.dev
Editing: Not stated
Image input: Up to 4 characters and up to 10 objects
“gemini-nano-banana-2.1 and gemini-3.1-flash-image support character resemblance of up to 4 characters and the fidelity of up to 10 objects in a single workflow.”
ai.google.dev
Text rendering: Not stated

The provider's pages disagree about this model: its status, note or deprecations row says how.

Recommended replacement is gemini-nano-banana-2.1, which costs half per image output token.

Gemini 3 Pro Image (Nano Banana Pro)

gemini-3-pro-image

Current

Prices (provider's own wording)

$120 per 1,000,000 image output tokens
Per 1M image tokens - Standard
Image output tokens
“Image output is priced at $120 per 1,000,000 tokens.”
ai.google.dev
$0.134 per 1K to 2K image
Per image - 1K/2K - Standard
Per image 1K/2K, Standard
“Output images from 1024x1024px (1K) and up to 2048x2048px (2K) consume 1120 tokens and are equivalent to $0.134 per image.”
ai.google.dev
$0.24 per 4K image
Per image - 4K - Standard
Per image 4K, Standard
“Output images up to 4096x4096px (4K) consume 2000 tokens and are equivalent to $0.24 per image.”
ai.google.dev
$0.067 per 1K/2K image (Batch)
Per image - 1K/2K - Batch
Batch rate
Per image 1K/2K, Batch
“$0.067 per 1K/2K image”
ai.google.dev
$0.12 per 4K image (Batch)
Per image - 4K - Batch
Batch rate
Per image 4K, Batch
“$0.12 per 4K image”
ai.google.dev
$0.0011 per input image (560 tokens)
Per input image - Image input
Image input
“Image input is set at 560 tokens or $0.0011 per image.”
ai.google.dev

Status: GA (released 2026-05-28; no shutdown date)
“| gemini-3-pro-image | May 28, 2026 | No shutdown date announced |”
ai.google.dev
Max resolution: 4K (up to 4096x4096)
“Output images up to 4096x4096px (4K) consume 2000 tokens and are equivalent to $0.24 per image.”
ai.google.dev
Editing: Not stated
Image input: 5 high-fidelity images, up to 14 total
“gemini-3-pro-image supports 5 images with high fidelity, and up to 14 images in total.”
ai.google.dev
Text rendering: legible, stylized text (family-level claim)
“Advanced text rendering: Capable of generating legible, stylized text for infographics, menus, diagrams, and marketing assets.”
ai.google.dev

Retired or retiring

Shut down, or scheduled to within six months. Dates are cross-checked against our deprecations tracker.

Gemini 2.5 Flash Image (Nano Banana)

gemini-2.5-flash-image

Retiring 2027-03-15

Deprecations tracker: shutdown 2027-03-15, replacement gemini-3.1-flash-lite-image. See the row

Prices (provider's own wording)

$0.039 per image (up to 1024x1024)
Per image - Up to 1024x1024 - Standard
Per image, Standard
“Output images up to 1024x1024px consume 1290 tokens and are equivalent to $0.039 per image.”
ai.google.dev
$0.0195 per image (Batch)
Per image - Up to 1024x1024 - Batch
Batch rate
Per image, Batch
“| Output price | Not available | $0.0195 per image* |”
ai.google.dev
$0.30 per 1M input tokens (text / image)
Text and input tokens
Input tokens
“| Input price | Not available | $0.30 (text / image) |”
ai.google.dev

Status: retiring 2027-03-15
“| gemini-2.5-flash-image | October 2, 2025 | March 15, 2027 | gemini-3.1-flash-lite-image |”
ai.google.dev
Max resolution: 1024x1024 at 1:1
“| 1:1 | 1024x1024 | 1290 |”
ai.google.dev
Editing: Not stated
Image input: Works best with up to 3 input images
“gemini-2.5-flash-image works best with up to 3 images as input”
ai.google.dev
Text rendering: Not stated

Imagen 4 imagen-4.0-generate-001No longer priced; replacement gemini-nano-banana-2.1.Retired 2026-08-17
Imagen 4 Ultra imagen-4.0-ultra-generate-001No longer priced; replacement gemini-nano-banana-2.1.Retired 2026-08-17
Imagen 4 Fast imagen-4.0-fast-generate-001No longer priced; replacement gemini-nano-banana-2.1.Retired 2026-08-17

FAQ

How much does Gemini API image generation cost?

Gemini Nano Banana 2.1: $30 per 1,000,000 image output tokens (Standard); $15 per 1,000,000 (Batch) (Standard and Batch). Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite): $30 per 1,000,000 image output tokens (Standard). Gemini 3.1 Flash Image (Nano Banana 2): $60 per 1,000,000 image output tokens (Standard). Gemini 3 Pro Image (Nano Banana Pro): $120 per 1,000,000 image output tokens (Standard). Gemini 2.5 Flash Image (Nano Banana): $0.039 per image (up to 1024x1024) (Up to 1024x1024, Standard). Each is the first price the provider lists for the model, in its own unit, as of October 18, 2026; the model cards list every size and quality.

Which Gemini API image models are retiring?

gemini-2.5-flash-image: retiring 2027-03-15, replacement gemini-3.1-flash-lite-image.

Sources

Source: ai.google.dev/gemini-api/docs/image-generation
Source: ai.google.dev/gemini-api/docs/deprecations
Source: ai.google.dev/gemini-api/docs/pricing

Verified 2026-10-18 from each provider's own pricing pages and image docs; every quote was string-matched against the page that day. Prices are shown in the provider's own unit and never converted between units. Retirement dates are cross-checked against our deprecations tracker. Prices change without notice; check the linked source before you commit a budget to one.

Newsletter

One email per week. New model releases, pricing changes and what they mean for what you build.

What Gemini API's pricing page says

Models

Prices (provider's own wording)

Prices (provider's own wording)

Prices (provider's own wording)

Prices (provider's own wording)

Retired or retiring

Prices (provider's own wording)

FAQ

How much does Gemini API image generation cost?

Which Gemini API image models are retiring?

Sources

Know when an image API changes its prices