gemini-3-pro-image AI Image API

gemini-3-pro-image (Nano Banana Pro): Generate images, edit from references and iterate on visual designs through Flatkey. The request example uses Gemini contents/parts, not an interchangeable Images API payload.

Text to ImageReference-guided Image
Input /M
$2/ 1M tokens$2/ 1M tokens
Cache /M
$0.2/ 1M tokens$0.2/ 1M tokens
Output /M
$12/ 1M tokens$12/ 1M tokens
Provider
Google
Generator setup · Playground (edit before sign-up)

Input

PromptCheck more995 / 10000
Quick Prompts
Reference Images
Start generating

Output

Preview
Image preview

Generated with Image 2

Request summary

Endpoint
POST /v1beta/models/gemini-3-pro-image:generateContent
Model ID
gemini-3-pro-image
Aspect ratio
16:9
Resolution
1K

Preview only. Sign in to submit this request to Flatkey.

Request preview
{
  "model": "gemini-3-pro-image",
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Scene: On a small theater stage, a startled magician in black pulls a long rainbow cloth from a tall black trunk wrapped in more cloth. The audience is dim behind him, with red curtains and colored spotlights. Freeze the harmless reveal at the moment the fabric stretches between hand and trunk; preserve object weight, pose, and stage spacing. No readable words, logos, injury, or watermark.\n\nComposition and rendering: Deliver one 16:9 physical-comedy still at the described instant. Make the cause of the gag readable through body balance, grip and object spacing. Separate the reaction from the airborne props; retain believable gravity and contact points. Keep the face and important props sharp, with only restrained directional blur on fast edges. Preserve the stated lighting and room or stage layout.\n\nAvoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above."
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "TEXT",
      "IMAGE"
    ],
    "imageConfig": {
      "aspectRatio": "16:9",
      "imageSize": "1K"
    }
  }
}

gemini-3-pro-image API performance

gemini-3-pro-image API reliability and uptime

Live Flatkey request telemetry for gemini-3-pro-image appears here when enough production traffic is available.

Avg. provider uptime
80.7%
last 30 days
Latency
2.79s
last 30 days
Requests
88
30-day window
Successful inference trend

gemini-3-pro-image API activity

gemini-3-pro-image API usage and request activity

Track request volume and successful inference activity for gemini-3-pro-image over the latest reporting window.

Requests
88
30-day window
Latency
2.79s
last 30 days
Uptime
80.7%
last 30 days
Successful inference trendActivity

gemini-3-pro-image pricing

gemini-3-pro-image API pricing and billing

Read the current Flatkey input/output token rates in the price cards. A token rate is not a fixed per-image quote: image settings, reference inputs and generated output affect usage. Google direct prices and free allowances do not automatically apply to this route.

Flatkey price

Input /M

Live catalog model
$2/ 1M tokens$2/ 1M tokens
Input /M
$2/ 1M tokens$2/ 1M tokens
Cache /M
$0.2/ 1M tokens$0.2/ 1M tokens
Output /M
$12/ 1M tokens$12/ 1M tokens
Image input /M
$0.12/ 1M tokens$0.12/ 1M tokens
Try a prompt
Shared balance

Add credits

Add credits

Use the same Flatkey balance and API key across image, video, audio, and text models.

Model catalog
Model Type
Text to Image
API
/v1beta/models/gemini-3-pro-image:generateContent
Billing basis
1M tokens
Outputs
1

gemini-3-pro-image image generation: core capabilities

Google's gemini-3-pro-image route supports text · image. Catalog categories: Marketing.

Text to Image

Describe the subject, composition, lighting and any text to render. Keep output controls in the request fields rather than only in the prompt.

Reference image

Provide reference images and specify what to preserve and what to change. Use the reference limits shown in this page’s parameter matrix.

Outputs

Select only the aspect ratios and image sizes offered by this model’s Playground. Flash, Flash Lite and Pro do not share all output limits.

API

Keep the exact model ID and the contents/parts request shape shown below. Test a small request before connecting batch image jobs.

Compare

gemini-3-pro-image API comparison: capabilities and access

Compare the catalog facts for gemini-3-pro-image with the previous-generation baseline before changing your integration.

CapabilityPrevious generationgemini-3-pro-image
ProviderNot verified in this catalog snapshotGoogle
ModalitiesNot verified in this catalog snapshottext · image
ContextNot verified in this catalog snapshotContext window not listed in the catalog
EndpointNot verified in this catalog snapshot/v1beta/models/gemini-3-pro-image:generateContent
BillingNot verified in this catalog snapshot$2/$12 per 1M tokens

Choose the right request before you integrate

Review the supported workflows, live cost for the current setup, and the exact parameter contract used by Flatkey.

Live cost estimate

Calculated from the current Playground settings and the live catalog rate when a fixed unit price is available.

Current setup
1×
Live rate
$0.12
Estimated request
Variable usage pricing

The final charge follows the submitted request and your account group. Token-priced or tiered requests cannot be reduced to one fixed estimate.

Workflows and Model ID

Use only the workflows marked available. Flatkey keeps one public model ID while the request body selects the input workflow.

Available

Text to Image

Generate a new image from a text prompt and output controls.

Model ID
gemini-3-pro-image
Endpoint
/v1beta/models/gemini-3-pro-image:generateContent
Available

Reference-guided Image

Use reference images for edits, variations, or identity and composition guidance.

Model ID
gemini-3-pro-image
Endpoint
/v1beta/models/gemini-3-pro-image:generateContent

Parameter compatibility

These values come from the same model configuration used by the Playground and request preview.

aspect_ratioAspect ratio
Accepted

1:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 21:9

Default: 1:1
image_sizeSize
Accepted

1K · 2K · 4K

Default: 1K
imageReference limit
Accepted

4 files

Endpoint: /v1beta/models/gemini-3-pro-image:generateContent

From first test to production

Use the same request contract in the Playground and API, then handle validation, balance, task state, and output retrieval explicitly.

Request lifecycle

  1. 1

    Validate the model, prompt, references, and output settings.

  2. 2

    POST the image request with the documented fields.

  3. 3

    Read the generated output or asynchronous task result returned by the route.

  4. 4

    Store the generated file and request metadata in your own workflow.

Production checks

Parameter validation

Reject unsupported sizes, durations, ratios, formats, or reference counts before submitting.

Authentication and balance

Handle invalid keys, insufficient balance, rate limits, and account-group pricing separately.

Input or policy rejection

Surface the rejected prompt or asset clearly so the user can replace only the failing input.

Task failure or timeout

Keep the task ID, use bounded retries, and never treat a timeout as a successful generation.

Prompt library

gemini-3-pro-image image generation prompt examples

Start with a gemini-3-pro-image prompt for product and ecommerce images, then adjust the request fields shown in the playground.

Game UI interaction and equipment switching
Game UI interaction and equipment switching

Generated with Image 2

Scene: A 16:9 underwater game loadout screen on a sea floor. An armored diver stands on a circular pedestal holding a glowing cyan sword, with submerged ruins behind and a weapon-swap panel on the right. Lock the diver silhouette, sword, aquatic lighting, pedestal, and interface hierarchy for an exact equipment-switch frame. No readable words, logos, invented stats, or watermark. Composition and rendering: Deliver one 16:9 game-interface keyframe. Separate the character, held equipment and HUD into clear depth layers; keep slot spacing and icon scale consistent, with the selected item visually dominant. Preserve the scene-specific game art style. Let material edges catch the existing light without letting interface glow obscure the silhouette. Keep all equipment fully inside the frame. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.

Create similar
Live sports broadcast simulation
Live sports broadcast simulation

Generated with Image 2

Scene: A televised basketball frame shows a red-uniform player taking a jump shot while a white-uniform defender contests it in an indoor arena. Include the hoop, overhead lights, crowd blur, and abstract red-and-gray lower-third panels without readable text. Keep the broadcast angle, ball arc, uniforms, and player spacing coherent; no real teams, athletes, logos, or watermark. Composition and rendering: Deliver one 16:9 broadcast still at the decisive instant. Use coherent perspective for the playing surface and equipment, readable separation between competitors, and a softer crowd behind the action. Keep the principal subject sharp, with directional blur limited to fast extremities and spray. Preserve the specified broadcast angle and reserve overlay areas clear of the action. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.

Create similar
Brand TVC and seamless ecommerce showcase
Brand TVC and seamless ecommerce showcase

Generated with Image 2

Scene: A clear glass dropper bottle filled with pale gold serum stands on a white stone block in a warm cream room. Soft sunlight and large leaf shadows fall across the wall and the liquid, glass, metal collar, and surface catch subtle reflections. Preserve the bottle proportions and generous blank space; no readable branding, extra products, hands, or watermark. Composition and rendering: Deliver one 16:9 commercial product still. Keep the complete product silhouette inside generous crop-safe margins. Resolve edges, seams and material transitions precisely; shape highlights to describe volume without clipping bright surfaces or crushing dark details. Align reflections with the object and light source. Retain the stated camera angle and existing negative space; add no decorative props. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.

Create similar
Cinematic character and storyboard direction
Cinematic character and storyboard direction

Generated with Image 2

Scene: At a rain-wet historic train platform, a young traveler in a dark cap and coat holds a brown suitcase while a steam train waits under a long canopy. Warm lamps recede into the blue night and reflect on the platform. Hold the traveler profile, suitcase, train direction, and wide composition for a continuous storyboard. No readable signs, logos, or watermark. Composition and rendering: Deliver one 16:9 storyboard keyframe, not a collage or an action sequence. Separate foreground, character plane and background through the existing light and atmospheric depth. Keep the stated pose and eyelines readable, and retain environmental landmarks for continuity. Match the described photographic, illustrated or puppet medium; give fabric and surfaces texture appropriate to that medium. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.

Create similar
Comedy sketch and physical storytelling
Comedy sketch and physical storytelling

Generated with Image 2

Scene: On a small theater stage, a startled magician in black pulls a long rainbow cloth from a tall black trunk wrapped in more cloth. The audience is dim behind him, with red curtains and colored spotlights. Freeze the harmless reveal at the moment the fabric stretches between hand and trunk; preserve object weight, pose, and stage spacing. No readable words, logos, injury, or watermark. Composition and rendering: Deliver one 16:9 physical-comedy still at the described instant. Make the cause of the gag readable through body balance, grip and object spacing. Separate the reaction from the airborne props; retain believable gravity and contact points. Keep the face and important props sharp, with only restrained directional blur on fast edges. Preserve the stated lighting and room or stage layout. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.

Create similar
Historical photo restoration and revival
Historical photo restoration and revival

Generated with Image 2

Scene: A sepia archival photograph shows four workers weaving cloth on wooden looms inside a rustic workshop, with yarn baskets and bright hillside scenery through the windows. Restore the paper texture, faces without sharpening them into modern portraits, loom construction, period clothing, and gentle film wear. No modern objects, readable signage, logos, captions, or watermark. Composition and restoration: Deliver one 16:9 archival-style still. Preserve the original framing, period-specific construction and restrained tonal range; retain monochrome, sepia or faded color as described. Recover modest detail in faces, clothing and architecture without synthetic sharpening. Keep fine grain and authentic aging consistent across the frame; repair damage without replacing historical features. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.

Create similar

Why gemini-3-pro-image API

Why use gemini-3-pro-image through Flatkey?

Use one gateway for gemini-3-pro-image, account controls and the rest of your model catalog.

gemini-3-pro-image in one API

Keep the gemini-3-pro-image model id and endpoint explicit while using the same Flatkey key as other workloads.

Live catalog pricing

See the current gemini-3-pro-image billing dimensions before a request is sent, then confirm the final estimate in your account.

A practical model handoff

Test a gemini-3-pro-image prompt in the public playground and carry the same settings into an authenticated integration.

Usage and routing controls

Centralize keys, quotas and routing for gemini-3-pro-image without changing your application’s provider-facing workflow.

API

gemini-3-pro-image API

Four ways in, all on the same key and the same model catalog. Pick one to see a runnable example.

Call any model with an OpenAI-compatible API. Copy a ready-to-run example for your model and language.
Use the OpenAI SDK you already know — with Flatkey as the gateway.
Generate images and videos from your terminal. Let your AI assistant drive the workflow.
Connect your coding agent with one command, then use Flatkey from your existing projects.
curl https://router.flatkey.ai/v1beta/models/gemini-3-pro-image:generateContent \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{"model":"gemini-3-pro-image","contents":[{"role":"user","parts":[{"text":"Create a high-quality product image with gemini-3-pro-image: clean composition, precise lighting, strong subject focus, and realistic detail."}]}],"generationConfig":{"responseModalities":["TEXT","IMAGE"],"imageConfig":{"aspectRatio":"1:1","imageSize":"1K"}}}'
Docs

FAQ

gemini-3-pro-image API
pricing, features, and usage FAQs

Answers about gemini-3-pro-image pricing, capabilities, endpoint access and catalog limits.

What is gemini-3-pro-image used for?
gemini-3-pro-image (Nano Banana Pro): Generate images, edit from references and iterate on visual designs through Flatkey. The request example uses Gemini contents/parts, not an interchangeable Images API payload.
How is gemini-3-pro-image priced?
Input /M: $2; Cache /M: $0.2; Output /M: $12; Image input /M: $0.12. Read the current Flatkey input/output token rates in the price cards. A token rate is not a fixed per-image quote: image settings, reference inputs and generated output affect usage. Google direct prices and free allowances do not automatically apply to this route.
Which API endpoint calls gemini-3-pro-image?
POST /v1beta/models/gemini-3-pro-image:generateContent · gemini-3-pro-image
Does Flatkey expose every feature in Google’s model documentation?
No. Google’s model specifications and Flatkey’s routed request contract are different scopes. Use this page’s supported fields; do not infer access to search grounding, provider tools or every documented input type from the model name alone.