All models

Gemini Nano Banana 2.1

新着 IteraCompute での提供開始日

オンライン

Google

gemini/gemini-nano-banana-2.1
Tool calling
非対応ツール呼び出し · 非対応
Reasoning
サポートされています推論 · サポートされています
Vision
サポートされていますビジョン · サポートされています
Streaming
サポートされていますストリーミング · サポートされています
JSON mode
非対応JSON モード · 非対応

USD / 1M tokens

Text input
$1.50
Image input
$1.50
Image output
$30.00
Text / thinking output
$7.50
Precision
公式精度
Price checked

Overview

Gemini Nano Banana 2.1 accepts text and reference images for image generation and editing. Use /v1/images/generations with prompt or Gemini contents. Streaming returns image progress and completed-image events, followed by total usage.

Version
gemini-nano-banana-2.1
Input / output
text, image / text, image
Endpoint
/v1/images/generations

API protocols and integration

Base URL · OpenAI SDK
https://api.iteracompute.com/v1
Authentication
Authorization: Bearer ITERACOMPUTE_API_KEY

Choose request fields, response parsing and stream completion by endpoint. This table describes wire formats; see this model's capabilities and verification scope.

Customer endpointModel statusInput / output budgetResultSSE completion
OpenAI Images · Generation
POST /v1/images/generations
Declared for this modelprompt; Gemini: contents / generationConfig
n (1–4); model-specific size and quality
data[].b64_json; usageimage_generation.completed
OpenAI Images · Editing
POST /v1/images/edits
Not declared; acceptance pendingmultipart: image[]; prompt; optional mask
n (1–4); size; quality
data[].b64_json; usageunsupported

Generation uses JSON; GPT image edits use multipart. Images are returned as base64 and billed by actual tokens.

View docs
LLMs.txt · Copy for an AI coding assistant

Includes this model's ID, wire formats and parameter constraints. Check this page's verification scope and current prices before use.

LLMs.txt
# IteraCompute · gemini/gemini-nano-banana-2.1

Model ID: gemini/gemini-nano-banana-2.1
Base URL (OpenAI SDK): https://api.iteracompute.com/v1
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY
Content-Type: application/json

Use only the customer endpoints below. Request and response formats differ by protocol. An endpoint declaration does not certify every capability.

## Images · Generation
POST https://api.iteracompute.com/v1/images/generations
Input: prompt; Gemini: contents / generationConfig
Output budget: n (1–4); model-specific size and quality
Read result: data[].b64_json; usage
SSE completion: image_generation.completed
Docs: https://iteracompute.com/docs.html#images-api

## Parameters
Configuration and parameter acceptance do not establish semantic capability. Do not invent undisclosed defaults.
Parameter revision: 1b7cb9c6eb26f5e2d8a02d03f6349b28b09ca8e1fc7afb60f79e69cd883556dd
Capability tools: disabled
Capability reasoning: configured enabled (see verification scope)
Capability vision: configured enabled (see verification scope)
Capability streaming: configured enabled (see verification scope)
Capability json_mode: disabled
Capability image_generation: configured enabled (see verification scope)
Capability image_editing: configured enabled (see verification scope)
- prompt: string; accepted; min=unknown; max=unknown; default=Undisclosed. Image instruction, 1–4000 UTF-8 bytes.
- n: integer; accepted; min=1; max=4; default=Undisclosed. Number of completions; many routes accept only 1.
- size: enum; accepted; values=["1024x1024"]; default=Undisclosed. Image dimensions; pixel and aspect limits also apply.
- response_format: enum; accepted; values=["b64_json"]; default=Undisclosed. Text: Chat output format. Images: b64_json only; not text JSON mode.
- stream: boolean; accepted; min=unknown; max=unknown; default=Undisclosed. Enable SSE streaming; completion markers depend on the protocol.
- contents: array; accepted; min=unknown; max=unknown; default=Undisclosed. Gemini native messages with text and inlineData reference images.
- systemInstruction: object; accepted; min=unknown; max=unknown; default=Undisclosed. Gemini image system instruction; text parts only.
- generationConfig: object; accepted; min=unknown; max=unknown; default=Undisclosed. Gemini image configuration: output token budget, image size/aspect and thinking. See model limits.
- safetySettings: array; accepted; min=unknown; max=unknown; default=Undisclosed. Gemini native image safety category settings.

## Images example · JSON body
```json
{
  "model": "gemini/gemini-nano-banana-2.1",
  "prompt": "A blue square on a white background",
  "n": 1,
  "size": "1024x1024",
  "response_format": "b64_json",
  "generationConfig": {
    "maxOutputTokens": 8192,
    "thinkingConfig": {
      "thinkingLevel": "MINIMAL"
    },
    "imageConfig": {
      "imageSize": "1K",
      "aspectRatio": "1:1"
    }
  }
}
```

## References
Model catalog: https://iteracompute.com/models/
Current prices and billing: https://iteracompute.com/pricing/
Documentation index: https://iteracompute.com/llms.txt
Unknown prices are not zero. Account and subscription limits also apply.
Never include a real API key in an LLM prompt or client-side code.

Open plain text

API parameters

  • response_format is b64_json. Gemini reference images use contents with inlineData on the generation endpoint.
  • Use thinkingConfig.thinkingLevel MINIMAL, MEDIUM or HIGH; existing LOW requests remain compatible. Reasoning tokens are billed as text output.
  • Text/image input: $1.50 per million tokens; text/reasoning output: $7.50; image output: $30. Actual supplier token usage determines the charge, rounded up to USD micros.
  • The official model context is not a promise of the same payload size on this image endpoint; the platform applies narrower request and image bounds.

These parameters and ranges describe the current route. Account and context limits also apply. Parameter acceptance does not establish model capability.

Tool calling
Unsupported
Reasoning
Supported
Vision
Supported
Streaming
Supported
JSON mode
Unsupported
Image generation
Supported
Image editing
Supported

Parameters and values

Click a parameter to copy its name; scroll the table horizontally to see all columns. Usage notes identify protocol differences; identical names do not guarantee cross-endpoint support.

ParameterTypeAcceptanceRangeUsage / protocol
stringAccepted—Image instruction, 1–4000 UTF-8 bytes.
integerAccepted[1, 4]Number of completions; many routes accept only 1.
enumAccepted["1024x1024"]Image dimensions; pixel and aspect limits also apply.
enumAccepted["b64_json"]Text: Chat output format. Images: b64_json only; not text JSON mode.
booleanAccepted—Enable SSE streaming; completion markers depend on the protocol.
arrayAccepted—Gemini native messages with text and inlineData reference images.
objectAccepted—Gemini image system instruction; text parts only.
objectAccepted—Gemini image configuration: output token budget, image size/aspect and thinking. See model limits.
arrayAccepted—Gemini native image safety category settings.

Current configuration example

POST /v1/images/generations

Image generation request
{
  "model": "gemini/gemini-nano-banana-2.1",
  "prompt": "A blue square on a white background",
  "n": 1,
  "size": "1024x1024",
  "response_format": "b64_json",
  "generationConfig": {
    "maxOutputTokens": 8192,
    "thinkingConfig": {
      "thinkingLevel": "MINIMAL"
    },
    "imageConfig": {
      "imageSize": "1K",
      "aspectRatio": "1:1"
    }
  }
}

Parameter revision:1b7cb9c6eb26

Technical reference (current configuration takes precedence)

APIパラメータ

パラメーター名をクリックしてコピーします。

gemini/gemini-nano-banana-2.1
[{"role": "user", "content": "Hello!"}]

このルートの追加機能とモデル固有パラメーターは未検証です。本番利用前に必要な機能をテストしてください。

パラメーターの参照

パラメーターの使用方法

  • 画像生成と編集、最大 14 枚の参照画像、1K・2K・4K 出力に対応します。関数呼び出しは非対応です。モデルページにストリーミング対応の記載はありません。

インターフェース参照の確認日: 2026-10-23

API

POST /v1/images/generations

import base64, json, os, urllib.request

body = json.loads("{\n  \"model\": \"gemini/gemini-nano-banana-2.1\",\n  \"prompt\": \"A blue square on a white background\",\n  \"n\": 1,\n  \"size\": \"1024x1024\",\n  \"response_format\": \"b64_json\",\n  \"generationConfig\": {\n    \"maxOutputTokens\": 8192,\n    \"thinkingConfig\": {\n      \"thinkingLevel\": \"MINIMAL\"\n    },\n    \"imageConfig\": {\n      \"imageSize\": \"1K\",\n      \"aspectRatio\": \"1:1\"\n    }\n  }\n}")
request = urllib.request.Request(
    "https://api.iteracompute.com/v1/images/generations",
    data=json.dumps(body).encode(),
    headers={"Authorization": "Bearer " + os.environ["ITERACOMPUTE_API_KEY"],
             "Content-Type": "application/json"},
)
with urllib.request.urlopen(request, timeout=1800) as response:
    result = json.load(response)
with open("generated.png", "wb") as image:
    image.write(base64.b64decode(result["data"][0]["b64_json"]))
print(result["usage"])

料金

これは公開カタログのテキストトークン料金です。画像生成は別途課金され、テキスト出力料金がゼロでも画像は無料ではありません。利用前にコンソールで画像料金とエンドポイントの提供状況を確認してください。

Text input$1.50
Image input$1.50
Image output$30.00
Text / thinking output$7.50

Token計算機は画像生成には適用されません。画像tokens、枚数、秒数、ツール料金には各公開単位と実際の用量が必要です。テキスト単価ゼロは無料画像を意味しません。

Version / Model ID
gemini/gemini-nano-banana-2.1gemini-nano-banana-2.1
Context
128K
Precision
公式精度
Price checked
Verification scope and sources
View verification scope and sources

2026-11-13 · Verified text-to-image, a blue-to-green reference edit with visual review, n=1 and n=4, streaming completion and cancellation, native usage with reasoning tokens, authentication, invalid parameters and wallet reconciliation. Final runtime accepts MINIMAL. Tests used 1K square output; full model context, other resolutions and broad image quality were not tested.

料金の出典: 公開 Models API · 価格と精度の根拠は個別に確認します。

キャッシュ読み取り料金は実際のヒットに適用されます。未掲載料金(—)は不明であり、ゼロではありません。アカウントと Gateway のコンテキスト制限は利用制限をご覧ください。

Usage limits

  • Tool calling and JSON structured output are unavailable on this image interface.
  • The compatibility size field accepts only 1024x1024; native resolution and aspect ratio use generationConfig.imageConfig.
  • The platform accepts 1–4 images per request, at most 4000 UTF-8 text bytes and four reference images within its request-size limits.
  • Only 1K square generation and editing were visually reviewed in this acceptance. Other resolutions, aspect ratios and image quality are not established by these results.

Use cases

Product and concept illustrations from text

Changes to a supplied image, such as color and composition

Image variations with explicit image settings

新着モデル

新着モデルに選ばれたモデルの API 料金、対応機能、連携ガイドをご覧ください。

新着モデルを見る
Google新着

Gemini 4 Hydrogen

gemini/gemini-4-hydrogen

Google Cloud lists Gemini 4 Hydrogen for fast coding assistance, multimodal input and high-volume text generation.

IteraCompute での提供開始日

入力
$1.50
出力
$7.50

USD / 100万トークン

OpenAI新着

GPT-6.2 Astra

openai/gpt-6.2-astra

OpenAI lists GPT-6.2 Astra for complex engineering and long-horizon reasoning.

IteraCompute での提供開始日

入力
$8.00
出力
$40.00

USD / 100万トークン