Nano Banana 2 is Google’s Gemini 3.1 Flash Image model for native image generation and conversational editing. Its design emphasises efficient visual creation and repeated revisions. The documented API profile accepts text, images, video and PDF and returns image and text. It is a distinct named edition from Gemini Nano Banana 2.1, rather than a label for every later Nano Banana update.
Output sizes include 0.5K, 1K, 2K and 4K, with 1K as the default. The smaller 0.5K option is specific to this profile and can suit an initial composition; the larger tiers supply more pixels for the selected output shape. The documented ratios cover square, portrait and landscape formats, including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, with additional 1:4, 4:1, 1:8 and 8:1 formats. For example, square outputs range from 512 × 512 at 0.5K to 4096 × 4096 at 4K. Choose the shape for the intended placement before refining small details.
Google identifies improved aspect-ratio adherence, visual consistency and multilingual text rendering among this edition’s updates. Use exact wording for a poster, menu or infographic and define which label belongs to which object. For small text or a long passage, the model card reports remaining legibility limitations, especially at 1K. Keep captions concise and make their relative size explicit; for dense body text, treat the image as a visual layout reference and check the actual lettering carefully.
Up to 14 reference images can be combined in a workflow. The image guide describes fidelity for up to ten objects and resemblance for up to four characters. Label the references and specify what each one supplies. For a product scene, one image can establish the object, another the environment and another the lighting. For a character sequence, carry previous outputs into the next prompt and state the features that must persist across a change in view or pose.
Web Search and Image Search grounding can inform generation with current information and retrieved visual references. Image Search adds visual context rather than merely a written description of the search result. The manufacturer supports the search feature across the documented thinking settings. Its image-search workflow excludes real-world images of people as search-derived references and returns attribution metadata with grounded results; preserve that metadata when using the result in an application.
The documented thinking controls for Gemini 3.1 Flash Image are minimal and high, with minimal as the default. This differs from the three-level, medium-default profile of Nano Banana 2.1. Thinking supports more complex composition and instruction handling. The model is based on Gemini 3 Flash, but that relationship does not turn it into a general code-execution or function-calling model: those capabilities are marked unsupported on this image edition’s table.
Conversational editing supports changing a supplied image or refining an earlier generation. A concrete brief can say: “Keep the bottle shape, label text and camera angle. Replace the background with a light stone surface and add softer shadows.” Describe preserved elements as carefully as changed ones. The model card notes that character consistency, left/right localisation and doodle-based edits can remain imperfect, so compare those particular details before continuing a visual sequence.
The API model table gives 131,072 input tokens and 32,768 output tokens. It supports image generation, search grounding, thinking and batch processing, while audio generation, caching, structured outputs, file search, Live API and URL context are unsupported. The image workflow does not accept audio input. Video or PDF can inform a still-image task in this API profile; the output remains image and text. Generated images include SynthID, and the requested count of images is not always followed exactly.
For a practical infographic, supply approved labels, the intended audience, reading order, reference material and a target ratio. Ask for one clear visual explanation, then use the next turn to correct wording or spacing while preserving the established composition. For a product mockup, specify geometry, surface, light and the visual details that define the product. The useful result is an image with its associated text that can be inspected, selected and refined in a controlled sequence.
", "aboutText": "Nano Banana 2 is Google’s Gemini 3.1 Flash Image model for native image generation and conversational editing. Its design emphasises efficient visual creation and repeated revisions. The documented API profile accepts text, images, video and PDF and returns image and text. It is a distinct named edition from Gemini Nano Banana 2.1, rather than a label for every later Nano Banana update.\n\nOutput sizes include 0.5K, 1K, 2K and 4K, with 1K as the default. The smaller 0.5K option is specific to this profile and can suit an initial composition; the larger tiers supply more pixels for the selected output shape. The documented ratios cover square, portrait and landscape formats, including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, with additional 1:4, 4:1, 1:8 and 8:1 formats. For example, square outputs range from 512 × 512 at 0.5K to 4096 × 4096 at 4K. Choose the shape for the intended placement before refining small details.\n\nGoogle identifies improved aspect-ratio adherence, visual consistency and multilingual text rendering among this edition’s updates. Use exact wording for a poster, menu or infographic and define which label belongs to which object. For small text or a long passage, the model card reports remaining legibility limitations, especially at 1K. Keep captions concise and make their relative size explicit; for dense body text, treat the image as a visual layout reference and check the actual lettering carefully.\n\nUp to 14 reference images can be combined in a workflow. The image guide describes fidelity for up to ten objects and resemblance for up to four characters. Label the references and specify what each one supplies. For a product scene, one image can establish the object, another the environment and another the lighting. For a character sequence, carry previous outputs into the next prompt and state the features that must persist across a change in view or pose.\n\nWeb Search and Image Search grounding can inform generation with current information and retrieved visual references. Image Search adds visual context rather than merely a written description of the search result. The manufacturer supports the search feature across the documented thinking settings. Its image-search workflow excludes real-world images of people as search-derived references and returns attribution metadata with grounded results; preserve that metadata when using the result in an application.\n\nThe documented thinking controls for Gemini 3.1 Flash Image are minimal and high, with minimal as the default. This differs from the three-level, medium-default profile of Nano Banana 2.1. Thinking supports more complex composition and instruction handling. The model is based on Gemini 3 Flash, but that relationship does not turn it into a general code-execution or function-calling model: those capabilities are marked unsupported on this image edition’s table.\n\nConversational editing supports changing a supplied image or refining an earlier generation. A concrete brief can say: “Keep the bottle shape, label text and camera angle. Replace the background with a light stone surface and add softer shadows.” Describe preserved elements as carefully as changed ones. The model card notes that character consistency, left/right localisation and doodle-based edits can remain imperfect, so compare those particular details before continuing a visual sequence.\n\nThe API model table gives 131,072 input tokens and 32,768 output tokens. It supports image generation, search grounding, thinking and batch processing, while audio generation, caching, structured outputs, file search, Live API and URL context are unsupported. The image workflow does not accept audio input. Video or PDF can inform a still-image task in this API profile; the output remains image and text. Generated images include SynthID, and the requested count of images is not always followed exactly.\n\nFor a practical infographic, supply approved labels, the intended audience, reading order, reference material and a target ratio. Ask for one clear visual explanation, then use the next turn to correct wording or spacing while preserving the established composition. For a product mockup, specify geometry, surface, light and the visual details that define the product. The useful result is an image with its associated text that can be inspected, selected and refined in a controlled sequence.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Create a simple bicycle-care infographic\n\nCreate one portrait infographic teaching three bicycle checks before a short ride: tires, brakes and chain. Use three large illustrated steps in that order, a warm ivory background and dark green accents. Include only these headings: 'TIRES', 'BRAKES', 'CHAIN'. Leave generous space around each heading and keep the illustrations clearly separated.One portrait image with three ordered illustrated steps and the three exact, readable headings.Inspect the rendered image for heading spelling, order and clear separation of the three checks.gemini-3.1-flash-imageNano Banana 2 (Gemini 3.1 Flash Image) generates and edits images in a conversation. It supports text and visual sources, 0.5K–4K output, reference-image composition and search grounding for product scenes, infographics and iterative visual work.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nano Banana 2 is Google’s Gemini 3.1 Flash Image model for native image generation and conversational editing. Its design emphasises efficient visual creation and repeated revisions. The documented API profile accepts text, images, video and PDF and returns image and text. It is a distinct named edition from Gemini Nano Banana 2.1, rather than a label for every later Nano Banana update.
Output sizes include 0.5K, 1K, 2K and 4K, with 1K as the default. The smaller 0.5K option is specific to this profile and can suit an initial composition; the larger tiers supply more pixels for the selected output shape. The documented ratios cover square, portrait and landscape formats, including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, with additional 1:4, 4:1, 1:8 and 8:1 formats. For example, square outputs range from 512 × 512 at 0.5K to 4096 × 4096 at 4K. Choose the shape for the intended placement before refining small details.
Google identifies improved aspect-ratio adherence, visual consistency and multilingual text rendering among this edition’s updates. Use exact wording for a poster, menu or infographic and define which label belongs to which object. For small text or a long passage, the model card reports remaining legibility limitations, especially at 1K. Keep captions concise and make their relative size explicit; for dense body text, treat the image as a visual layout reference and check the actual lettering carefully.
Up to 14 reference images can be combined in a workflow. The image guide describes fidelity for up to ten objects and resemblance for up to four characters. Label the references and specify what each one supplies. For a product scene, one image can establish the object, another the environment and another the lighting. For a character sequence, carry previous outputs into the next prompt and state the features that must persist across a change in view or pose.
Web Search and Image Search grounding can inform generation with current information and retrieved visual references. Image Search adds visual context rather than merely a written description of the search result. The manufacturer supports the search feature across the documented thinking settings. Its image-search workflow excludes real-world images of people as search-derived references and returns attribution metadata with grounded results; preserve that metadata when using the result in an application.
The documented thinking controls for Gemini 3.1 Flash Image are minimal and high, with minimal as the default. This differs from the three-level, medium-default profile of Nano Banana 2.1. Thinking supports more complex composition and instruction handling. The model is based on Gemini 3 Flash, but that relationship does not turn it into a general code-execution or function-calling model: those capabilities are marked unsupported on this image edition’s table.
Conversational editing supports changing a supplied image or refining an earlier generation. A concrete brief can say: “Keep the bottle shape, label text and camera angle. Replace the background with a light stone surface and add softer shadows.” Describe preserved elements as carefully as changed ones. The model card notes that character consistency, left/right localisation and doodle-based edits can remain imperfect, so compare those particular details before continuing a visual sequence.
The API model table gives 131,072 input tokens and 32,768 output tokens. It supports image generation, search grounding, thinking and batch processing, while audio generation, caching, structured outputs, file search, Live API and URL context are unsupported. The image workflow does not accept audio input. Video or PDF can inform a still-image task in this API profile; the output remains image and text. Generated images include SynthID, and the requested count of images is not always followed exactly.
For a practical infographic, supply approved labels, the intended audience, reading order, reference material and a target ratio. Ask for one clear visual explanation, then use the next turn to correct wording or spacing while preserving the established composition. For a product mockup, specify geometry, surface, light and the visual details that define the product. The useful result is an image with its associated text that can be inspected, selected and refined in a controlled sequence.
POST /v1/images/generationstextimage, text| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3.1-flash-image | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default1 |
Fieldresponse_format | Typestring | RequirementOptional | Values & limits url, b64_json | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldsize | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldquality | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldbackground | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldoutput_format | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldoutput_compression | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmoderation | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinput_fidelity | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstyle | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldpartial_images | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Text to image · Required: prompt
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext |
Parameterrequired | Contractmodel, prompt |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/images/generationsAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationUltra | Rate scheduleBase rate | Charge Input · Input tokens $0.0010000 / 1K tokens Output · Output tokens $0.006000 / 1K tokens Output · image output $0.12000 / 1K tokens Output · web search $0.028 per web search |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-3.1-flash-image", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nfrom openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\n\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Set your actual UTF-8 image brief file")\nrequest={'model': 'gemini-3.1-flash-image', 'prompt': ''}\nrequest["prompt"]=f.read_text(encoding="utf-8")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.images.generate(**request)\nPath("sdk-result.txt").write_text(str(result),encoding="utf-8")\nsave_images([{"b64_json":getattr(item,"b64_json",None),"url":getattr(item,"url",None)} for item in result.data])\nimport OpenAI from "openai";\nimport { readFileSync, writeFileSync } from "node:fs";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error("Set your actual Ailoot API key");\nconst client=new OpenAI({baseURL:"https://api.ailoot.ai/v1",apiKey:key,maxRetries:0});\nconst request={"model": "gemini-3.1-flash-image", "prompt": ""};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error("Set your actual UTF-8 image brief file");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,"utf8");\nconst result=await client.images.generate(request);\nwriteFileSync("sdk-result.json",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error("No completed images");\nfor(let index=0;index<result.data.length;index++) {\n const item=result.data[index];let encoded=item.b64_json,uri=item.url||"",raw;\n if(!encoded && uri.startsWith("data:image/")) {\n const comma=uri.indexOf(",");if(comma<0 || !uri.slice(0,comma).includes(";base64")) throw new Error("Unsupported image data URI");\n encoded=uri.slice(comma+1);\n }\n if(encoded) {\n if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error("Invalid Base64");\n raw=Buffer.from(encoded,"base64");\n } else if(uri) {\n const u=new URL(uri,"https://api.ailoot.ai");\n if(u.protocol!=="https:" || u.username || u.password) throw new Error("Invalid returned URL");\n const owned=u.origin==="https://api.ailoot.ai" && u.pathname.startsWith("/v1/media/assets/") && u.pathname.endsWith("/content");\n const response=await fetch(u,{headers:owned?{Authorization:"Bearer "+key}:{},redirect:"manual"});\n if(!response.ok) throw new Error("Image content download failed: "+response.status);\n raw=Buffer.from(await response.arrayBuffer());\n } else throw new Error("Image has neither bytes nor URL");\n if(!raw.length) throw new Error("Empty image result");\n const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?"png":raw[0]===255&&raw[1]===216?"jpg":raw.toString("ascii",0,4)==="RIFF"&&raw.toString("ascii",8,12)==="WEBP"?"webp":raw.toString("utf8").trimStart().startsWith("<svg")||raw.toString("utf8").trimStart().startsWith("<?xml")?"svg":"bin";\n writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log("Every returned image saved; sdk-result.json retains complete metadata");\nDownload each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Save every completed image; retrieve each returned URL or decode its Base64 contents.
Save every data item. Decode each b64_json or fetch every returned signed URL. Select a filename extension from the actual MIME/bytes.
If an image generation or edit result requires a check, keep the original operation_id/X-Client-Request-ID and returned result information. Recover existing owned results through the media library using actual task_id or asset_id values. Do not resubmit the generation/edit request or construct a polling URL from operation_id.
| Field | Type |
|---|---|
Fieldcreated | Typeinteger |
Fielddata[].url | Typestring |
Fielddata[].b64_json | Typebase64 string |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Ailoot gemini-3.1-flash-image
Ailoot Ultra google/gemini-3.1-flash-image
/v1/images
google/gemini-3.1-flash-imageNano Banana 2 (Gemini 3.1 Flash Image) generates and edits images in a conversation. It supports text and visual sources, 0.5K–4K output, reference-image composition and search grounding for product scenes, infographics and iterative visual work.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nano Banana 2 is Google’s Gemini 3.1 Flash Image model for native image generation and conversational editing. Its design emphasises efficient visual creation and repeated revisions. The documented API profile accepts text, images, video and PDF and returns image and text. It is a distinct named edition from Gemini Nano Banana 2.1, rather than a label for every later Nano Banana update.
Output sizes include 0.5K, 1K, 2K and 4K, with 1K as the default. The smaller 0.5K option is specific to this profile and can suit an initial composition; the larger tiers supply more pixels for the selected output shape. The documented ratios cover square, portrait and landscape formats, including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, with additional 1:4, 4:1, 1:8 and 8:1 formats. For example, square outputs range from 512 × 512 at 0.5K to 4096 × 4096 at 4K. Choose the shape for the intended placement before refining small details.
Google identifies improved aspect-ratio adherence, visual consistency and multilingual text rendering among this edition’s updates. Use exact wording for a poster, menu or infographic and define which label belongs to which object. For small text or a long passage, the model card reports remaining legibility limitations, especially at 1K. Keep captions concise and make their relative size explicit; for dense body text, treat the image as a visual layout reference and check the actual lettering carefully.
Up to 14 reference images can be combined in a workflow. The image guide describes fidelity for up to ten objects and resemblance for up to four characters. Label the references and specify what each one supplies. For a product scene, one image can establish the object, another the environment and another the lighting. For a character sequence, carry previous outputs into the next prompt and state the features that must persist across a change in view or pose.
Web Search and Image Search grounding can inform generation with current information and retrieved visual references. Image Search adds visual context rather than merely a written description of the search result. The manufacturer supports the search feature across the documented thinking settings. Its image-search workflow excludes real-world images of people as search-derived references and returns attribution metadata with grounded results; preserve that metadata when using the result in an application.
The documented thinking controls for Gemini 3.1 Flash Image are minimal and high, with minimal as the default. This differs from the three-level, medium-default profile of Nano Banana 2.1. Thinking supports more complex composition and instruction handling. The model is based on Gemini 3 Flash, but that relationship does not turn it into a general code-execution or function-calling model: those capabilities are marked unsupported on this image edition’s table.
Conversational editing supports changing a supplied image or refining an earlier generation. A concrete brief can say: “Keep the bottle shape, label text and camera angle. Replace the background with a light stone surface and add softer shadows.” Describe preserved elements as carefully as changed ones. The model card notes that character consistency, left/right localisation and doodle-based edits can remain imperfect, so compare those particular details before continuing a visual sequence.
The API model table gives 131,072 input tokens and 32,768 output tokens. It supports image generation, search grounding, thinking and batch processing, while audio generation, caching, structured outputs, file search, Live API and URL context are unsupported. The image workflow does not accept audio input. Video or PDF can inform a still-image task in this API profile; the output remains image and text. Generated images include SynthID, and the requested count of images is not always followed exactly.
For a practical infographic, supply approved labels, the intended audience, reading order, reference material and a target ratio. Ask for one clear visual explanation, then use the next turn to correct wording or spacing while preserving the established composition. For a product mockup, specify geometry, surface, light and the visual details that define the product. The useful result is an image with its associated text that can be inspected, selected and refined in a controlled sequence.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-flash-image | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Image output tokens $0.12 / 1K image tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationGoogle: Nano Banana 2 (Gemini 3.1 Flash Image) · Default configuration | Billing conditionsDefault configuration | Charge Input · Input tokens $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Output · Output image $0.12 / 1K tokens Output · Web search $0.028 per search |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "google/gemini-3.1-flash-image", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='google/gemini-3.1-flash-image',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='google/gemini-3.1-flash-image',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.1-flash-image
Ailoot Ultra google/gemini-3.1-flash-image
/v1/images
google/gemini-3.1-flash-imageNano Banana 2 (Gemini 3.1 Flash Image) generates and edits images in a conversation. It supports text and visual sources, 0.5K–4K output, reference-image composition and search grounding for product scenes, infographics and iterative visual work.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nano Banana 2 is Google’s Gemini 3.1 Flash Image model for native image generation and conversational editing. Its design emphasises efficient visual creation and repeated revisions. The documented API profile accepts text, images, video and PDF and returns image and text. It is a distinct named edition from Gemini Nano Banana 2.1, rather than a label for every later Nano Banana update.
Output sizes include 0.5K, 1K, 2K and 4K, with 1K as the default. The smaller 0.5K option is specific to this profile and can suit an initial composition; the larger tiers supply more pixels for the selected output shape. The documented ratios cover square, portrait and landscape formats, including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, with additional 1:4, 4:1, 1:8 and 8:1 formats. For example, square outputs range from 512 × 512 at 0.5K to 4096 × 4096 at 4K. Choose the shape for the intended placement before refining small details.
Google identifies improved aspect-ratio adherence, visual consistency and multilingual text rendering among this edition’s updates. Use exact wording for a poster, menu or infographic and define which label belongs to which object. For small text or a long passage, the model card reports remaining legibility limitations, especially at 1K. Keep captions concise and make their relative size explicit; for dense body text, treat the image as a visual layout reference and check the actual lettering carefully.
Up to 14 reference images can be combined in a workflow. The image guide describes fidelity for up to ten objects and resemblance for up to four characters. Label the references and specify what each one supplies. For a product scene, one image can establish the object, another the environment and another the lighting. For a character sequence, carry previous outputs into the next prompt and state the features that must persist across a change in view or pose.
Web Search and Image Search grounding can inform generation with current information and retrieved visual references. Image Search adds visual context rather than merely a written description of the search result. The manufacturer supports the search feature across the documented thinking settings. Its image-search workflow excludes real-world images of people as search-derived references and returns attribution metadata with grounded results; preserve that metadata when using the result in an application.
The documented thinking controls for Gemini 3.1 Flash Image are minimal and high, with minimal as the default. This differs from the three-level, medium-default profile of Nano Banana 2.1. Thinking supports more complex composition and instruction handling. The model is based on Gemini 3 Flash, but that relationship does not turn it into a general code-execution or function-calling model: those capabilities are marked unsupported on this image edition’s table.
Conversational editing supports changing a supplied image or refining an earlier generation. A concrete brief can say: “Keep the bottle shape, label text and camera angle. Replace the background with a light stone surface and add softer shadows.” Describe preserved elements as carefully as changed ones. The model card notes that character consistency, left/right localisation and doodle-based edits can remain imperfect, so compare those particular details before continuing a visual sequence.
The API model table gives 131,072 input tokens and 32,768 output tokens. It supports image generation, search grounding, thinking and batch processing, while audio generation, caching, structured outputs, file search, Live API and URL context are unsupported. The image workflow does not accept audio input. Video or PDF can inform a still-image task in this API profile; the output remains image and text. Generated images include SynthID, and the requested count of images is not always followed exactly.
For a practical infographic, supply approved labels, the intended audience, reading order, reference material and a target ratio. Ask for one clear visual explanation, then use the next turn to correct wording or spacing while preserving the established composition. For a product mockup, specify geometry, surface, light and the visual details that define the product. The useful result is an image with its associated text that can be inspected, selected and refined in a controlled sequence.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-flash-image | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldresolution | Typestring | RequirementOptional | Values & limits 512, 1K, 2K, 4K | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9 | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 1 | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 14 | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parametermaterial_types | Contracttext, image |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge Output · Estimated generation cost · Estimate for comparison only $0.49152 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'google/gemini-3.1-flash-image', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nDownload each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\nSave every completed image; retrieve each returned URL or decode its Base64 contents.
Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.
Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.
| Field | Type |
|---|---|
Fieldcreated | Type |
Fielddata[].url | Type |
Fielddata[].b64_json | Type |
Fieldusage | Type |
Ailoot gemini-3.1-flash-image
Ailoot Ultra google/gemini-3.1-flash-image
/v1/images
google/gemini-3.1-flash-imageNano Banana 2 (Gemini 3.1 Flash Image) generates and edits images in a conversation. It supports text and visual sources, 0.5K–4K output, reference-image composition and search grounding for product scenes, infographics and iterative visual work.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nano Banana 2 is Google’s Gemini 3.1 Flash Image model for native image generation and conversational editing. Its design emphasises efficient visual creation and repeated revisions. The documented API profile accepts text, images, video and PDF and returns image and text. It is a distinct named edition from Gemini Nano Banana 2.1, rather than a label for every later Nano Banana update.
Output sizes include 0.5K, 1K, 2K and 4K, with 1K as the default. The smaller 0.5K option is specific to this profile and can suit an initial composition; the larger tiers supply more pixels for the selected output shape. The documented ratios cover square, portrait and landscape formats, including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, with additional 1:4, 4:1, 1:8 and 8:1 formats. For example, square outputs range from 512 × 512 at 0.5K to 4096 × 4096 at 4K. Choose the shape for the intended placement before refining small details.
Google identifies improved aspect-ratio adherence, visual consistency and multilingual text rendering among this edition’s updates. Use exact wording for a poster, menu or infographic and define which label belongs to which object. For small text or a long passage, the model card reports remaining legibility limitations, especially at 1K. Keep captions concise and make their relative size explicit; for dense body text, treat the image as a visual layout reference and check the actual lettering carefully.
Up to 14 reference images can be combined in a workflow. The image guide describes fidelity for up to ten objects and resemblance for up to four characters. Label the references and specify what each one supplies. For a product scene, one image can establish the object, another the environment and another the lighting. For a character sequence, carry previous outputs into the next prompt and state the features that must persist across a change in view or pose.
Web Search and Image Search grounding can inform generation with current information and retrieved visual references. Image Search adds visual context rather than merely a written description of the search result. The manufacturer supports the search feature across the documented thinking settings. Its image-search workflow excludes real-world images of people as search-derived references and returns attribution metadata with grounded results; preserve that metadata when using the result in an application.
The documented thinking controls for Gemini 3.1 Flash Image are minimal and high, with minimal as the default. This differs from the three-level, medium-default profile of Nano Banana 2.1. Thinking supports more complex composition and instruction handling. The model is based on Gemini 3 Flash, but that relationship does not turn it into a general code-execution or function-calling model: those capabilities are marked unsupported on this image edition’s table.
Conversational editing supports changing a supplied image or refining an earlier generation. A concrete brief can say: “Keep the bottle shape, label text and camera angle. Replace the background with a light stone surface and add softer shadows.” Describe preserved elements as carefully as changed ones. The model card notes that character consistency, left/right localisation and doodle-based edits can remain imperfect, so compare those particular details before continuing a visual sequence.
The API model table gives 131,072 input tokens and 32,768 output tokens. It supports image generation, search grounding, thinking and batch processing, while audio generation, caching, structured outputs, file search, Live API and URL context are unsupported. The image workflow does not accept audio input. Video or PDF can inform a still-image task in this API profile; the output remains image and text. Generated images include SynthID, and the requested count of images is not always followed exactly.
For a practical infographic, supply approved labels, the intended audience, reading order, reference material and a target ratio. Ask for one clear visual explanation, then use the next turn to correct wording or spacing while preserving the established composition. For a product mockup, specify geometry, surface, light and the visual details that define the product. The useful result is an image with its associated text that can be inspected, selected and refined in a controlled sequence.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-flash-image | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Image output tokens $0.12 / 1K image tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-3.1-flash-image",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-3.1-flash-image', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-3.1-flash-image', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.1-flash-image
Ailoot Ultra google/gemini-3.1-flash-image
/v1/images
Technical example in English
Create a simple bicycle-care infographic\n\nCreate one portrait infographic teaching three bicycle checks before a short ride: tires, brakes and chain. Use three large illustrated steps in that order, a warm ivory background and dark green accents. Include only these headings: 'TIRES', 'BRAKES', 'CHAIN'. Leave generous space around each heading and keep the illustrations clearly separated.One portrait image with three ordered illustrated steps and the three exact, readable headings.Inspect the rendered image for heading spelling, order and clear separation of the three checks.