Gemini Nano Banana 2.1 is Google’s image-generation and conversational-editing model. It is an update to Nano Banana 2, with improvements in visual realism, adherence to instructions, text rendering and character consistency across successive edits. Its input table includes text, images, video and PDF, while the output is image and text. This makes it useful for a product scene, an infographic or a visual series that develops through several specific revisions.
The model offers 1K, 2K and 4K output, with 1K as the default. It does not inherit Nano Banana 2’s 0.5K option. The documented aspect ratios include 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus the tall or panoramic formats 1:4, 4:1, 1:8 and 8:1. Google identifies fixes to tiling artifacts in the latter wide and tall formats at 2K and 4K. Resolution labels are size tiers, not one fixed rectangle: a square 4K image is 4096 × 4096, while the documented 16:9 4K output is 5504 × 3072.
Text is a substantial part of the visual workflow. The model is designed to render legible styled wording and organise infographic elements more accurately. Prepare the exact headline, labels and reading order, then request the image with that approved text. For a menu, diagram or instructional graphic, name the relationship between a caption and its visual element. Google recommends creating the wording first and then asking for the image, so the visual composition starts from a settled text brief.
Reference-image fusion supports up to 14 images. The documented profile covers consistency for up to four characters and fidelity for up to ten objects. Assign each reference a role: the product that must stay recognisable, the character appearance, the intended background or the visual style. An illustrative product brief is: “Use image A for the bottle shape and label. Use image B for the surface and lighting. Keep the product unchanged, place it beside a folded towel and leave clear space above it for the supplied headline.”
Google Web Search and Image Search grounding can provide current information and visual context for generation. Image Search supplies retrieved web images as references; standard web grounding supplies information about the subject. This is useful for a factual graphic or a scene whose appearance depends on a real object. The image-search workflow does not support retrieving real-world images of people for this purpose. Grounded responses carry source and attribution metadata in Google’s documented workflow, so an application should preserve it with the generated result.
Thinking is configurable at minimal, medium and high levels, with medium as the default for this exact model. It helps the model work through composition and more complex instructions before final output. The image guide describes interim composition images within that process; they are distinct from the intended final deliverable. Choose the required final layout, aspect ratio and resolution explicitly rather than expecting the prompt’s description alone to fix every output setting.
Conversational editing lets a follow-up change one part of an existing result: adjust the light, move an object or translate the labels while preserving the rest of the composition. Carry the earlier image or interaction into the next turn and state both the requested change and the features to retain. For a character series, keep appearance references consistent and use a pose reference when a new angle or complex pose matters. A practical revision brief can say: “Preserve the product, labels and layout; make only the background a warmer grey.”
The model table gives an input limit of 131,072 tokens and an output limit of 32,768 tokens. Image generation and search grounding are supported, while audio generation, code execution, function calling, structured outputs, caching, file search, URL context and Live API are not listed as supported for this edition. Video can inform a generated still image; it does not make this model a video generator. Google also notes that a request for an exact number of images may not produce that count. All generated images include a SynthID watermark.
For a useful first brief, give the image’s purpose, subject, composition, lighting, camera view, required text and output shape. For example, request a portrait infographic with three labelled steps, a readable heading and a specified colour hierarchy, then review the wording and relative placement before the next edit. The result can become a product illustration, editorial graphic or design reference, with the chosen image and its explanatory text retained together.
", "aboutText": "Gemini Nano Banana 2.1 is Google’s image-generation and conversational-editing model. It is an update to Nano Banana 2, with improvements in visual realism, adherence to instructions, text rendering and character consistency across successive edits. Its input table includes text, images, video and PDF, while the output is image and text. This makes it useful for a product scene, an infographic or a visual series that develops through several specific revisions.\n\nThe model offers 1K, 2K and 4K output, with 1K as the default. It does not inherit Nano Banana 2’s 0.5K option. The documented aspect ratios include 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus the tall or panoramic formats 1:4, 4:1, 1:8 and 8:1. Google identifies fixes to tiling artifacts in the latter wide and tall formats at 2K and 4K. Resolution labels are size tiers, not one fixed rectangle: a square 4K image is 4096 × 4096, while the documented 16:9 4K output is 5504 × 3072.\n\nText is a substantial part of the visual workflow. The model is designed to render legible styled wording and organise infographic elements more accurately. Prepare the exact headline, labels and reading order, then request the image with that approved text. For a menu, diagram or instructional graphic, name the relationship between a caption and its visual element. Google recommends creating the wording first and then asking for the image, so the visual composition starts from a settled text brief.\n\nReference-image fusion supports up to 14 images. The documented profile covers consistency for up to four characters and fidelity for up to ten objects. Assign each reference a role: the product that must stay recognisable, the character appearance, the intended background or the visual style. An illustrative product brief is: “Use image A for the bottle shape and label. Use image B for the surface and lighting. Keep the product unchanged, place it beside a folded towel and leave clear space above it for the supplied headline.”\n\nGoogle Web Search and Image Search grounding can provide current information and visual context for generation. Image Search supplies retrieved web images as references; standard web grounding supplies information about the subject. This is useful for a factual graphic or a scene whose appearance depends on a real object. The image-search workflow does not support retrieving real-world images of people for this purpose. Grounded responses carry source and attribution metadata in Google’s documented workflow, so an application should preserve it with the generated result.\n\nThinking is configurable at minimal, medium and high levels, with medium as the default for this exact model. It helps the model work through composition and more complex instructions before final output. The image guide describes interim composition images within that process; they are distinct from the intended final deliverable. Choose the required final layout, aspect ratio and resolution explicitly rather than expecting the prompt’s description alone to fix every output setting.\n\nConversational editing lets a follow-up change one part of an existing result: adjust the light, move an object or translate the labels while preserving the rest of the composition. Carry the earlier image or interaction into the next turn and state both the requested change and the features to retain. For a character series, keep appearance references consistent and use a pose reference when a new angle or complex pose matters. A practical revision brief can say: “Preserve the product, labels and layout; make only the background a warmer grey.”\n\nThe model table gives an input limit of 131,072 tokens and an output limit of 32,768 tokens. Image generation and search grounding are supported, while audio generation, code execution, function calling, structured outputs, caching, file search, URL context and Live API are not listed as supported for this edition. Video can inform a generated still image; it does not make this model a video generator. Google also notes that a request for an exact number of images may not produce that count. All generated images include a SynthID watermark.\n\nFor a useful first brief, give the image’s purpose, subject, composition, lighting, camera view, required text and output shape. For example, request a portrait infographic with three labelled steps, a readable heading and a specified colour hierarchy, then review the wording and relative placement before the next edit. The result can become a product illustration, editorial graphic or design reference, with the chosen image and its explanatory text retained together.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Refine an approved poster background\n\nEdit the supplied event poster. Preserve every word, the headline hierarchy, illustration placement and portrait composition. Change only the background from cool white to warm ivory, keeping dark text readable and retaining the original accent color. Do not add shapes, badges, textures or extra captions. Return the revised poster image.One edited poster with the original wording and layout preserved over a warm ivory background.Compare every word and element position against the supplied poster, then inspect text contrast.google/gemini-nano-banana-2.1Gemini Nano Banana 2.1 generates and edits images conversationally from text and visual material. It improves text rendering, infographic layout and multi-turn consistency, with 1K–4K output and up to 14 reference images for a defined visual brief.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini Nano Banana 2.1 is Google’s image-generation and conversational-editing model. It is an update to Nano Banana 2, with improvements in visual realism, adherence to instructions, text rendering and character consistency across successive edits. Its input table includes text, images, video and PDF, while the output is image and text. This makes it useful for a product scene, an infographic or a visual series that develops through several specific revisions.
The model offers 1K, 2K and 4K output, with 1K as the default. It does not inherit Nano Banana 2’s 0.5K option. The documented aspect ratios include 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus the tall or panoramic formats 1:4, 4:1, 1:8 and 8:1. Google identifies fixes to tiling artifacts in the latter wide and tall formats at 2K and 4K. Resolution labels are size tiers, not one fixed rectangle: a square 4K image is 4096 × 4096, while the documented 16:9 4K output is 5504 × 3072.
Text is a substantial part of the visual workflow. The model is designed to render legible styled wording and organise infographic elements more accurately. Prepare the exact headline, labels and reading order, then request the image with that approved text. For a menu, diagram or instructional graphic, name the relationship between a caption and its visual element. Google recommends creating the wording first and then asking for the image, so the visual composition starts from a settled text brief.
Reference-image fusion supports up to 14 images. The documented profile covers consistency for up to four characters and fidelity for up to ten objects. Assign each reference a role: the product that must stay recognisable, the character appearance, the intended background or the visual style. An illustrative product brief is: “Use image A for the bottle shape and label. Use image B for the surface and lighting. Keep the product unchanged, place it beside a folded towel and leave clear space above it for the supplied headline.”
Google Web Search and Image Search grounding can provide current information and visual context for generation. Image Search supplies retrieved web images as references; standard web grounding supplies information about the subject. This is useful for a factual graphic or a scene whose appearance depends on a real object. The image-search workflow does not support retrieving real-world images of people for this purpose. Grounded responses carry source and attribution metadata in Google’s documented workflow, so an application should preserve it with the generated result.
Thinking is configurable at minimal, medium and high levels, with medium as the default for this exact model. It helps the model work through composition and more complex instructions before final output. The image guide describes interim composition images within that process; they are distinct from the intended final deliverable. Choose the required final layout, aspect ratio and resolution explicitly rather than expecting the prompt’s description alone to fix every output setting.
Conversational editing lets a follow-up change one part of an existing result: adjust the light, move an object or translate the labels while preserving the rest of the composition. Carry the earlier image or interaction into the next turn and state both the requested change and the features to retain. For a character series, keep appearance references consistent and use a pose reference when a new angle or complex pose matters. A practical revision brief can say: “Preserve the product, labels and layout; make only the background a warmer grey.”
The model table gives an input limit of 131,072 tokens and an output limit of 32,768 tokens. Image generation and search grounding are supported, while audio generation, code execution, function calling, structured outputs, caching, file search, URL context and Live API are not listed as supported for this edition. Video can inform a generated still image; it does not make this model a video generator. Google also notes that a request for an exact number of images may not produce that count. All generated images include a SynthID watermark.
For a useful first brief, give the image’s purpose, subject, composition, lighting, camera view, required text and output shape. For example, request a portrait infographic with three labelled steps, a readable heading and a specified colour hierarchy, then review the wording and relative placement before the next edit. The result can become a product illustration, editorial graphic or design reference, with the chosen image and its explanatory text retained together.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-nano-banana-2.1 | 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 $0.003 / 1K tokens Output · Output tokens $0.015 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Image output tokens $0.06 / 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 $0.003 / 1K tokens Output · Output tokens $0.015 / 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 2.1 · Default configuration | Billing conditionsDefault configuration | Charge Input · Input tokens $0.003 / 1K tokens Output · Output tokens $0.015 / 1K tokens Output · Output image $0.06 / 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-nano-banana-2.1", "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-nano-banana-2.1',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-nano-banana-2.1',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 Ultra google/gemini-nano-banana-2.1
/v1/images
google/gemini-nano-banana-2.1Gemini Nano Banana 2.1 generates and edits images conversationally from text and visual material. It improves text rendering, infographic layout and multi-turn consistency, with 1K–4K output and up to 14 reference images for a defined visual brief.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini Nano Banana 2.1 is Google’s image-generation and conversational-editing model. It is an update to Nano Banana 2, with improvements in visual realism, adherence to instructions, text rendering and character consistency across successive edits. Its input table includes text, images, video and PDF, while the output is image and text. This makes it useful for a product scene, an infographic or a visual series that develops through several specific revisions.
The model offers 1K, 2K and 4K output, with 1K as the default. It does not inherit Nano Banana 2’s 0.5K option. The documented aspect ratios include 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus the tall or panoramic formats 1:4, 4:1, 1:8 and 8:1. Google identifies fixes to tiling artifacts in the latter wide and tall formats at 2K and 4K. Resolution labels are size tiers, not one fixed rectangle: a square 4K image is 4096 × 4096, while the documented 16:9 4K output is 5504 × 3072.
Text is a substantial part of the visual workflow. The model is designed to render legible styled wording and organise infographic elements more accurately. Prepare the exact headline, labels and reading order, then request the image with that approved text. For a menu, diagram or instructional graphic, name the relationship between a caption and its visual element. Google recommends creating the wording first and then asking for the image, so the visual composition starts from a settled text brief.
Reference-image fusion supports up to 14 images. The documented profile covers consistency for up to four characters and fidelity for up to ten objects. Assign each reference a role: the product that must stay recognisable, the character appearance, the intended background or the visual style. An illustrative product brief is: “Use image A for the bottle shape and label. Use image B for the surface and lighting. Keep the product unchanged, place it beside a folded towel and leave clear space above it for the supplied headline.”
Google Web Search and Image Search grounding can provide current information and visual context for generation. Image Search supplies retrieved web images as references; standard web grounding supplies information about the subject. This is useful for a factual graphic or a scene whose appearance depends on a real object. The image-search workflow does not support retrieving real-world images of people for this purpose. Grounded responses carry source and attribution metadata in Google’s documented workflow, so an application should preserve it with the generated result.
Thinking is configurable at minimal, medium and high levels, with medium as the default for this exact model. It helps the model work through composition and more complex instructions before final output. The image guide describes interim composition images within that process; they are distinct from the intended final deliverable. Choose the required final layout, aspect ratio and resolution explicitly rather than expecting the prompt’s description alone to fix every output setting.
Conversational editing lets a follow-up change one part of an existing result: adjust the light, move an object or translate the labels while preserving the rest of the composition. Carry the earlier image or interaction into the next turn and state both the requested change and the features to retain. For a character series, keep appearance references consistent and use a pose reference when a new angle or complex pose matters. A practical revision brief can say: “Preserve the product, labels and layout; make only the background a warmer grey.”
The model table gives an input limit of 131,072 tokens and an output limit of 32,768 tokens. Image generation and search grounding are supported, while audio generation, code execution, function calling, structured outputs, caching, file search, URL context and Live API are not listed as supported for this edition. Video can inform a generated still image; it does not make this model a video generator. Google also notes that a request for an exact number of images may not produce that count. All generated images include a SynthID watermark.
For a useful first brief, give the image’s purpose, subject, composition, lighting, camera view, required text and output shape. For example, request a portrait infographic with three labelled steps, a readable heading and a specified colour hierarchy, then review the wording and relative placement before the next edit. The result can become a product illustration, editorial graphic or design reference, with the chosen image and its explanatory text retained together.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-nano-banana-2.1 | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldresolution | Typestring | RequirementOptional | Values & limits 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 $0.24576 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-nano-banana-2.1', '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 Ultra google/gemini-nano-banana-2.1
/v1/images
google/gemini-nano-banana-2.1Gemini Nano Banana 2.1 generates and edits images conversationally from text and visual material. It improves text rendering, infographic layout and multi-turn consistency, with 1K–4K output and up to 14 reference images for a defined visual brief.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini Nano Banana 2.1 is Google’s image-generation and conversational-editing model. It is an update to Nano Banana 2, with improvements in visual realism, adherence to instructions, text rendering and character consistency across successive edits. Its input table includes text, images, video and PDF, while the output is image and text. This makes it useful for a product scene, an infographic or a visual series that develops through several specific revisions.
The model offers 1K, 2K and 4K output, with 1K as the default. It does not inherit Nano Banana 2’s 0.5K option. The documented aspect ratios include 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus the tall or panoramic formats 1:4, 4:1, 1:8 and 8:1. Google identifies fixes to tiling artifacts in the latter wide and tall formats at 2K and 4K. Resolution labels are size tiers, not one fixed rectangle: a square 4K image is 4096 × 4096, while the documented 16:9 4K output is 5504 × 3072.
Text is a substantial part of the visual workflow. The model is designed to render legible styled wording and organise infographic elements more accurately. Prepare the exact headline, labels and reading order, then request the image with that approved text. For a menu, diagram or instructional graphic, name the relationship between a caption and its visual element. Google recommends creating the wording first and then asking for the image, so the visual composition starts from a settled text brief.
Reference-image fusion supports up to 14 images. The documented profile covers consistency for up to four characters and fidelity for up to ten objects. Assign each reference a role: the product that must stay recognisable, the character appearance, the intended background or the visual style. An illustrative product brief is: “Use image A for the bottle shape and label. Use image B for the surface and lighting. Keep the product unchanged, place it beside a folded towel and leave clear space above it for the supplied headline.”
Google Web Search and Image Search grounding can provide current information and visual context for generation. Image Search supplies retrieved web images as references; standard web grounding supplies information about the subject. This is useful for a factual graphic or a scene whose appearance depends on a real object. The image-search workflow does not support retrieving real-world images of people for this purpose. Grounded responses carry source and attribution metadata in Google’s documented workflow, so an application should preserve it with the generated result.
Thinking is configurable at minimal, medium and high levels, with medium as the default for this exact model. It helps the model work through composition and more complex instructions before final output. The image guide describes interim composition images within that process; they are distinct from the intended final deliverable. Choose the required final layout, aspect ratio and resolution explicitly rather than expecting the prompt’s description alone to fix every output setting.
Conversational editing lets a follow-up change one part of an existing result: adjust the light, move an object or translate the labels while preserving the rest of the composition. Carry the earlier image or interaction into the next turn and state both the requested change and the features to retain. For a character series, keep appearance references consistent and use a pose reference when a new angle or complex pose matters. A practical revision brief can say: “Preserve the product, labels and layout; make only the background a warmer grey.”
The model table gives an input limit of 131,072 tokens and an output limit of 32,768 tokens. Image generation and search grounding are supported, while audio generation, code execution, function calling, structured outputs, caching, file search, URL context and Live API are not listed as supported for this edition. Video can inform a generated still image; it does not make this model a video generator. Google also notes that a request for an exact number of images may not produce that count. All generated images include a SynthID watermark.
For a useful first brief, give the image’s purpose, subject, composition, lighting, camera view, required text and output shape. For example, request a portrait infographic with three labelled steps, a readable heading and a specified colour hierarchy, then review the wording and relative placement before the next edit. The result can become a product illustration, editorial graphic or design reference, with the chosen image and its explanatory text retained together.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-nano-banana-2.1 | 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 $0.003 / 1K tokens Output · Output tokens $0.015 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Image output tokens $0.06 / 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 $0.003 / 1K tokens Output · Output tokens $0.015 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-nano-banana-2.1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-nano-banana-2.1', '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-nano-banana-2.1', '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 Ultra google/gemini-nano-banana-2.1
/v1/images
Technical example in English
Refine an approved poster background\n\nEdit the supplied event poster. Preserve every word, the headline hierarchy, illustration placement and portrait composition. Change only the background from cool white to warm ivory, keeping dark text readable and retaining the original accent color. Do not add shapes, badges, textures or extra captions. Return the revised poster image.One edited poster with the original wording and layout preserved over a warm ivory background.Compare every word and element position against the supplied poster, then inspect text contrast.