Gemini 2.5 Flash Image, also known as Nano Banana, is Google’s text-and-image model for visual creation and conversational image editing. It accepts an instruction with optional image references and can return images with accompanying text. This exact 2.5 Flash Image edition is distinct from Nano Banana 2, Nano Banana Pro and later Lite image models. Its useful result is a generated or revised visual asset, not the response of the general Gemini 2.5 text model.
The exact model card lists 65,536 input tokens and 32,768 output tokens. Images and instructions are part of the input, and the returned image or text is part of the result. The guide’s resolution table gives 1:1 output at 1024×1024, 3:4 at 864×1184 and 16:9 at 1344×768, among its supported aspect ratios. Choose the intended display shape before designing the scene. The high-resolution options of a later Gemini image edition should not be treated as controls documented for this exact model.
For text-to-image creation, specify the subject, action, environment, style, lighting and viewpoint. A product illustration might use a supplied visual identity and request a clearly visible material detail in an appropriate setting. Explain the purpose of the picture so the model can allocate space for the subject and any text. Photographic descriptions such as a close view, an overhead composition or a low-angle perspective help define framing more clearly than a list of unrelated style words.
For editing, supply the original image and identify the part to change. The maker’s guide describes adding or removing elements, semantic masking, style transfer and composition using references. A useful request names both the revision and the conditions to preserve—for example, change the background while retaining the product’s shape, surface and label. Label each input’s role when combining references, such as subject appearance, setting or style. The guide says this edition works best with up to three input images; this is practical guidance, not a reason to combine an unlimited set of conflicting references.
Conversational refinement can keep the same subject while changing a specific visual decision. Ask for one connected revision at a time and retain the source image and the accepted result used for that turn. Describe what should stay consistent and what may vary. For a sequence of assets, identify the shared subject, colors and visual rules explicitly rather than assuming that a new isolated prompt will recover them. Compare the revised image with the reference before treating a preservation instruction as successfully followed.
For in-image text, settle the exact wording first and then request the picture containing that text, as recommended by the guide. State the language, reading order, placement and relative emphasis of labels. An infographic request should identify the relationship each label explains and the visual elements that support it. Review spelling, punctuation and visual association at the actual display size; a readable-looking generated label can still change a name, number or intended meaning.
The model card does not list thinking, search grounding, function calling, code execution or constrained structured output for this edition. It also does not advertise audio generation or the Live API. Its documented input is text and images, so audio, video and document-processing features from other Gemini models should not be attached to this profile. An application should handle the returned content parts explicitly instead of assuming that a normal prose reply contains the finished image asset.
The guide notes that the requested number of images may not always be followed and that generated images include SynthID marking. Inspect every returned image for composition, subject fidelity, object count and exact wording. If the scene has several components, describe their intended arrangement in a clear order and express the desired appearance positively. Retain the exact model identity, prompt and references with the result. This makes the visual generation or editing task reviewable and gives a later revision a concrete starting point.
", "aboutText": "Gemini 2.5 Flash Image, also known as Nano Banana, is Google’s text-and-image model for visual creation and conversational image editing. It accepts an instruction with optional image references and can return images with accompanying text. This exact 2.5 Flash Image edition is distinct from Nano Banana 2, Nano Banana Pro and later Lite image models. Its useful result is a generated or revised visual asset, not the response of the general Gemini 2.5 text model.\n\nThe exact model card lists 65,536 input tokens and 32,768 output tokens. Images and instructions are part of the input, and the returned image or text is part of the result. The guide’s resolution table gives 1:1 output at 1024×1024, 3:4 at 864×1184 and 16:9 at 1344×768, among its supported aspect ratios. Choose the intended display shape before designing the scene. The high-resolution options of a later Gemini image edition should not be treated as controls documented for this exact model.\n\nFor text-to-image creation, specify the subject, action, environment, style, lighting and viewpoint. A product illustration might use a supplied visual identity and request a clearly visible material detail in an appropriate setting. Explain the purpose of the picture so the model can allocate space for the subject and any text. Photographic descriptions such as a close view, an overhead composition or a low-angle perspective help define framing more clearly than a list of unrelated style words.\n\nFor editing, supply the original image and identify the part to change. The maker’s guide describes adding or removing elements, semantic masking, style transfer and composition using references. A useful request names both the revision and the conditions to preserve—for example, change the background while retaining the product’s shape, surface and label. Label each input’s role when combining references, such as subject appearance, setting or style. The guide says this edition works best with up to three input images; this is practical guidance, not a reason to combine an unlimited set of conflicting references.\n\nConversational refinement can keep the same subject while changing a specific visual decision. Ask for one connected revision at a time and retain the source image and the accepted result used for that turn. Describe what should stay consistent and what may vary. For a sequence of assets, identify the shared subject, colors and visual rules explicitly rather than assuming that a new isolated prompt will recover them. Compare the revised image with the reference before treating a preservation instruction as successfully followed.\n\nFor in-image text, settle the exact wording first and then request the picture containing that text, as recommended by the guide. State the language, reading order, placement and relative emphasis of labels. An infographic request should identify the relationship each label explains and the visual elements that support it. Review spelling, punctuation and visual association at the actual display size; a readable-looking generated label can still change a name, number or intended meaning.\n\nThe model card does not list thinking, search grounding, function calling, code execution or constrained structured output for this edition. It also does not advertise audio generation or the Live API. Its documented input is text and images, so audio, video and document-processing features from other Gemini models should not be attached to this profile. An application should handle the returned content parts explicitly instead of assuming that a normal prose reply contains the finished image asset.\n\nThe guide notes that the requested number of images may not always be followed and that generated images include SynthID marking. Inspect every returned image for composition, subject fidelity, object count and exact wording. If the scene has several components, describe their intended arrangement in a clear order and express the desired appearance positively. Retain the exact model identity, prompt and references with the result. This makes the visual generation or editing task reviewable and gives a later revision a concrete starting point.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Change a product photo background\n\nUsing the supplied product photograph, preserve the ceramic mug's shape, handle, glaze and existing logo exactly. Replace only the background with a pale stone tabletop and soft morning side light. Keep the camera angle and mug position. Remove unrelated background clutter and add no new lettering, props or decorative marks.An edited image retaining the reference mug while changing its setting and light as requested.Compare the result with the reference for mug geometry, logo fidelity, camera angle and removal of clutter.google/gemini-2.5-flash-imageNano Banana (Gemini 2.5 Flash Image) generates and edits pictures from text and images. Use its conversational workflow to compose a scene, change a selected element, combine visual references or refine a product image while stating which details should remain.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Flash Image, also known as Nano Banana, is Google’s text-and-image model for visual creation and conversational image editing. It accepts an instruction with optional image references and can return images with accompanying text. This exact 2.5 Flash Image edition is distinct from Nano Banana 2, Nano Banana Pro and later Lite image models. Its useful result is a generated or revised visual asset, not the response of the general Gemini 2.5 text model.
The exact model card lists 65,536 input tokens and 32,768 output tokens. Images and instructions are part of the input, and the returned image or text is part of the result. The guide’s resolution table gives 1:1 output at 1024×1024, 3:4 at 864×1184 and 16:9 at 1344×768, among its supported aspect ratios. Choose the intended display shape before designing the scene. The high-resolution options of a later Gemini image edition should not be treated as controls documented for this exact model.
For text-to-image creation, specify the subject, action, environment, style, lighting and viewpoint. A product illustration might use a supplied visual identity and request a clearly visible material detail in an appropriate setting. Explain the purpose of the picture so the model can allocate space for the subject and any text. Photographic descriptions such as a close view, an overhead composition or a low-angle perspective help define framing more clearly than a list of unrelated style words.
For editing, supply the original image and identify the part to change. The maker’s guide describes adding or removing elements, semantic masking, style transfer and composition using references. A useful request names both the revision and the conditions to preserve—for example, change the background while retaining the product’s shape, surface and label. Label each input’s role when combining references, such as subject appearance, setting or style. The guide says this edition works best with up to three input images; this is practical guidance, not a reason to combine an unlimited set of conflicting references.
Conversational refinement can keep the same subject while changing a specific visual decision. Ask for one connected revision at a time and retain the source image and the accepted result used for that turn. Describe what should stay consistent and what may vary. For a sequence of assets, identify the shared subject, colors and visual rules explicitly rather than assuming that a new isolated prompt will recover them. Compare the revised image with the reference before treating a preservation instruction as successfully followed.
For in-image text, settle the exact wording first and then request the picture containing that text, as recommended by the guide. State the language, reading order, placement and relative emphasis of labels. An infographic request should identify the relationship each label explains and the visual elements that support it. Review spelling, punctuation and visual association at the actual display size; a readable-looking generated label can still change a name, number or intended meaning.
The model card does not list thinking, search grounding, function calling, code execution or constrained structured output for this edition. It also does not advertise audio generation or the Live API. Its documented input is text and images, so audio, video and document-processing features from other Gemini models should not be attached to this profile. An application should handle the returned content parts explicitly instead of assuming that a normal prose reply contains the finished image asset.
The guide notes that the requested number of images may not always be followed and that generated images include SynthID marking. Inspect every returned image for composition, subject fidelity, object count and exact wording. If the scene has several components, describe their intended arrangement in a clear order and express the desired appearance positively. Retain the exact model identity, prompt and references with the result. This makes the visual generation or editing task reviewable and gives a later revision a concrete starting point.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-2.5-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 $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 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 $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 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/gemini-2.5-flash-image · Default configuration | Billing conditionsDefault configuration | Charge Input · Input $0.0006 / 1K tokens Output · Output $0.06 / 1K tokens |
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationGoogle: Nano Banana (Gemini 2.5 Flash Image) · Default configuration | Billing conditionsDefault configuration | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Input image $0.0006 / 1K tokens Output · Output image $0.06 / 1K tokens Input · Audio input $0.002 / 1K tokens Input · Audio cache read $0.0002 / 1K tokens Output · Web search $0.028 per search Output · Reasoning tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write · 5 minutes ≈$0.000167 / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "google/gemini-2.5-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-2.5-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-2.5-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 Ultra google/gemini-2.5-flash-image
/v1/images
google/gemini-2.5-flash-imageNano Banana (Gemini 2.5 Flash Image) generates and edits pictures from text and images. Use its conversational workflow to compose a scene, change a selected element, combine visual references or refine a product image while stating which details should remain.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Flash Image, also known as Nano Banana, is Google’s text-and-image model for visual creation and conversational image editing. It accepts an instruction with optional image references and can return images with accompanying text. This exact 2.5 Flash Image edition is distinct from Nano Banana 2, Nano Banana Pro and later Lite image models. Its useful result is a generated or revised visual asset, not the response of the general Gemini 2.5 text model.
The exact model card lists 65,536 input tokens and 32,768 output tokens. Images and instructions are part of the input, and the returned image or text is part of the result. The guide’s resolution table gives 1:1 output at 1024×1024, 3:4 at 864×1184 and 16:9 at 1344×768, among its supported aspect ratios. Choose the intended display shape before designing the scene. The high-resolution options of a later Gemini image edition should not be treated as controls documented for this exact model.
For text-to-image creation, specify the subject, action, environment, style, lighting and viewpoint. A product illustration might use a supplied visual identity and request a clearly visible material detail in an appropriate setting. Explain the purpose of the picture so the model can allocate space for the subject and any text. Photographic descriptions such as a close view, an overhead composition or a low-angle perspective help define framing more clearly than a list of unrelated style words.
For editing, supply the original image and identify the part to change. The maker’s guide describes adding or removing elements, semantic masking, style transfer and composition using references. A useful request names both the revision and the conditions to preserve—for example, change the background while retaining the product’s shape, surface and label. Label each input’s role when combining references, such as subject appearance, setting or style. The guide says this edition works best with up to three input images; this is practical guidance, not a reason to combine an unlimited set of conflicting references.
Conversational refinement can keep the same subject while changing a specific visual decision. Ask for one connected revision at a time and retain the source image and the accepted result used for that turn. Describe what should stay consistent and what may vary. For a sequence of assets, identify the shared subject, colors and visual rules explicitly rather than assuming that a new isolated prompt will recover them. Compare the revised image with the reference before treating a preservation instruction as successfully followed.
For in-image text, settle the exact wording first and then request the picture containing that text, as recommended by the guide. State the language, reading order, placement and relative emphasis of labels. An infographic request should identify the relationship each label explains and the visual elements that support it. Review spelling, punctuation and visual association at the actual display size; a readable-looking generated label can still change a name, number or intended meaning.
The model card does not list thinking, search grounding, function calling, code execution or constrained structured output for this edition. It also does not advertise audio generation or the Live API. Its documented input is text and images, so audio, video and document-processing features from other Gemini models should not be attached to this profile. An application should handle the returned content parts explicitly instead of assuming that a normal prose reply contains the finished image asset.
The guide notes that the requested number of images may not always be followed and that generated images include SynthID marking. Inspect every returned image for composition, subject fidelity, object count and exact wording. If the scene has several components, describe their intended arrangement in a clear order and express the desired appearance positively. Retain the exact model identity, prompt and references with the result. This makes the visual generation or editing task reviewable and gives a later revision a concrete starting point.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-2.5-flash-image | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 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: 3 | 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-2.5-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 Ultra google/gemini-2.5-flash-image
/v1/images
google/gemini-2.5-flash-imageNano Banana (Gemini 2.5 Flash Image) generates and edits pictures from text and images. Use its conversational workflow to compose a scene, change a selected element, combine visual references or refine a product image while stating which details should remain.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Flash Image, also known as Nano Banana, is Google’s text-and-image model for visual creation and conversational image editing. It accepts an instruction with optional image references and can return images with accompanying text. This exact 2.5 Flash Image edition is distinct from Nano Banana 2, Nano Banana Pro and later Lite image models. Its useful result is a generated or revised visual asset, not the response of the general Gemini 2.5 text model.
The exact model card lists 65,536 input tokens and 32,768 output tokens. Images and instructions are part of the input, and the returned image or text is part of the result. The guide’s resolution table gives 1:1 output at 1024×1024, 3:4 at 864×1184 and 16:9 at 1344×768, among its supported aspect ratios. Choose the intended display shape before designing the scene. The high-resolution options of a later Gemini image edition should not be treated as controls documented for this exact model.
For text-to-image creation, specify the subject, action, environment, style, lighting and viewpoint. A product illustration might use a supplied visual identity and request a clearly visible material detail in an appropriate setting. Explain the purpose of the picture so the model can allocate space for the subject and any text. Photographic descriptions such as a close view, an overhead composition or a low-angle perspective help define framing more clearly than a list of unrelated style words.
For editing, supply the original image and identify the part to change. The maker’s guide describes adding or removing elements, semantic masking, style transfer and composition using references. A useful request names both the revision and the conditions to preserve—for example, change the background while retaining the product’s shape, surface and label. Label each input’s role when combining references, such as subject appearance, setting or style. The guide says this edition works best with up to three input images; this is practical guidance, not a reason to combine an unlimited set of conflicting references.
Conversational refinement can keep the same subject while changing a specific visual decision. Ask for one connected revision at a time and retain the source image and the accepted result used for that turn. Describe what should stay consistent and what may vary. For a sequence of assets, identify the shared subject, colors and visual rules explicitly rather than assuming that a new isolated prompt will recover them. Compare the revised image with the reference before treating a preservation instruction as successfully followed.
For in-image text, settle the exact wording first and then request the picture containing that text, as recommended by the guide. State the language, reading order, placement and relative emphasis of labels. An infographic request should identify the relationship each label explains and the visual elements that support it. Review spelling, punctuation and visual association at the actual display size; a readable-looking generated label can still change a name, number or intended meaning.
The model card does not list thinking, search grounding, function calling, code execution or constrained structured output for this edition. It also does not advertise audio generation or the Live API. Its documented input is text and images, so audio, video and document-processing features from other Gemini models should not be attached to this profile. An application should handle the returned content parts explicitly instead of assuming that a normal prose reply contains the finished image asset.
The guide notes that the requested number of images may not always be followed and that generated images include SynthID marking. Inspect every returned image for composition, subject fidelity, object count and exact wording. If the scene has several components, describe their intended arrangement in a clear order and express the desired appearance positively. Retain the exact model identity, prompt and references with the result. This makes the visual generation or editing task reviewable and gives a later revision a concrete starting point.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-2.5-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 $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 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 $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-2.5-flash-image",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-2.5-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-2.5-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 Ultra google/gemini-2.5-flash-image
/v1/images
Technical example in English
Change a product photo background\n\nUsing the supplied product photograph, preserve the ceramic mug's shape, handle, glaze and existing logo exactly. Replace only the background with a pale stone tabletop and soft morning side light. Keep the camera angle and mug position. Remove unrelated background clutter and add no new lettering, props or decorative marks.An edited image retaining the reference mug while changing its setting and light as requested.Compare the result with the reference for mug geometry, logo fidelity, camera angle and removal of clutter.