Gemini 2.5 Flash-Lite Preview 09-2025 is Google's September edition for frequent tasks that need a concise, well-directed text result. The manufacturer organizes its update around three themes: stronger following of complex instructions and system prompts, reduced verbosity, and improved translation and multimodal understanding. The dated name identifies this particular preview separately from the June Flash-Lite preview, the stable model and a moving latest alias.
Improved instruction following is useful when a task has several rules that must remain active together. Supply the source material, the audience and the required format, then separate mandatory content from optional explanation. A support-processing task could require a category, the customer's exact question and a next step based only on a provided reference. A document task might specify which terms to preserve, which facts must appear and how missing values should be represented. These examples turn a detailed instruction into a result with observable requirements.
Reduced verbosity is a stated characteristic of this release. It is especially relevant when the output becomes a brief field value, a short reply or the next input in a larger workflow. Ask for the needed information rather than a general discussion: the decision, its source and the unresolved question. For a summary, list the facts and deadlines that must survive compression and specify the number or purpose of sections. Concision is not the same as omitting important conditions; a practical output template makes the required content explicit.
Google reports improved translation quality, image understanding and audio transcription for this September update. For translation, identify the target audience and a glossary, and distinguish names that remain unchanged from wording that should be localized. For an image, mark the component or passage to explain and describe the intended use of the response. For audio transcription, request a written rendering with the language and formatting rules needed for the next step. A multimedia source can also be summarized or compared with a textual requirement when the question identifies the relevant content.
The exact dated card lists text, images, video, audio and PDF as inputs, with text as the output. Its limits are 1,048,576 input tokens and 65,536 output tokens, and its documented knowledge cutoff is January 2025. The large input profile can combine materials, instructions and examples; give each source a label and state what evidence the answer should use. This is the text-output Flash-Lite edition: generated speech, generated pictures and a real-time voice interface are not part of its listed output profile.
The manufacturer documents thinking, structured outputs, function calling, code execution, search grounding, URL context and file search. Thinking can be used for a task with dependent conditions; a structured response can provide fields for extraction or classification. A function call contains a proposed function name and arguments, while the application executes it and returns the result. Google's code-execution tool uses Python; search and document tools supply external material for an informed written response. The exact profile also includes caching and batch processing support. These are documented model capabilities, not a claim that one specific application has enabled every tool or combined them in one request.
The family card describes a sparse mixture-of-experts transformer with native multimodal understanding. Pre-training includes web text, programming languages, images, audio and video. Post-training uses vetted paired instructions and responses, human-preference information and tool-use data, with deduplication, safety and quality filtering in preparation. The same card identifies possible factual invention, causal and counterfactual reasoning difficulties, complex logical deduction limits and inconsistent adherence to thinking budgets. It also records a tendency for some responses to sound overly lecturing. These are substantive review points for a concise processing model.
Prepare representative ordinary, ambiguous and incomplete inputs for a repeated task. For translation, compare terminology, meaning and the requested output-only format. For transcription or document extraction, compare the returned details with the supplied material and identify what could not be established. For a short reply, inspect whether every mandatory fact was retained. The finished artifact might be a translated passage, a compact summary, extracted fields or a category and next action. This preparation uses the September edition's specific emphasis on instruction accuracy, compactness and multimedia handling while keeping the result tied to the original evidence.
", "aboutText": "Gemini 2.5 Flash-Lite Preview 09-2025 is Google's September edition for frequent tasks that need a concise, well-directed text result. The manufacturer organizes its update around three themes: stronger following of complex instructions and system prompts, reduced verbosity, and improved translation and multimodal understanding. The dated name identifies this particular preview separately from the June Flash-Lite preview, the stable model and a moving latest alias.\n\nImproved instruction following is useful when a task has several rules that must remain active together. Supply the source material, the audience and the required format, then separate mandatory content from optional explanation. A support-processing task could require a category, the customer's exact question and a next step based only on a provided reference. A document task might specify which terms to preserve, which facts must appear and how missing values should be represented. These examples turn a detailed instruction into a result with observable requirements.\n\nReduced verbosity is a stated characteristic of this release. It is especially relevant when the output becomes a brief field value, a short reply or the next input in a larger workflow. Ask for the needed information rather than a general discussion: the decision, its source and the unresolved question. For a summary, list the facts and deadlines that must survive compression and specify the number or purpose of sections. Concision is not the same as omitting important conditions; a practical output template makes the required content explicit.\n\nGoogle reports improved translation quality, image understanding and audio transcription for this September update. For translation, identify the target audience and a glossary, and distinguish names that remain unchanged from wording that should be localized. For an image, mark the component or passage to explain and describe the intended use of the response. For audio transcription, request a written rendering with the language and formatting rules needed for the next step. A multimedia source can also be summarized or compared with a textual requirement when the question identifies the relevant content.\n\nThe exact dated card lists text, images, video, audio and PDF as inputs, with text as the output. Its limits are 1,048,576 input tokens and 65,536 output tokens, and its documented knowledge cutoff is January 2025. The large input profile can combine materials, instructions and examples; give each source a label and state what evidence the answer should use. This is the text-output Flash-Lite edition: generated speech, generated pictures and a real-time voice interface are not part of its listed output profile.\n\nThe manufacturer documents thinking, structured outputs, function calling, code execution, search grounding, URL context and file search. Thinking can be used for a task with dependent conditions; a structured response can provide fields for extraction or classification. A function call contains a proposed function name and arguments, while the application executes it and returns the result. Google's code-execution tool uses Python; search and document tools supply external material for an informed written response. The exact profile also includes caching and batch processing support. These are documented model capabilities, not a claim that one specific application has enabled every tool or combined them in one request.\n\nThe family card describes a sparse mixture-of-experts transformer with native multimodal understanding. Pre-training includes web text, programming languages, images, audio and video. Post-training uses vetted paired instructions and responses, human-preference information and tool-use data, with deduplication, safety and quality filtering in preparation. The same card identifies possible factual invention, causal and counterfactual reasoning difficulties, complex logical deduction limits and inconsistent adherence to thinking budgets. It also records a tendency for some responses to sound overly lecturing. These are substantive review points for a concise processing model.\n\nPrepare representative ordinary, ambiguous and incomplete inputs for a repeated task. For translation, compare terminology, meaning and the requested output-only format. For transcription or document extraction, compare the returned details with the supplied material and identify what could not be established. For a short reply, inspect whether every mandatory fact was retained. The finished artifact might be a translated passage, a compact summary, extracted fields or a category and next action. This preparation uses the September edition's specific emphasis on instruction accuracy, compactness and multimedia handling while keeping the result tied to the original evidence.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Translate a constrained support notice\n\nTranslate into French for a customer: “Your Atlas Hub replacement is reserved. We will confirm dispatch after the address check.” Keep Atlas Hub unchanged, preserve the difference between a reservation and dispatch confirmation, and return only the translation. Do not add a date, tracking number or guarantee.One French translation with the product name unchanged and both stages kept distinct.Check that the translation preserves the pending address check and does not announce dispatch.gemini-2.5-flash-lite-preview-09-2025Gemini 2.5 Flash-Lite Preview 09-2025 focuses on instruction following, concise text, translation and multimedia understanding. Google’s September edition accepts text, images, video, audio and PDF, with structured responses and documented tools for high-volume processing.
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-Lite Preview 09-2025 is Google's September edition for frequent tasks that need a concise, well-directed text result. The manufacturer organizes its update around three themes: stronger following of complex instructions and system prompts, reduced verbosity, and improved translation and multimodal understanding. The dated name identifies this particular preview separately from the June Flash-Lite preview, the stable model and a moving latest alias.
Improved instruction following is useful when a task has several rules that must remain active together. Supply the source material, the audience and the required format, then separate mandatory content from optional explanation. A support-processing task could require a category, the customer's exact question and a next step based only on a provided reference. A document task might specify which terms to preserve, which facts must appear and how missing values should be represented. These examples turn a detailed instruction into a result with observable requirements.
Reduced verbosity is a stated characteristic of this release. It is especially relevant when the output becomes a brief field value, a short reply or the next input in a larger workflow. Ask for the needed information rather than a general discussion: the decision, its source and the unresolved question. For a summary, list the facts and deadlines that must survive compression and specify the number or purpose of sections. Concision is not the same as omitting important conditions; a practical output template makes the required content explicit.
Google reports improved translation quality, image understanding and audio transcription for this September update. For translation, identify the target audience and a glossary, and distinguish names that remain unchanged from wording that should be localized. For an image, mark the component or passage to explain and describe the intended use of the response. For audio transcription, request a written rendering with the language and formatting rules needed for the next step. A multimedia source can also be summarized or compared with a textual requirement when the question identifies the relevant content.
The exact dated card lists text, images, video, audio and PDF as inputs, with text as the output. Its limits are 1,048,576 input tokens and 65,536 output tokens, and its documented knowledge cutoff is January 2025. The large input profile can combine materials, instructions and examples; give each source a label and state what evidence the answer should use. This is the text-output Flash-Lite edition: generated speech, generated pictures and a real-time voice interface are not part of its listed output profile.
The manufacturer documents thinking, structured outputs, function calling, code execution, search grounding, URL context and file search. Thinking can be used for a task with dependent conditions; a structured response can provide fields for extraction or classification. A function call contains a proposed function name and arguments, while the application executes it and returns the result. Google's code-execution tool uses Python; search and document tools supply external material for an informed written response. The exact profile also includes caching and batch processing support. These are documented model capabilities, not a claim that one specific application has enabled every tool or combined them in one request.
The family card describes a sparse mixture-of-experts transformer with native multimodal understanding. Pre-training includes web text, programming languages, images, audio and video. Post-training uses vetted paired instructions and responses, human-preference information and tool-use data, with deduplication, safety and quality filtering in preparation. The same card identifies possible factual invention, causal and counterfactual reasoning difficulties, complex logical deduction limits and inconsistent adherence to thinking budgets. It also records a tendency for some responses to sound overly lecturing. These are substantive review points for a concise processing model.
Prepare representative ordinary, ambiguous and incomplete inputs for a repeated task. For translation, compare terminology, meaning and the requested output-only format. For transcription or document extraction, compare the returned details with the supplied material and identify what could not be established. For a short reply, inspect whether every mandatory fact was retained. The finished artifact might be a translated passage, a compact summary, extracted fields or a category and next action. This preparation uses the September edition's specific emphasis on instruction accuracy, compactness and multimedia handling while keeping the result tied to the original evidence.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-2.5-flash-lite-preview-09-2025 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-2.5-flash-lite-preview-09-2025", "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='gemini-2.5-flash-lite-preview-09-2025',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='gemini-2.5-flash-lite-preview-09-2025',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 gemini-2.5-flash-lite-preview-09-2025
Use the method paths shown above.
gemini-2.5-flash-lite-preview-09-2025Gemini 2.5 Flash-Lite Preview 09-2025 focuses on instruction following, concise text, translation and multimedia understanding. Google’s September edition accepts text, images, video, audio and PDF, with structured responses and documented tools for high-volume processing.
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-Lite Preview 09-2025 is Google's September edition for frequent tasks that need a concise, well-directed text result. The manufacturer organizes its update around three themes: stronger following of complex instructions and system prompts, reduced verbosity, and improved translation and multimodal understanding. The dated name identifies this particular preview separately from the June Flash-Lite preview, the stable model and a moving latest alias.
Improved instruction following is useful when a task has several rules that must remain active together. Supply the source material, the audience and the required format, then separate mandatory content from optional explanation. A support-processing task could require a category, the customer's exact question and a next step based only on a provided reference. A document task might specify which terms to preserve, which facts must appear and how missing values should be represented. These examples turn a detailed instruction into a result with observable requirements.
Reduced verbosity is a stated characteristic of this release. It is especially relevant when the output becomes a brief field value, a short reply or the next input in a larger workflow. Ask for the needed information rather than a general discussion: the decision, its source and the unresolved question. For a summary, list the facts and deadlines that must survive compression and specify the number or purpose of sections. Concision is not the same as omitting important conditions; a practical output template makes the required content explicit.
Google reports improved translation quality, image understanding and audio transcription for this September update. For translation, identify the target audience and a glossary, and distinguish names that remain unchanged from wording that should be localized. For an image, mark the component or passage to explain and describe the intended use of the response. For audio transcription, request a written rendering with the language and formatting rules needed for the next step. A multimedia source can also be summarized or compared with a textual requirement when the question identifies the relevant content.
The exact dated card lists text, images, video, audio and PDF as inputs, with text as the output. Its limits are 1,048,576 input tokens and 65,536 output tokens, and its documented knowledge cutoff is January 2025. The large input profile can combine materials, instructions and examples; give each source a label and state what evidence the answer should use. This is the text-output Flash-Lite edition: generated speech, generated pictures and a real-time voice interface are not part of its listed output profile.
The manufacturer documents thinking, structured outputs, function calling, code execution, search grounding, URL context and file search. Thinking can be used for a task with dependent conditions; a structured response can provide fields for extraction or classification. A function call contains a proposed function name and arguments, while the application executes it and returns the result. Google's code-execution tool uses Python; search and document tools supply external material for an informed written response. The exact profile also includes caching and batch processing support. These are documented model capabilities, not a claim that one specific application has enabled every tool or combined them in one request.
The family card describes a sparse mixture-of-experts transformer with native multimodal understanding. Pre-training includes web text, programming languages, images, audio and video. Post-training uses vetted paired instructions and responses, human-preference information and tool-use data, with deduplication, safety and quality filtering in preparation. The same card identifies possible factual invention, causal and counterfactual reasoning difficulties, complex logical deduction limits and inconsistent adherence to thinking budgets. It also records a tendency for some responses to sound overly lecturing. These are substantive review points for a concise processing model.
Prepare representative ordinary, ambiguous and incomplete inputs for a repeated task. For translation, compare terminology, meaning and the requested output-only format. For transcription or document extraction, compare the returned details with the supplied material and identify what could not be established. For a short reply, inspect whether every mandatory fact was retained. The finished artifact might be a translated passage, a compact summary, extracted fields or a category and next action. This preparation uses the September edition's specific emphasis on instruction accuracy, compactness and multimedia handling while keeping the result tied to the original evidence.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-2.5-flash-lite-preview-09-2025 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gemini-2.5-flash-lite-preview-09-2025",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'gemini-2.5-flash-lite-preview-09-2025', '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': 'gemini-2.5-flash-lite-preview-09-2025', '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 gemini-2.5-flash-lite-preview-09-2025
Use the method paths shown above.
Technical example in English
Translate a constrained support notice\n\nTranslate into French for a customer: “Your Atlas Hub replacement is reserved. We will confirm dispatch after the address check.” Keep Atlas Hub unchanged, preserve the difference between a reservation and dispatch confirmation, and return only the translation. Do not add a date, tracking number or guarantee.One French translation with the product name unchanged and both stages kept distinct.Check that the translation preserves the pending address check and does not announce dispatch.