Gemini 3 Pro Preview is Google's named Gemini 3 Pro preview profile for multimodal reasoning and text generation. It can work with text, images, audio, video and PDF documents and return a written result. The intended uses include complex analysis, advanced coding, algorithm development and tasks that combine a substantial source set with a specific question.
Gemini 3 Pro is a transformer-based sparse mixture-of-experts model with native multimodal input support. Its architecture routes each token through a selected subset of experts. This is a model-design distinction, rather than a user control for selecting a particular expert or fixing a serving configuration.
Prepare inputs around the task's information need. A document, screenshot and audio recording can each supply different evidence. Identify what each asset contains and how it should contribute to the answer. The output remains text; understanding visual or spoken material does not make this preview an image, speech or video generator.
Use images for questions about visible content, audio for spoken or acoustic information and video for a sequence whose changes matter over time. Keep the actual asset with the question rather than describing it only from memory. When comparing several assets, label them clearly so that the answer can refer to the right source.
For example, a product-analysis brief can combine a written specification, a screenshot of the interface and a recorded demonstration. Ask for a comparison that separates what the specification promises from what is visible or audible in the supplied material. Define the desired result as findings, supporting observations and unresolved questions.
For a PDF task, provide the document and identify the sections or claims to examine. A useful question asks for a comparison, extraction or explanation tied to the source, instead of only requesting a general summary of a large file.
The exact preview specification lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. The maker gives a January 2025 knowledge cutoff; supply newer evidence when the question depends on later events or information. These are different allowances. A large source set can be read for a focused answer without requiring the model to reproduce every part of the input.
Organize long material so that its structure is clear: document titles, section boundaries, code paths and the question that the output must answer. Keep relevant exceptions and definitions close to the content they qualify. If a task needs a long report, specify the report's sections and the evidence expected in each one.
A large context window does not guarantee that every detail will receive equal attention or that every conclusion will be correct. Google also identifies possible degradation across multi-turn conversations; review important source facts and reused context as an exchange develops. Review the answer against the particular passages or assets that support its important claims.
The producer's intended uses include advanced coding and algorithmic work. Supply the relevant source, environment assumptions, observed failure and expected behavior. For an algorithm task, define the input, desired output and conditions such as ordering, duplicates or invalid data.
A useful debugging brief pairs the failing input and error with the smallest relevant source region. Ask for a diagnosis and a focused change, then inspect whether the proposed change addresses the reported behavior. Generated code and a claim that it should work are different from an implementation that has been run and verified.
For a larger repository question, use the input allowance to supply the necessary files with clear path labels. State whether the desired artifact is an explanation, a proposed patch or an analysis of alternatives so that the result has a concrete purpose.
The preview's producer specification supports function calling, code execution, file search, search grounding and URL context. These features have distinct roles. A function call describes an operation for an application to execute; a tool result then supplies evidence for the following model step. Code execution is a tool workflow, rather than a guarantee that arbitrary generated application code has already been tested.
Search grounding and URL context provide source-oriented workflows, while file search works with a prepared file collection. Keep tool results and source associations with the answer so that a conclusion can be inspected. The profile does not support computer use or Maps grounding according to its specification.
Structured output support can express a result in a defined schema. Specify the fields and their meaning before generation, and review the contents as well as the format. A valid structured object still needs factual and task-specific checking.
Thinking is supported for this preview. Use a clear task, relevant evidence and explicit constraints for work that requires several reasoning steps. The result should explain assumptions and the useful conclusion; hidden reasoning or the existence of a thinking mode is not itself verification.
The producer also lists caching and batch support. These are processing features separate from the model's content capabilities, and their presence does not establish that a particular request was cached or that a batch result is correct.
Keep Gemini 3 Pro Preview separate from Gemini 3.1 Pro Preview, Gemini 3 Pro Image and the audio or Live profiles. This preview's output is text, and its specification does not include image generation, audio generation or Live operation. Evaluate the returned answer, code or structured result against the supplied source set and intended task.
", "aboutText": "Gemini 3 Pro Preview is Google's named Gemini 3 Pro preview profile for multimodal reasoning and text generation. It can work with text, images, audio, video and PDF documents and return a written result. The intended uses include complex analysis, advanced coding, algorithm development and tasks that combine a substantial source set with a specific question.\n\n### Model and input structure\n\nGemini 3 Pro is a transformer-based sparse mixture-of-experts model with native multimodal input support. Its architecture routes each token through a selected subset of experts. This is a model-design distinction, rather than a user control for selecting a particular expert or fixing a serving configuration.\n\nPrepare inputs around the task's information need. A document, screenshot and audio recording can each supply different evidence. Identify what each asset contains and how it should contribute to the answer. The output remains text; understanding visual or spoken material does not make this preview an image, speech or video generator.\n\n### Multimodal analysis\n\nUse images for questions about visible content, audio for spoken or acoustic information and video for a sequence whose changes matter over time. Keep the actual asset with the question rather than describing it only from memory. When comparing several assets, label them clearly so that the answer can refer to the right source.\n\nFor example, a product-analysis brief can combine a written specification, a screenshot of the interface and a recorded demonstration. Ask for a comparison that separates what the specification promises from what is visible or audible in the supplied material. Define the desired result as findings, supporting observations and unresolved questions.\n\nFor a PDF task, provide the document and identify the sections or claims to examine. A useful question asks for a comparison, extraction or explanation tied to the source, instead of only requesting a general summary of a large file.\n\n### Long context and the output allowance\n\nThe exact preview specification lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. The maker gives a January 2025 knowledge cutoff; supply newer evidence when the question depends on later events or information. These are different allowances. A large source set can be read for a focused answer without requiring the model to reproduce every part of the input.\n\nOrganize long material so that its structure is clear: document titles, section boundaries, code paths and the question that the output must answer. Keep relevant exceptions and definitions close to the content they qualify. If a task needs a long report, specify the report's sections and the evidence expected in each one.\n\nA large context window does not guarantee that every detail will receive equal attention or that every conclusion will be correct. Google also identifies possible degradation across multi-turn conversations; review important source facts and reused context as an exchange develops. Review the answer against the particular passages or assets that support its important claims.\n\n### Coding and algorithm development\n\nThe producer's intended uses include advanced coding and algorithmic work. Supply the relevant source, environment assumptions, observed failure and expected behavior. For an algorithm task, define the input, desired output and conditions such as ordering, duplicates or invalid data.\n\nA useful debugging brief pairs the failing input and error with the smallest relevant source region. Ask for a diagnosis and a focused change, then inspect whether the proposed change addresses the reported behavior. Generated code and a claim that it should work are different from an implementation that has been run and verified.\n\nFor a larger repository question, use the input allowance to supply the necessary files with clear path labels. State whether the desired artifact is an explanation, a proposed patch or an analysis of alternatives so that the result has a concrete purpose.\n\n### Tools, sources and structured results\n\nThe preview's producer specification supports function calling, code execution, file search, search grounding and URL context. These features have distinct roles. A function call describes an operation for an application to execute; a tool result then supplies evidence for the following model step. Code execution is a tool workflow, rather than a guarantee that arbitrary generated application code has already been tested.\n\nSearch grounding and URL context provide source-oriented workflows, while file search works with a prepared file collection. Keep tool results and source associations with the answer so that a conclusion can be inspected. The profile does not support computer use or Maps grounding according to its specification.\n\nStructured output support can express a result in a defined schema. Specify the fields and their meaning before generation, and review the contents as well as the format. A valid structured object still needs factual and task-specific checking.\n\n### Reasoning, reuse and edition boundaries\n\nThinking is supported for this preview. Use a clear task, relevant evidence and explicit constraints for work that requires several reasoning steps. The result should explain assumptions and the useful conclusion; hidden reasoning or the existence of a thinking mode is not itself verification.\n\nThe producer also lists caching and batch support. These are processing features separate from the model's content capabilities, and their presence does not establish that a particular request was cached or that a batch result is correct.\n\nKeep Gemini 3 Pro Preview separate from Gemini 3.1 Pro Preview, Gemini 3 Pro Image and the audio or Live profiles. This preview's output is text, and its specification does not include image generation, audio generation or Live operation. Evaluate the returned answer, code or structured result against the supplied source set and intended task.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "e3edcf0214894108e57b6db1f24bfe35498e85b39bb6c1155209f5425e112d48", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "gemini-3-pro-previewGemini 3 Pro Preview is Google's multimodal reasoning model for text, images, audio, video and PDFs, with text output. Its large input allowance, coding capabilities and supported tool workflows suit detailed analysis, document comparison and evidence-based task execution.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3 Pro Preview is Google's named Gemini 3 Pro preview profile for multimodal reasoning and text generation. It can work with text, images, audio, video and PDF documents and return a written result. The intended uses include complex analysis, advanced coding, algorithm development and tasks that combine a substantial source set with a specific question.
Gemini 3 Pro is a transformer-based sparse mixture-of-experts model with native multimodal input support. Its architecture routes each token through a selected subset of experts. This is a model-design distinction, rather than a user control for selecting a particular expert or fixing a serving configuration.
Prepare inputs around the task's information need. A document, screenshot and audio recording can each supply different evidence. Identify what each asset contains and how it should contribute to the answer. The output remains text; understanding visual or spoken material does not make this preview an image, speech or video generator.
Use images for questions about visible content, audio for spoken or acoustic information and video for a sequence whose changes matter over time. Keep the actual asset with the question rather than describing it only from memory. When comparing several assets, label them clearly so that the answer can refer to the right source.
For example, a product-analysis brief can combine a written specification, a screenshot of the interface and a recorded demonstration. Ask for a comparison that separates what the specification promises from what is visible or audible in the supplied material. Define the desired result as findings, supporting observations and unresolved questions.
For a PDF task, provide the document and identify the sections or claims to examine. A useful question asks for a comparison, extraction or explanation tied to the source, instead of only requesting a general summary of a large file.
The exact preview specification lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. The maker gives a January 2025 knowledge cutoff; supply newer evidence when the question depends on later events or information. These are different allowances. A large source set can be read for a focused answer without requiring the model to reproduce every part of the input.
Organize long material so that its structure is clear: document titles, section boundaries, code paths and the question that the output must answer. Keep relevant exceptions and definitions close to the content they qualify. If a task needs a long report, specify the report's sections and the evidence expected in each one.
A large context window does not guarantee that every detail will receive equal attention or that every conclusion will be correct. Google also identifies possible degradation across multi-turn conversations; review important source facts and reused context as an exchange develops. Review the answer against the particular passages or assets that support its important claims.
The producer's intended uses include advanced coding and algorithmic work. Supply the relevant source, environment assumptions, observed failure and expected behavior. For an algorithm task, define the input, desired output and conditions such as ordering, duplicates or invalid data.
A useful debugging brief pairs the failing input and error with the smallest relevant source region. Ask for a diagnosis and a focused change, then inspect whether the proposed change addresses the reported behavior. Generated code and a claim that it should work are different from an implementation that has been run and verified.
For a larger repository question, use the input allowance to supply the necessary files with clear path labels. State whether the desired artifact is an explanation, a proposed patch or an analysis of alternatives so that the result has a concrete purpose.
The preview's producer specification supports function calling, code execution, file search, search grounding and URL context. These features have distinct roles. A function call describes an operation for an application to execute; a tool result then supplies evidence for the following model step. Code execution is a tool workflow, rather than a guarantee that arbitrary generated application code has already been tested.
Search grounding and URL context provide source-oriented workflows, while file search works with a prepared file collection. Keep tool results and source associations with the answer so that a conclusion can be inspected. The profile does not support computer use or Maps grounding according to its specification.
Structured output support can express a result in a defined schema. Specify the fields and their meaning before generation, and review the contents as well as the format. A valid structured object still needs factual and task-specific checking.
Thinking is supported for this preview. Use a clear task, relevant evidence and explicit constraints for work that requires several reasoning steps. The result should explain assumptions and the useful conclusion; hidden reasoning or the existence of a thinking mode is not itself verification.
The producer also lists caching and batch support. These are processing features separate from the model's content capabilities, and their presence does not establish that a particular request was cached or that a batch result is correct.
Keep Gemini 3 Pro Preview separate from Gemini 3.1 Pro Preview, Gemini 3 Pro Image and the audio or Live profiles. This preview's output is text, and its specification does not include image generation, audio generation or Live operation. Evaluate the returned answer, code or structured result against the supplied source set and intended task.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3-pro-preview | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
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 |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
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 $0.004 / 1K tokens Output · Output tokens $0.024 / 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-3-pro-preview","messages":[{"role":"user","content":"hello"}],"stream":false}')\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-3-pro-preview", messages=[{"role":"user","content":"hello"}], stream=False)\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"))\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-3-pro-preview
/chat/completions
gemini-3-pro-previewGemini 3 Pro Preview is Google's multimodal reasoning model for text, images, audio, video and PDFs, with text output. Its large input allowance, coding capabilities and supported tool workflows suit detailed analysis, document comparison and evidence-based task execution.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3 Pro Preview is Google's named Gemini 3 Pro preview profile for multimodal reasoning and text generation. It can work with text, images, audio, video and PDF documents and return a written result. The intended uses include complex analysis, advanced coding, algorithm development and tasks that combine a substantial source set with a specific question.
Gemini 3 Pro is a transformer-based sparse mixture-of-experts model with native multimodal input support. Its architecture routes each token through a selected subset of experts. This is a model-design distinction, rather than a user control for selecting a particular expert or fixing a serving configuration.
Prepare inputs around the task's information need. A document, screenshot and audio recording can each supply different evidence. Identify what each asset contains and how it should contribute to the answer. The output remains text; understanding visual or spoken material does not make this preview an image, speech or video generator.
Use images for questions about visible content, audio for spoken or acoustic information and video for a sequence whose changes matter over time. Keep the actual asset with the question rather than describing it only from memory. When comparing several assets, label them clearly so that the answer can refer to the right source.
For example, a product-analysis brief can combine a written specification, a screenshot of the interface and a recorded demonstration. Ask for a comparison that separates what the specification promises from what is visible or audible in the supplied material. Define the desired result as findings, supporting observations and unresolved questions.
For a PDF task, provide the document and identify the sections or claims to examine. A useful question asks for a comparison, extraction or explanation tied to the source, instead of only requesting a general summary of a large file.
The exact preview specification lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. The maker gives a January 2025 knowledge cutoff; supply newer evidence when the question depends on later events or information. These are different allowances. A large source set can be read for a focused answer without requiring the model to reproduce every part of the input.
Organize long material so that its structure is clear: document titles, section boundaries, code paths and the question that the output must answer. Keep relevant exceptions and definitions close to the content they qualify. If a task needs a long report, specify the report's sections and the evidence expected in each one.
A large context window does not guarantee that every detail will receive equal attention or that every conclusion will be correct. Google also identifies possible degradation across multi-turn conversations; review important source facts and reused context as an exchange develops. Review the answer against the particular passages or assets that support its important claims.
The producer's intended uses include advanced coding and algorithmic work. Supply the relevant source, environment assumptions, observed failure and expected behavior. For an algorithm task, define the input, desired output and conditions such as ordering, duplicates or invalid data.
A useful debugging brief pairs the failing input and error with the smallest relevant source region. Ask for a diagnosis and a focused change, then inspect whether the proposed change addresses the reported behavior. Generated code and a claim that it should work are different from an implementation that has been run and verified.
For a larger repository question, use the input allowance to supply the necessary files with clear path labels. State whether the desired artifact is an explanation, a proposed patch or an analysis of alternatives so that the result has a concrete purpose.
The preview's producer specification supports function calling, code execution, file search, search grounding and URL context. These features have distinct roles. A function call describes an operation for an application to execute; a tool result then supplies evidence for the following model step. Code execution is a tool workflow, rather than a guarantee that arbitrary generated application code has already been tested.
Search grounding and URL context provide source-oriented workflows, while file search works with a prepared file collection. Keep tool results and source associations with the answer so that a conclusion can be inspected. The profile does not support computer use or Maps grounding according to its specification.
Structured output support can express a result in a defined schema. Specify the fields and their meaning before generation, and review the contents as well as the format. A valid structured object still needs factual and task-specific checking.
Thinking is supported for this preview. Use a clear task, relevant evidence and explicit constraints for work that requires several reasoning steps. The result should explain assumptions and the useful conclusion; hidden reasoning or the existence of a thinking mode is not itself verification.
The producer also lists caching and batch support. These are processing features separate from the model's content capabilities, and their presence does not establish that a particular request was cached or that a batch result is correct.
Keep Gemini 3 Pro Preview separate from Gemini 3.1 Pro Preview, Gemini 3 Pro Image and the audio or Live profiles. This preview's output is text, and its specification does not include image generation, audio generation or Live operation. Evaluate the returned answer, code or structured result against the supplied source set and intended task.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3-pro-preview | 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 $0.004 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gemini-3-pro-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-3-pro-preview', '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-3-pro-preview', '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-3-pro-preview
/chat/completions