Gemini 3.1 Pro Preview Custom Tools is Google’s specialized variant for agent workflows that mix terminal commands with custom tools. Its distinguishing behavior is prioritizing application-defined tools, with the manufacturer giving view_file and search_code as examples. It is a separate named variant of Gemini 3.1 Pro Preview, not a different label for every Pro request. A useful task relies on the right tool to obtain evidence before preparing the final text result.
The Pro Preview line accepts text, images, video, audio and PDF and returns text. The maker lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens for that line. A repository investigation can combine source files, written requirements and an interface screenshot; a document workflow can combine pages and questions. Label the sources and define the final artifact so the large input budget supports a specific task rather than an unfocused archive dump.
For a software agent, define the goal, available tools and the scope of the requested change. A custom search tool might return matching file locations, while a read-file tool supplies the exact relevant content. Specify their accepted arguments and returned fields. The application executes an accepted call and passes the result back to the model, which can choose the next step based on what actually happened. A returned path is evidence of a search result, not proof that the file was changed or a test was run.
The Custom Tools variant is intended for cases where those specialized actions should take priority over reaching for a generic bash command. For example, an agent can first search for the implementation of a named behavior, read the associated files, compare them with the user’s requirement and then propose a bounded change. Define which interfaces and behavior must remain intact, and request a final list of proposed changes with the source information used. If a controlled test runner is available, return its actual result before asking for a conclusion about the change.
The maker’s 3.1 Pro documentation includes thinking, structured outputs and function calling, together with code execution, search grounding, Google Maps grounding, URL context and caching. Its file-search listing is explicitly scoped to Google AI Studio. Tool availability is therefore part of the chosen producer interface and application setup. The variant’s special preference for custom tools does not itself supply those tools or run an external operation. Maintain a record of the function name, validated arguments and result for each completed application action.
The Gemini 3 guide describes low, medium and high thinking levels for 3.1 Pro, with high as the default. These are relative analysis allowances rather than strict token guarantees. Choose the level according to the task and provide direct instructions rather than elaborate prompting rituals. If structured output is required, define the fields, types and missing-value rules. For an implementation report, the final record could identify the files examined, the required behavior, the proposed modification and the remaining questions. Check that each entry follows from the actual tool or source results.
Multi-turn agents must retain the conversation and required reasoning context. The maker’s guide explains thought signatures and distinguishes managed stateful history from manually managed stateless history. Use the documented handling in the selected interface, especially when continuing after a tool result. For long source material, place the specific question after the context and tie the requested answer to it. The guide also recommends its default temperature of 1.0 rather than transplanting a low-temperature setting that may produce loops on complex tasks.
The manufacturer warns that quality can fluctuate in use cases that do not benefit from custom tools. This is a meaningful selection boundary: use this profile for a tool-centered agent rather than assuming a general improvement for every isolated prompt. The text output can be a plan, code proposal, explanation or structured result; image or audio inputs do not turn the variant into a media generator. Inspect proposed code, verify calculations and distinguish confirmed operations from suggestions. Retain the exact Custom Tools model identity with the task, tool definitions and returned evidence so a later continuation has a concrete basis.
", "aboutText": "Gemini 3.1 Pro Preview Custom Tools is Google’s specialized variant for agent workflows that mix terminal commands with custom tools. Its distinguishing behavior is prioritizing application-defined tools, with the manufacturer giving view_file and search_code as examples. It is a separate named variant of Gemini 3.1 Pro Preview, not a different label for every Pro request. A useful task relies on the right tool to obtain evidence before preparing the final text result.\n\nThe Pro Preview line accepts text, images, video, audio and PDF and returns text. The maker lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens for that line. A repository investigation can combine source files, written requirements and an interface screenshot; a document workflow can combine pages and questions. Label the sources and define the final artifact so the large input budget supports a specific task rather than an unfocused archive dump.\n\nFor a software agent, define the goal, available tools and the scope of the requested change. A custom search tool might return matching file locations, while a read-file tool supplies the exact relevant content. Specify their accepted arguments and returned fields. The application executes an accepted call and passes the result back to the model, which can choose the next step based on what actually happened. A returned path is evidence of a search result, not proof that the file was changed or a test was run.\n\nThe Custom Tools variant is intended for cases where those specialized actions should take priority over reaching for a generic bash command. For example, an agent can first search for the implementation of a named behavior, read the associated files, compare them with the user’s requirement and then propose a bounded change. Define which interfaces and behavior must remain intact, and request a final list of proposed changes with the source information used. If a controlled test runner is available, return its actual result before asking for a conclusion about the change.\n\nThe maker’s 3.1 Pro documentation includes thinking, structured outputs and function calling, together with code execution, search grounding, Google Maps grounding, URL context and caching. Its file-search listing is explicitly scoped to Google AI Studio. Tool availability is therefore part of the chosen producer interface and application setup. The variant’s special preference for custom tools does not itself supply those tools or run an external operation. Maintain a record of the function name, validated arguments and result for each completed application action.\n\nThe Gemini 3 guide describes low, medium and high thinking levels for 3.1 Pro, with high as the default. These are relative analysis allowances rather than strict token guarantees. Choose the level according to the task and provide direct instructions rather than elaborate prompting rituals. If structured output is required, define the fields, types and missing-value rules. For an implementation report, the final record could identify the files examined, the required behavior, the proposed modification and the remaining questions. Check that each entry follows from the actual tool or source results.\n\nMulti-turn agents must retain the conversation and required reasoning context. The maker’s guide explains thought signatures and distinguishes managed stateful history from manually managed stateless history. Use the documented handling in the selected interface, especially when continuing after a tool result. For long source material, place the specific question after the context and tie the requested answer to it. The guide also recommends its default temperature of 1.0 rather than transplanting a low-temperature setting that may produce loops on complex tasks.\n\nThe manufacturer warns that quality can fluctuate in use cases that do not benefit from custom tools. This is a meaningful selection boundary: use this profile for a tool-centered agent rather than assuming a general improvement for every isolated prompt. The text output can be a plan, code proposal, explanation or structured result; image or audio inputs do not turn the variant into a media generator. Inspect proposed code, verify calculations and distinguish confirmed operations from suggestions. Retain the exact Custom Tools model identity with the task, tool definitions and returned evidence so a later continuation has a concrete basis.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Interpret custom-tool evidence\n\nUse this supplied tool transcript. search_code returned settings.py:12 and view_file returned: 'RETRY_LIMIT = 3'. No edit or test result is present. Requirement: increase the retry limit to five. Return the examined file, the exact proposed edit and the remaining check. Distinguish the retrieved value from actions that have not occurred.A file-linked proposed edit and an explicitly unexecuted validation step.The answer must not claim that settings.py was changed or a test passed.google/gemini-3.1-pro-preview-customtoolsGemini 3.1 Pro Preview Custom Tools is a distinct agent-oriented variant that prioritizes application-defined tools alongside terminal commands. Use it when actions such as reading files or searching code should drive a multi-step task, with the application executing and returning each tool result.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.1 Pro Preview Custom Tools is Google’s specialized variant for agent workflows that mix terminal commands with custom tools. Its distinguishing behavior is prioritizing application-defined tools, with the manufacturer giving view_file and search_code as examples. It is a separate named variant of Gemini 3.1 Pro Preview, not a different label for every Pro request. A useful task relies on the right tool to obtain evidence before preparing the final text result.
The Pro Preview line accepts text, images, video, audio and PDF and returns text. The maker lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens for that line. A repository investigation can combine source files, written requirements and an interface screenshot; a document workflow can combine pages and questions. Label the sources and define the final artifact so the large input budget supports a specific task rather than an unfocused archive dump.
For a software agent, define the goal, available tools and the scope of the requested change. A custom search tool might return matching file locations, while a read-file tool supplies the exact relevant content. Specify their accepted arguments and returned fields. The application executes an accepted call and passes the result back to the model, which can choose the next step based on what actually happened. A returned path is evidence of a search result, not proof that the file was changed or a test was run.
The Custom Tools variant is intended for cases where those specialized actions should take priority over reaching for a generic bash command. For example, an agent can first search for the implementation of a named behavior, read the associated files, compare them with the user’s requirement and then propose a bounded change. Define which interfaces and behavior must remain intact, and request a final list of proposed changes with the source information used. If a controlled test runner is available, return its actual result before asking for a conclusion about the change.
The maker’s 3.1 Pro documentation includes thinking, structured outputs and function calling, together with code execution, search grounding, Google Maps grounding, URL context and caching. Its file-search listing is explicitly scoped to Google AI Studio. Tool availability is therefore part of the chosen producer interface and application setup. The variant’s special preference for custom tools does not itself supply those tools or run an external operation. Maintain a record of the function name, validated arguments and result for each completed application action.
The Gemini 3 guide describes low, medium and high thinking levels for 3.1 Pro, with high as the default. These are relative analysis allowances rather than strict token guarantees. Choose the level according to the task and provide direct instructions rather than elaborate prompting rituals. If structured output is required, define the fields, types and missing-value rules. For an implementation report, the final record could identify the files examined, the required behavior, the proposed modification and the remaining questions. Check that each entry follows from the actual tool or source results.
Multi-turn agents must retain the conversation and required reasoning context. The maker’s guide explains thought signatures and distinguishes managed stateful history from manually managed stateless history. Use the documented handling in the selected interface, especially when continuing after a tool result. For long source material, place the specific question after the context and tie the requested answer to it. The guide also recommends its default temperature of 1.0 rather than transplanting a low-temperature setting that may produce loops on complex tasks.
The manufacturer warns that quality can fluctuate in use cases that do not benefit from custom tools. This is a meaningful selection boundary: use this profile for a tool-centered agent rather than assuming a general improvement for every isolated prompt. The text output can be a plan, code proposal, explanation or structured result; image or audio inputs do not turn the variant into a media generator. Inspect proposed code, verify calculations and distinguish confirmed operations from suggestions. Retain the exact Custom Tools model identity with the task, tool definitions and returned evidence so a later continuation has a concrete basis.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-pro-preview-customtools | 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 $0.004 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Reasoning output tokens $0.024 / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including200,000 | Charge Input · Input tokens $0.004 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than200,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.008 / 1K tokens Output · Output tokens $0.036 / 1K tokens Input · Cache read $0.0008 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "google/gemini-3.1-pro-preview-customtools", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='google/gemini-3.1-pro-preview-customtools',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='google/gemini-3.1-pro-preview-customtools',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-3.1-pro-preview-customtools
Use the method paths shown above.
google/gemini-3.1-pro-preview-customtoolsGemini 3.1 Pro Preview Custom Tools is a distinct agent-oriented variant that prioritizes application-defined tools alongside terminal commands. Use it when actions such as reading files or searching code should drive a multi-step task, with the application executing and returning each tool result.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.1 Pro Preview Custom Tools is Google’s specialized variant for agent workflows that mix terminal commands with custom tools. Its distinguishing behavior is prioritizing application-defined tools, with the manufacturer giving view_file and search_code as examples. It is a separate named variant of Gemini 3.1 Pro Preview, not a different label for every Pro request. A useful task relies on the right tool to obtain evidence before preparing the final text result.
The Pro Preview line accepts text, images, video, audio and PDF and returns text. The maker lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens for that line. A repository investigation can combine source files, written requirements and an interface screenshot; a document workflow can combine pages and questions. Label the sources and define the final artifact so the large input budget supports a specific task rather than an unfocused archive dump.
For a software agent, define the goal, available tools and the scope of the requested change. A custom search tool might return matching file locations, while a read-file tool supplies the exact relevant content. Specify their accepted arguments and returned fields. The application executes an accepted call and passes the result back to the model, which can choose the next step based on what actually happened. A returned path is evidence of a search result, not proof that the file was changed or a test was run.
The Custom Tools variant is intended for cases where those specialized actions should take priority over reaching for a generic bash command. For example, an agent can first search for the implementation of a named behavior, read the associated files, compare them with the user’s requirement and then propose a bounded change. Define which interfaces and behavior must remain intact, and request a final list of proposed changes with the source information used. If a controlled test runner is available, return its actual result before asking for a conclusion about the change.
The maker’s 3.1 Pro documentation includes thinking, structured outputs and function calling, together with code execution, search grounding, Google Maps grounding, URL context and caching. Its file-search listing is explicitly scoped to Google AI Studio. Tool availability is therefore part of the chosen producer interface and application setup. The variant’s special preference for custom tools does not itself supply those tools or run an external operation. Maintain a record of the function name, validated arguments and result for each completed application action.
The Gemini 3 guide describes low, medium and high thinking levels for 3.1 Pro, with high as the default. These are relative analysis allowances rather than strict token guarantees. Choose the level according to the task and provide direct instructions rather than elaborate prompting rituals. If structured output is required, define the fields, types and missing-value rules. For an implementation report, the final record could identify the files examined, the required behavior, the proposed modification and the remaining questions. Check that each entry follows from the actual tool or source results.
Multi-turn agents must retain the conversation and required reasoning context. The maker’s guide explains thought signatures and distinguishes managed stateful history from manually managed stateless history. Use the documented handling in the selected interface, especially when continuing after a tool result. For long source material, place the specific question after the context and tie the requested answer to it. The guide also recommends its default temperature of 1.0 rather than transplanting a low-temperature setting that may produce loops on complex tasks.
The manufacturer warns that quality can fluctuate in use cases that do not benefit from custom tools. This is a meaningful selection boundary: use this profile for a tool-centered agent rather than assuming a general improvement for every isolated prompt. The text output can be a plan, code proposal, explanation or structured result; image or audio inputs do not turn the variant into a media generator. Inspect proposed code, verify calculations and distinguish confirmed operations from suggestions. Retain the exact Custom Tools model identity with the task, tool definitions and returned evidence so a later continuation has a concrete basis.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-pro-preview-customtools | 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 $0.004 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Reasoning output tokens $0.024 / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including200,000 | Charge Input · Input tokens $0.004 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than200,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.008 / 1K tokens Output · Output tokens $0.036 / 1K tokens Input · Cache read $0.0008 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-3.1-pro-preview-customtools",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-3.1-pro-preview-customtools', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-3.1-pro-preview-customtools', '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-3.1-pro-preview-customtools
Use the method paths shown above.
Technical example in English
Interpret custom-tool evidence\n\nUse this supplied tool transcript. search_code returned settings.py:12 and view_file returned: 'RETRY_LIMIT = 3'. No edit or test result is present. Requirement: increase the retry limit to five. Return the examined file, the exact proposed edit and the remaining check. Distinguish the retrieved value from actions that have not occurred.A file-linked proposed edit and an explicitly unexecuted validation step.The answer must not claim that settings.py was changed or a test passed.