Nemotron 3.5 Content Safety is NVIDIA’s compact multimodal guardrail model, fine-tuned from Google Gemma-3-4B with four billion parameters. It reviews inputs to and responses from language and vision-language models. Text and images are accepted; the output is text containing safe or unsafe classifications, safety category labels and, optionally, a reasoning trace.
Supply the material to assess and identify which part is the user input and which part is the model response. Preserve their relationship when the response depends on an instruction or visual source. A useful review result keeps the classification with the exact content it evaluated, so a later reader can inspect the reason for a flagged item.
The profile is suited to prompt moderation, response moderation, content classification and safety review within a larger application. The surrounding application chooses the policy action, such as retaining an item for review or continuing a workflow. Keep that action distinct from the classification returned by the model.
A supplied image can be part of the content being assessed. Retain its identifier with the associated text so a safety label remains connected to the correct source. The published profile covers 12 languages and lists a 131,072-token context window. Use representative material from the intended language and preserve the details that determine the assessment in a longer input.
Reasoning can be enabled or disabled in the documented profile. When it is included, inspect the explanation alongside the classification and original content. A category label and its explanation serve different purposes: one supports a policy decision, while the other helps a reviewer understand the assessment.
The model returns a safety result rather than executing the policy action itself. Match the output to the content identifier, review ambiguous cases against the source and preserve any subsequent decision made by the application or reviewer. The published interface does not expose function tools or enforce a JSON response format, so an application should validate the actual returned result before processing its fields.
A useful guardrail artifact joins the evaluated prompt or response, relevant image references, classification, category labels and any returned reasoning. Keep those parts together when auditing or improving the policy workflow.
", "aboutText": "Nemotron 3.5 Content Safety is NVIDIA’s compact multimodal guardrail model, fine-tuned from Google Gemma-3-4B with four billion parameters. It reviews inputs to and responses from language and vision-language models. Text and images are accepted; the output is text containing safe or unsafe classifications, safety category labels and, optionally, a reasoning trace.\n\n### Review the prompt and the response\n\nSupply the material to assess and identify which part is the user input and which part is the model response. Preserve their relationship when the response depends on an instruction or visual source. A useful review result keeps the classification with the exact content it evaluated, so a later reader can inspect the reason for a flagged item.\n\nThe profile is suited to prompt moderation, response moderation, content classification and safety review within a larger application. The surrounding application chooses the policy action, such as retaining an item for review or continuing a workflow. Keep that action distinct from the classification returned by the model.\n\n### Multimodal evidence and reasoning\n\nA supplied image can be part of the content being assessed. Retain its identifier with the associated text so a safety label remains connected to the correct source. The published profile covers 12 languages and lists a 131,072-token context window. Use representative material from the intended language and preserve the details that determine the assessment in a longer input.\n\nReasoning can be enabled or disabled in the documented profile. When it is included, inspect the explanation alongside the classification and original content. A category label and its explanation serve different purposes: one supports a policy decision, while the other helps a reviewer understand the assessment.\n\n### Use the classification in a policy workflow\n\nThe model returns a safety result rather than executing the policy action itself. Match the output to the content identifier, review ambiguous cases against the source and preserve any subsequent decision made by the application or reviewer. The published interface does not expose function tools or enforce a JSON response format, so an application should validate the actual returned result before processing its fields.\n\nA useful guardrail artifact joins the evaluated prompt or response, relevant image references, classification, category labels and any returned reasoning. Keep those parts together when auditing or improving the policy workflow.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Review a benign prompt-response pair\n\nReview this exact text pair for content safety. User: 'How can I organize my public reading list by author?' Assistant: 'Sort the entries by the author surname, keeping titles with their authors.' Identify the user prompt and assistant response separately. Return documented safe or unsafe classifications and, if supplied, a brief reason. Do not execute a moderation action.A safety result associated separately with the supplied prompt and response, using safe/unsafe labels.Check classifications stay attached to the correct text and no undocumented category vocabulary is added.nvidia/nemotron-3.5-content-safetyNemotron 3.5 Content Safety is NVIDIA’s 4B multimodal guardrail model for prompt and response review. It accepts text and images and returns safe or unsafe classifications, safety labels and optional reasoning, covering 12 languages.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nemotron 3.5 Content Safety is NVIDIA’s compact multimodal guardrail model, fine-tuned from Google Gemma-3-4B with four billion parameters. It reviews inputs to and responses from language and vision-language models. Text and images are accepted; the output is text containing safe or unsafe classifications, safety category labels and, optionally, a reasoning trace.
Supply the material to assess and identify which part is the user input and which part is the model response. Preserve their relationship when the response depends on an instruction or visual source. A useful review result keeps the classification with the exact content it evaluated, so a later reader can inspect the reason for a flagged item.
The profile is suited to prompt moderation, response moderation, content classification and safety review within a larger application. The surrounding application chooses the policy action, such as retaining an item for review or continuing a workflow. Keep that action distinct from the classification returned by the model.
A supplied image can be part of the content being assessed. Retain its identifier with the associated text so a safety label remains connected to the correct source. The published profile covers 12 languages and lists a 131,072-token context window. Use representative material from the intended language and preserve the details that determine the assessment in a longer input.
Reasoning can be enabled or disabled in the documented profile. When it is included, inspect the explanation alongside the classification and original content. A category label and its explanation serve different purposes: one supports a policy decision, while the other helps a reviewer understand the assessment.
The model returns a safety result rather than executing the policy action itself. Match the output to the content identifier, review ambiguous cases against the source and preserve any subsequent decision made by the application or reviewer. The published interface does not expose function tools or enforce a JSON response format, so an application should validate the actual returned result before processing its fields.
A useful guardrail artifact joins the evaluated prompt or response, relevant image references, classification, category labels and any returned reasoning. Keep those parts together when auditing or improving the policy workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nvidia/nemotron-3.5-content-safety | 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 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— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext |
Parameterrequired | Contractmodel, messages |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/chat/completionsAiloot 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 →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
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 |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nvidia/nemotron-3.5-content-safety", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\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\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\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)\nresp = client.chat.completions.create(\n model="nvidia/nemotron-3.5-content-safety",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\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(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "nvidia/nemotron-3.5-content-safety",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\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='nvidia/nemotron-3.5-content-safety',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 nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
Ailoot Ultra nvidia/nemotron-3.5-content-safety
Use the method paths shown above.
nvidia/nemotron-3.5-content-safety, nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
nvidia/nemotron-3.5-content-safetyNemotron 3.5 Content Safety is NVIDIA’s 4B multimodal guardrail model for prompt and response review. It accepts text and images and returns safe or unsafe classifications, safety labels and optional reasoning, covering 12 languages.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nemotron 3.5 Content Safety is NVIDIA’s compact multimodal guardrail model, fine-tuned from Google Gemma-3-4B with four billion parameters. It reviews inputs to and responses from language and vision-language models. Text and images are accepted; the output is text containing safe or unsafe classifications, safety category labels and, optionally, a reasoning trace.
Supply the material to assess and identify which part is the user input and which part is the model response. Preserve their relationship when the response depends on an instruction or visual source. A useful review result keeps the classification with the exact content it evaluated, so a later reader can inspect the reason for a flagged item.
The profile is suited to prompt moderation, response moderation, content classification and safety review within a larger application. The surrounding application chooses the policy action, such as retaining an item for review or continuing a workflow. Keep that action distinct from the classification returned by the model.
A supplied image can be part of the content being assessed. Retain its identifier with the associated text so a safety label remains connected to the correct source. The published profile covers 12 languages and lists a 131,072-token context window. Use representative material from the intended language and preserve the details that determine the assessment in a longer input.
Reasoning can be enabled or disabled in the documented profile. When it is included, inspect the explanation alongside the classification and original content. A category label and its explanation serve different purposes: one supports a policy decision, while the other helps a reviewer understand the assessment.
The model returns a safety result rather than executing the policy action itself. Match the output to the content identifier, review ambiguous cases against the source and preserve any subsequent decision made by the application or reviewer. The published interface does not expose function tools or enforce a JSON response format, so an application should validate the actual returned result before processing its fields.
A useful guardrail artifact joins the evaluated prompt or response, relevant image references, classification, category labels and any returned reasoning. Keep those parts together when auditing or improving the policy workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nvidia/nemotron-3.5-content-safety | 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 $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nvidia/nemotron-3.5-content-safety", "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='nvidia/nemotron-3.5-content-safety',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='nvidia/nemotron-3.5-content-safety',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 nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
Ailoot Ultra nvidia/nemotron-3.5-content-safety
Use the method paths shown above.
nvidia/nemotron-3.5-content-safety, nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
nvidia/nemotron-3.5-content-safetyNemotron 3.5 Content Safety is NVIDIA’s 4B multimodal guardrail model for prompt and response review. It accepts text and images and returns safe or unsafe classifications, safety labels and optional reasoning, covering 12 languages.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nemotron 3.5 Content Safety is NVIDIA’s compact multimodal guardrail model, fine-tuned from Google Gemma-3-4B with four billion parameters. It reviews inputs to and responses from language and vision-language models. Text and images are accepted; the output is text containing safe or unsafe classifications, safety category labels and, optionally, a reasoning trace.
Supply the material to assess and identify which part is the user input and which part is the model response. Preserve their relationship when the response depends on an instruction or visual source. A useful review result keeps the classification with the exact content it evaluated, so a later reader can inspect the reason for a flagged item.
The profile is suited to prompt moderation, response moderation, content classification and safety review within a larger application. The surrounding application chooses the policy action, such as retaining an item for review or continuing a workflow. Keep that action distinct from the classification returned by the model.
A supplied image can be part of the content being assessed. Retain its identifier with the associated text so a safety label remains connected to the correct source. The published profile covers 12 languages and lists a 131,072-token context window. Use representative material from the intended language and preserve the details that determine the assessment in a longer input.
Reasoning can be enabled or disabled in the documented profile. When it is included, inspect the explanation alongside the classification and original content. A category label and its explanation serve different purposes: one supports a policy decision, while the other helps a reviewer understand the assessment.
The model returns a safety result rather than executing the policy action itself. Match the output to the content identifier, review ambiguous cases against the source and preserve any subsequent decision made by the application or reviewer. The published interface does not expose function tools or enforce a JSON response format, so an application should validate the actual returned result before processing its fields.
A useful guardrail artifact joins the evaluated prompt or response, relevant image references, classification, category labels and any returned reasoning. Keep those parts together when auditing or improving the policy workflow.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nvidia/nemotron-3.5-content-safety | 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 $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "nvidia/nemotron-3.5-content-safety",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'nvidia/nemotron-3.5-content-safety', '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': 'nvidia/nemotron-3.5-content-safety', '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 nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
Ailoot Ultra nvidia/nemotron-3.5-content-safety
Use the method paths shown above.
nvidia/nemotron-3.5-content-safety, nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
nemotron-content-safetyNemotron 3.5 Content Safety is NVIDIA’s 4B multimodal guardrail model for prompt and response review. It accepts text and images and returns safe or unsafe classifications, safety labels and optional reasoning, covering 12 languages.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nemotron 3.5 Content Safety is NVIDIA’s compact multimodal guardrail model, fine-tuned from Google Gemma-3-4B with four billion parameters. It reviews inputs to and responses from language and vision-language models. Text and images are accepted; the output is text containing safe or unsafe classifications, safety category labels and, optionally, a reasoning trace.
Supply the material to assess and identify which part is the user input and which part is the model response. Preserve their relationship when the response depends on an instruction or visual source. A useful review result keeps the classification with the exact content it evaluated, so a later reader can inspect the reason for a flagged item.
The profile is suited to prompt moderation, response moderation, content classification and safety review within a larger application. The surrounding application chooses the policy action, such as retaining an item for review or continuing a workflow. Keep that action distinct from the classification returned by the model.
A supplied image can be part of the content being assessed. Retain its identifier with the associated text so a safety label remains connected to the correct source. The published profile covers 12 languages and lists a 131,072-token context window. Use representative material from the intended language and preserve the details that determine the assessment in a longer input.
Reasoning can be enabled or disabled in the documented profile. When it is included, inspect the explanation alongside the classification and original content. A category label and its explanation serve different purposes: one supports a policy decision, while the other helps a reviewer understand the assessment.
The model returns a safety result rather than executing the policy action itself. Match the output to the content identifier, review ambiguous cases against the source and preserve any subsequent decision made by the application or reviewer. The published interface does not expose function tools or enforce a JSON response format, so an application should validate the actual returned result before processing its fields.
A useful guardrail artifact joins the evaluated prompt or response, relevant image references, classification, category labels and any returned reasoning. Keep those parts together when auditing or improving the policy workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nemotron-content-safety | 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 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— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext |
Parameterrequired | Contractmodel, messages |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/chat/completionsAiloot 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 →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
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 |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nemotron-content-safety", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\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\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\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)\nresp = client.chat.completions.create(\n model="nemotron-content-safety",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\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(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "nemotron-content-safety",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\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='nemotron-content-safety',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 nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
Ailoot Ultra nvidia/nemotron-3.5-content-safety
Use the method paths shown above.
nvidia/nemotron-3.5-content-safety, nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
nemotron-content-safety-latestNemotron 3.5 Content Safety is NVIDIA’s 4B multimodal guardrail model for prompt and response review. It accepts text and images and returns safe or unsafe classifications, safety labels and optional reasoning, covering 12 languages.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nemotron 3.5 Content Safety is NVIDIA’s compact multimodal guardrail model, fine-tuned from Google Gemma-3-4B with four billion parameters. It reviews inputs to and responses from language and vision-language models. Text and images are accepted; the output is text containing safe or unsafe classifications, safety category labels and, optionally, a reasoning trace.
Supply the material to assess and identify which part is the user input and which part is the model response. Preserve their relationship when the response depends on an instruction or visual source. A useful review result keeps the classification with the exact content it evaluated, so a later reader can inspect the reason for a flagged item.
The profile is suited to prompt moderation, response moderation, content classification and safety review within a larger application. The surrounding application chooses the policy action, such as retaining an item for review or continuing a workflow. Keep that action distinct from the classification returned by the model.
A supplied image can be part of the content being assessed. Retain its identifier with the associated text so a safety label remains connected to the correct source. The published profile covers 12 languages and lists a 131,072-token context window. Use representative material from the intended language and preserve the details that determine the assessment in a longer input.
Reasoning can be enabled or disabled in the documented profile. When it is included, inspect the explanation alongside the classification and original content. A category label and its explanation serve different purposes: one supports a policy decision, while the other helps a reviewer understand the assessment.
The model returns a safety result rather than executing the policy action itself. Match the output to the content identifier, review ambiguous cases against the source and preserve any subsequent decision made by the application or reviewer. The published interface does not expose function tools or enforce a JSON response format, so an application should validate the actual returned result before processing its fields.
A useful guardrail artifact joins the evaluated prompt or response, relevant image references, classification, category labels and any returned reasoning. Keep those parts together when auditing or improving the policy workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nemotron-content-safety-latest | 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 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— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext |
Parameterrequired | Contractmodel, messages |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/chat/completionsAiloot 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 →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
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 |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nemotron-content-safety-latest", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\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\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\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)\nresp = client.chat.completions.create(\n model="nemotron-content-safety-latest",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\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(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "nemotron-content-safety-latest",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\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='nemotron-content-safety-latest',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 nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
Ailoot Ultra nvidia/nemotron-3.5-content-safety
Use the method paths shown above.
nvidia/nemotron-3.5-content-safety, nvidia/nemotron-3.5-content-safety, nemotron-content-safety, nemotron-content-safety-latest
Technical example in English
Review a benign prompt-response pair\n\nReview this exact text pair for content safety. User: 'How can I organize my public reading list by author?' Assistant: 'Sort the entries by the author surname, keeping titles with their authors.' Identify the user prompt and assistant response separately. Return documented safe or unsafe classifications and, if supplied, a brief reason. Do not execute a moderation action.A safety result associated separately with the supplied prompt and response, using safe/unsafe labels.Check classifications stay attached to the correct text and no undocumented category vocabulary is added.