Nemotron 3 Nano 30B A3B is NVIDIA’s hybrid mixture-of-experts text model, developed as one profile for reasoning and non-reasoning tasks. It accepts text and generates text, normally developing a reasoning trace before the final response. The producer chat template can disable that trace for direct answers, with a possible trade-off on harder prompts that benefit from analysis.
The maker architecture is a Mamba-2/transformer hybrid with approximately thirty billion total parameters. Its design has fifty-two layers: twenty-three Mamba-2 layers, twenty-three expert layers and six attention layers. Each expert layer has 128 routed experts and a shared expert, activating six routed experts per token.
NVIDIA describes training on twenty-five trillion tokens, followed by supervised fine-tuning and multi-environment reinforcement learning. The post-training domains include code, mathematics, science, instructions, structured outputs, multi-step tools and multi-turn conversations. These are original Nano properties, separate from the later 3.5 Lightning multi-token-prediction release.
For mathematics, give the complete condition and the final result format. For code, supply the relevant function, representative input, observed failure and required behaviour. A useful brief is: “Trace this input through the implementation, identify the first incorrect condition and return a focused correction with its supporting explanation.” A routine extraction can instead ask for only the defined fields.
The maker lists English, Spanish, French, German, Japanese and Italian. Specify the answer language and keep required terminology intact. Request the final artifact separately from intermediate reasoning so the result remains useful as an explanation, code or structured record.
NVIDIA demonstrates a reference client that first obtains reasoning content, closes an unfinished trace and then uses the remaining generation budget for the final answer. This is a producer client procedure, not an exact native cutoff implied by the model name. Choose a response budget that leaves room for the final answer rather than consuming all available space with analysis.
The producer profile includes training for tool use and structured outputs. An application supplies function definitions, performs the selected operations and returns their observations. Keep those results associated with their calls. A source-backed answer can use the actual retrieved material or calculation, while a code revision should use observed validation feedback.
The model card lists a maximum one-million-token input and output profile for its long-context design. These figures must be used with the selected execution configuration and the shared context budget; the prompt, history, reasoning and response still occupy space together. A long window does not make an unstructured source collection a clear task.
Organise documents by source and code by relevant boundaries, and state what completes the assignment. Review values against the material and code in its intended application. The useful deliverable is a textual result with its evidence and unresolved information identified, retaining the exact Nano edition rather than borrowing later Nemotron features or precision assumptions.
", "aboutText": "Nemotron 3 Nano 30B A3B is NVIDIA’s hybrid mixture-of-experts text model, developed as one profile for reasoning and non-reasoning tasks. It accepts text and generates text, normally developing a reasoning trace before the final response. The producer chat template can disable that trace for direct answers, with a possible trade-off on harder prompts that benefit from analysis.\n\n### Architecture and training\n\nThe maker architecture is a Mamba-2/transformer hybrid with approximately thirty billion total parameters. Its design has fifty-two layers: twenty-three Mamba-2 layers, twenty-three expert layers and six attention layers. Each expert layer has 128 routed experts and a shared expert, activating six routed experts per token.\n\nNVIDIA describes training on twenty-five trillion tokens, followed by supervised fine-tuning and multi-environment reinforcement learning. The post-training domains include code, mathematics, science, instructions, structured outputs, multi-step tools and multi-turn conversations. These are original Nano properties, separate from the later 3.5 Lightning multi-token-prediction release.\n\n### Prepare a reasoning or direct task\n\nFor mathematics, give the complete condition and the final result format. For code, supply the relevant function, representative input, observed failure and required behaviour. A useful brief is: “Trace this input through the implementation, identify the first incorrect condition and return a focused correction with its supporting explanation.” A routine extraction can instead ask for only the defined fields.\n\nThe maker lists English, Spanish, French, German, Japanese and Italian. Specify the answer language and keep required terminology intact. Request the final artifact separately from intermediate reasoning so the result remains useful as an explanation, code or structured record.\n\n### Reasoning-budget reference\n\nNVIDIA demonstrates a reference client that first obtains reasoning content, closes an unfinished trace and then uses the remaining generation budget for the final answer. This is a producer client procedure, not an exact native cutoff implied by the model name. Choose a response budget that leaves room for the final answer rather than consuming all available space with analysis.\n\n### Tools and long context\n\nThe producer profile includes training for tool use and structured outputs. An application supplies function definitions, performs the selected operations and returns their observations. Keep those results associated with their calls. A source-backed answer can use the actual retrieved material or calculation, while a code revision should use observed validation feedback.\n\nThe model card lists a maximum one-million-token input and output profile for its long-context design. These figures must be used with the selected execution configuration and the shared context budget; the prompt, history, reasoning and response still occupy space together. A long window does not make an unstructured source collection a clear task.\n\nOrganise documents by source and code by relevant boundaries, and state what completes the assignment. Review values against the material and code in its intended application. The useful deliverable is a textual result with its evidence and unresolved information identified, retaining the exact Nano edition rather than borrowing later Nemotron features or precision assumptions.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Trace an inclusive-range defect\n\nTrace this Python code for start=2 and end=4: values = []\nfor n in range(start, end):\n values.append(n)\n The caller expects both endpoints included. Explain the first mismatch and propose a focused correction preserving ascending integer inputs. Include tests for 2 through 4 and equal endpoints, and state how descending inputs should be handled.A short trace, an inclusive-range correction, two tests and an explicit descending-input assumption.The equal-endpoint test yields one included value, and the changed bound does not omit end.nvidia/nemotron-3-nano-30b-a3bNemotron 3 Nano is NVIDIA’s hybrid Mamba-2/transformer text model for reasoning and direct replies. Its approximately 30B producer profile supports long-context questions, coding, structured tasks and tools, with configurable thinking and a reference method for controlling reasoning length.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nemotron 3 Nano 30B A3B is NVIDIA’s hybrid mixture-of-experts text model, developed as one profile for reasoning and non-reasoning tasks. It accepts text and generates text, normally developing a reasoning trace before the final response. The producer chat template can disable that trace for direct answers, with a possible trade-off on harder prompts that benefit from analysis.
The maker architecture is a Mamba-2/transformer hybrid with approximately thirty billion total parameters. Its design has fifty-two layers: twenty-three Mamba-2 layers, twenty-three expert layers and six attention layers. Each expert layer has 128 routed experts and a shared expert, activating six routed experts per token.
NVIDIA describes training on twenty-five trillion tokens, followed by supervised fine-tuning and multi-environment reinforcement learning. The post-training domains include code, mathematics, science, instructions, structured outputs, multi-step tools and multi-turn conversations. These are original Nano properties, separate from the later 3.5 Lightning multi-token-prediction release.
For mathematics, give the complete condition and the final result format. For code, supply the relevant function, representative input, observed failure and required behaviour. A useful brief is: “Trace this input through the implementation, identify the first incorrect condition and return a focused correction with its supporting explanation.” A routine extraction can instead ask for only the defined fields.
The maker lists English, Spanish, French, German, Japanese and Italian. Specify the answer language and keep required terminology intact. Request the final artifact separately from intermediate reasoning so the result remains useful as an explanation, code or structured record.
NVIDIA demonstrates a reference client that first obtains reasoning content, closes an unfinished trace and then uses the remaining generation budget for the final answer. This is a producer client procedure, not an exact native cutoff implied by the model name. Choose a response budget that leaves room for the final answer rather than consuming all available space with analysis.
The producer profile includes training for tool use and structured outputs. An application supplies function definitions, performs the selected operations and returns their observations. Keep those results associated with their calls. A source-backed answer can use the actual retrieved material or calculation, while a code revision should use observed validation feedback.
The model card lists a maximum one-million-token input and output profile for its long-context design. These figures must be used with the selected execution configuration and the shared context budget; the prompt, history, reasoning and response still occupy space together. A long window does not make an unstructured source collection a clear task.
Organise documents by source and code by relevant boundaries, and state what completes the assignment. Review values against the material and code in its intended application. The useful deliverable is a textual result with its evidence and unresolved information identified, retaining the exact Nano edition rather than borrowing later Nemotron features or precision assumptions.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nvidia/nemotron-3-nano-30b-a3b | 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 $0.0001 / 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 $0.0001 / 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-nano-30b-a3b", "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-nano-30b-a3b',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-nano-30b-a3b',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 nvidia/nemotron-3-nano-30b-a3b
Use the method paths shown above.
nvidia/nemotron-3-nano-30b-a3bNemotron 3 Nano is NVIDIA’s hybrid Mamba-2/transformer text model for reasoning and direct replies. Its approximately 30B producer profile supports long-context questions, coding, structured tasks and tools, with configurable thinking and a reference method for controlling reasoning length.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Nemotron 3 Nano 30B A3B is NVIDIA’s hybrid mixture-of-experts text model, developed as one profile for reasoning and non-reasoning tasks. It accepts text and generates text, normally developing a reasoning trace before the final response. The producer chat template can disable that trace for direct answers, with a possible trade-off on harder prompts that benefit from analysis.
The maker architecture is a Mamba-2/transformer hybrid with approximately thirty billion total parameters. Its design has fifty-two layers: twenty-three Mamba-2 layers, twenty-three expert layers and six attention layers. Each expert layer has 128 routed experts and a shared expert, activating six routed experts per token.
NVIDIA describes training on twenty-five trillion tokens, followed by supervised fine-tuning and multi-environment reinforcement learning. The post-training domains include code, mathematics, science, instructions, structured outputs, multi-step tools and multi-turn conversations. These are original Nano properties, separate from the later 3.5 Lightning multi-token-prediction release.
For mathematics, give the complete condition and the final result format. For code, supply the relevant function, representative input, observed failure and required behaviour. A useful brief is: “Trace this input through the implementation, identify the first incorrect condition and return a focused correction with its supporting explanation.” A routine extraction can instead ask for only the defined fields.
The maker lists English, Spanish, French, German, Japanese and Italian. Specify the answer language and keep required terminology intact. Request the final artifact separately from intermediate reasoning so the result remains useful as an explanation, code or structured record.
NVIDIA demonstrates a reference client that first obtains reasoning content, closes an unfinished trace and then uses the remaining generation budget for the final answer. This is a producer client procedure, not an exact native cutoff implied by the model name. Choose a response budget that leaves room for the final answer rather than consuming all available space with analysis.
The producer profile includes training for tool use and structured outputs. An application supplies function definitions, performs the selected operations and returns their observations. Keep those results associated with their calls. A source-backed answer can use the actual retrieved material or calculation, while a code revision should use observed validation feedback.
The model card lists a maximum one-million-token input and output profile for its long-context design. These figures must be used with the selected execution configuration and the shared context budget; the prompt, history, reasoning and response still occupy space together. A long window does not make an unstructured source collection a clear task.
Organise documents by source and code by relevant boundaries, and state what completes the assignment. Review values against the material and code in its intended application. The useful deliverable is a textual result with its evidence and unresolved information identified, retaining the exact Nano edition rather than borrowing later Nemotron features or precision assumptions.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nvidia/nemotron-3-nano-30b-a3b | 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 $0.0001 / 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 $0.0001 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "nvidia/nemotron-3-nano-30b-a3b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-nano-30b-a3b', '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-nano-30b-a3b', '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 nvidia/nemotron-3-nano-30b-a3b
Use the method paths shown above.
Technical example in English
Trace an inclusive-range defect\n\nTrace this Python code for start=2 and end=4: values = []\nfor n in range(start, end):\n values.append(n)\n The caller expects both endpoints included. Explain the first mismatch and propose a focused correction preserving ascending integer inputs. Include tests for 2 through 4 and equal endpoints, and state how descending inputs should be handled.A short trace, an inclusive-range correction, two tests and an explicit descending-input assumption.The equal-endpoint test yields one included value, and the changed bound does not omit end.