Amazon Nova Premier is the most capable understanding model in Amazon’s first-generation Nova family, designed for complex work requiring deep understanding, context and planning across several steps. It processes text, images and video and produces text. Its role includes reasoning over long reports, comparing evidence across documents, understanding charts and visual material, and coordinating agent tasks. Premier is separate from the lighter Micro, Lite and Pro models, and from Nova models that generate images, video or conversational speech.
The exact producer model profile lists a 1 million-token context window and a maximum output of 25K tokens. Its documented knowledge cutoff is October 2024. This makes Premier useful when a task needs a large body of reference material alongside instructions and conversation. Organise that material with document names, section markers and a specific question rather than asking for an undirected analysis of everything. A useful result can be a comparison matrix, an evidence-based report or a proposed sequence of actions. The context budget covers the material the model works with; it is not a promise that every detail will appear in the final answer.
Premier’s documented multimodal workflow handles PNG, JPG/JPEG, GIF and WebP images and common video containers such as MP4, MOV, MKV and WebM. The document workflow includes PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-oriented files supply text; PDF and DOCX can supply page text with visual information. For a report with charts, keep labels readable and ask the model to describe the relevant observations before interpreting them. If only the prose is needed, supplying extracted text avoids making visual extraction a prerequisite to understanding the document. Embedded media shares a 25 MB payload budget, including base64 overhead. A request contains one video, limited to 1 GB through S3; combined S3 media can total 2 GB. PDF and DOCX inputs remain limited to five documents, with a combined allowance of 25 MB for direct upload or 2 GB through S3.
Video understanding is based on sampled visual frames. The first-generation guide specifically gives Premier a one-frame-per-second sampling rate up to 3,200 frames, a different allowance from the 960-frame strategy of Nova Lite and Pro. This is useful for scene summaries and questions about events over time, while brief actions between sampled frames may escape observation. Provide a relevant clip or time range and identify the details to track. For a long sequence, segmented analysis followed by a text summary can preserve focus, though splitting can lose context across segment boundaries. The documented model modalities do not include audio input, so spoken information should be supplied as text.
Premier supports response streaming, tool-oriented and retrieval-augmented workflows, and prompt caching in Amazon’s documented serving profile. Explicit caching requires at least 1K tokens per checkpoint and permits up to four checkpoints with five-minute retention. The producer limits prompt caching to 20K tokens, primarily for text prompts; that cache allowance is distinct from the full context window. Give an agent the task, the allowed tools and their argument descriptions, then let the application execute requested actions and return observations before the next model step. Its reasoning role does not imply that it can run an external system without that execution layer. The first-generation guidance supports explaining a solution in stages through prompting; Nova 2 Lite’s separate low, medium and high extended-thinking controls are not part of this edition’s documented interface. For a report or tool result, request explicit fields and examples of the desired structure; a requested JSON shape is distinct from enforced structured output.
A distinctive Premier role is teaching smaller Nova models through distillation. Amazon describes using Premier’s responses as training examples for specialised Nova Micro, Lite and Pro variants, then comparing the smaller model’s behaviour on the target task. That is a model-customisation workflow rather than a change to the identity of a normal Premier response. In ordinary use, supply the authoritative facts and require the answer to separate observations, assumptions and missing evidence. Nova can generate plausible claims that contradict a source, and generated code does not include automatic security scanning, so the useful artifact should carry enough evidence and detail to be checked against its inputs. The producer also states that this model does not identify or name people in images, documents or videos.
", "aboutText": "Amazon Nova Premier is the most capable understanding model in Amazon’s first-generation Nova family, designed for complex work requiring deep understanding, context and planning across several steps. It processes text, images and video and produces text. Its role includes reasoning over long reports, comparing evidence across documents, understanding charts and visual material, and coordinating agent tasks. Premier is separate from the lighter Micro, Lite and Pro models, and from Nova models that generate images, video or conversational speech.\n\nThe exact producer model profile lists a 1 million-token context window and a maximum output of 25K tokens. Its documented knowledge cutoff is October 2024. This makes Premier useful when a task needs a large body of reference material alongside instructions and conversation. Organise that material with document names, section markers and a specific question rather than asking for an undirected analysis of everything. A useful result can be a comparison matrix, an evidence-based report or a proposed sequence of actions. The context budget covers the material the model works with; it is not a promise that every detail will appear in the final answer.\n\nPremier’s documented multimodal workflow handles PNG, JPG/JPEG, GIF and WebP images and common video containers such as MP4, MOV, MKV and WebM. The document workflow includes PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-oriented files supply text; PDF and DOCX can supply page text with visual information. For a report with charts, keep labels readable and ask the model to describe the relevant observations before interpreting them. If only the prose is needed, supplying extracted text avoids making visual extraction a prerequisite to understanding the document. Embedded media shares a 25 MB payload budget, including base64 overhead. A request contains one video, limited to 1 GB through S3; combined S3 media can total 2 GB. PDF and DOCX inputs remain limited to five documents, with a combined allowance of 25 MB for direct upload or 2 GB through S3.\n\nVideo understanding is based on sampled visual frames. The first-generation guide specifically gives Premier a one-frame-per-second sampling rate up to 3,200 frames, a different allowance from the 960-frame strategy of Nova Lite and Pro. This is useful for scene summaries and questions about events over time, while brief actions between sampled frames may escape observation. Provide a relevant clip or time range and identify the details to track. For a long sequence, segmented analysis followed by a text summary can preserve focus, though splitting can lose context across segment boundaries. The documented model modalities do not include audio input, so spoken information should be supplied as text.\n\nPremier supports response streaming, tool-oriented and retrieval-augmented workflows, and prompt caching in Amazon’s documented serving profile. Explicit caching requires at least 1K tokens per checkpoint and permits up to four checkpoints with five-minute retention. The producer limits prompt caching to 20K tokens, primarily for text prompts; that cache allowance is distinct from the full context window. Give an agent the task, the allowed tools and their argument descriptions, then let the application execute requested actions and return observations before the next model step. Its reasoning role does not imply that it can run an external system without that execution layer. The first-generation guidance supports explaining a solution in stages through prompting; Nova 2 Lite’s separate low, medium and high extended-thinking controls are not part of this edition’s documented interface. For a report or tool result, request explicit fields and examples of the desired structure; a requested JSON shape is distinct from enforced structured output.\n\nA distinctive Premier role is teaching smaller Nova models through distillation. Amazon describes using Premier’s responses as training examples for specialised Nova Micro, Lite and Pro variants, then comparing the smaller model’s behaviour on the target task. That is a model-customisation workflow rather than a change to the identity of a normal Premier response. In ordinary use, supply the authoritative facts and require the answer to separate observations, assumptions and missing evidence. Nova can generate plausible claims that contradict a source, and generated code does not include automatic security scanning, so the useful artifact should carry enough evidence and detail to be checked against its inputs. The producer also states that this model does not identify or name people in images, documents or videos.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Compare two rollout proposals\n\nCompare these rollout notes for a support team. Plan A: train all 40 agents on Monday, migrate Tuesday, no rollback rehearsal. Plan B: train 10 agents, pilot for two days, rehearse rollback, then migrate the rest. Prepare a decision memo with evidence, trade-offs and one question the notes cannot answer.A short recommendation, a two-plan comparison table and one explicitly unanswered question.Check every stated advantage against the notes; do not invent costs, outage rates or pilot results.amazon/nova-premier-v1Amazon Nova Premier is the first-generation Nova model for complex multimodal reasoning, long-document analysis and agents. It accepts text, images and video, returns text, and also serves as a teacher for distilling specialised Nova models.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Amazon Nova Premier is the most capable understanding model in Amazon’s first-generation Nova family, designed for complex work requiring deep understanding, context and planning across several steps. It processes text, images and video and produces text. Its role includes reasoning over long reports, comparing evidence across documents, understanding charts and visual material, and coordinating agent tasks. Premier is separate from the lighter Micro, Lite and Pro models, and from Nova models that generate images, video or conversational speech.
The exact producer model profile lists a 1 million-token context window and a maximum output of 25K tokens. Its documented knowledge cutoff is October 2024. This makes Premier useful when a task needs a large body of reference material alongside instructions and conversation. Organise that material with document names, section markers and a specific question rather than asking for an undirected analysis of everything. A useful result can be a comparison matrix, an evidence-based report or a proposed sequence of actions. The context budget covers the material the model works with; it is not a promise that every detail will appear in the final answer.
Premier’s documented multimodal workflow handles PNG, JPG/JPEG, GIF and WebP images and common video containers such as MP4, MOV, MKV and WebM. The document workflow includes PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-oriented files supply text; PDF and DOCX can supply page text with visual information. For a report with charts, keep labels readable and ask the model to describe the relevant observations before interpreting them. If only the prose is needed, supplying extracted text avoids making visual extraction a prerequisite to understanding the document. Embedded media shares a 25 MB payload budget, including base64 overhead. A request contains one video, limited to 1 GB through S3; combined S3 media can total 2 GB. PDF and DOCX inputs remain limited to five documents, with a combined allowance of 25 MB for direct upload or 2 GB through S3.
Video understanding is based on sampled visual frames. The first-generation guide specifically gives Premier a one-frame-per-second sampling rate up to 3,200 frames, a different allowance from the 960-frame strategy of Nova Lite and Pro. This is useful for scene summaries and questions about events over time, while brief actions between sampled frames may escape observation. Provide a relevant clip or time range and identify the details to track. For a long sequence, segmented analysis followed by a text summary can preserve focus, though splitting can lose context across segment boundaries. The documented model modalities do not include audio input, so spoken information should be supplied as text.
Premier supports response streaming, tool-oriented and retrieval-augmented workflows, and prompt caching in Amazon’s documented serving profile. Explicit caching requires at least 1K tokens per checkpoint and permits up to four checkpoints with five-minute retention. The producer limits prompt caching to 20K tokens, primarily for text prompts; that cache allowance is distinct from the full context window. Give an agent the task, the allowed tools and their argument descriptions, then let the application execute requested actions and return observations before the next model step. Its reasoning role does not imply that it can run an external system without that execution layer. The first-generation guidance supports explaining a solution in stages through prompting; Nova 2 Lite’s separate low, medium and high extended-thinking controls are not part of this edition’s documented interface. For a report or tool result, request explicit fields and examples of the desired structure; a requested JSON shape is distinct from enforced structured output.
A distinctive Premier role is teaching smaller Nova models through distillation. Amazon describes using Premier’s responses as training examples for specialised Nova Micro, Lite and Pro variants, then comparing the smaller model’s behaviour on the target task. That is a model-customisation workflow rather than a change to the identity of a normal Premier response. In ordinary use, supply the authoritative facts and require the answer to separate observations, assumptions and missing evidence. Nova can generate plausible claims that contradict a source, and generated code does not include automatic security scanning, so the useful artifact should carry enough evidence and detail to be checked against its inputs. The producer also states that this model does not identify or name people in images, documents or videos.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits amazon/nova-premier-v1 | 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 $0.005 / 1K tokens Output · Output tokens $0.025 / 1K tokens Input · Cache read $0.00125 / 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 $0.005 / 1K tokens Output · Output tokens $0.025 / 1K tokens Input · Cache read $0.00125 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "amazon/nova-premier-v1", "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='amazon/nova-premier-v1',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='amazon/nova-premier-v1',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 amazon/nova-premier-v1
Use the method paths shown above.
amazon/nova-premier-v1Amazon Nova Premier is the first-generation Nova model for complex multimodal reasoning, long-document analysis and agents. It accepts text, images and video, returns text, and also serves as a teacher for distilling specialised Nova models.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Amazon Nova Premier is the most capable understanding model in Amazon’s first-generation Nova family, designed for complex work requiring deep understanding, context and planning across several steps. It processes text, images and video and produces text. Its role includes reasoning over long reports, comparing evidence across documents, understanding charts and visual material, and coordinating agent tasks. Premier is separate from the lighter Micro, Lite and Pro models, and from Nova models that generate images, video or conversational speech.
The exact producer model profile lists a 1 million-token context window and a maximum output of 25K tokens. Its documented knowledge cutoff is October 2024. This makes Premier useful when a task needs a large body of reference material alongside instructions and conversation. Organise that material with document names, section markers and a specific question rather than asking for an undirected analysis of everything. A useful result can be a comparison matrix, an evidence-based report or a proposed sequence of actions. The context budget covers the material the model works with; it is not a promise that every detail will appear in the final answer.
Premier’s documented multimodal workflow handles PNG, JPG/JPEG, GIF and WebP images and common video containers such as MP4, MOV, MKV and WebM. The document workflow includes PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-oriented files supply text; PDF and DOCX can supply page text with visual information. For a report with charts, keep labels readable and ask the model to describe the relevant observations before interpreting them. If only the prose is needed, supplying extracted text avoids making visual extraction a prerequisite to understanding the document. Embedded media shares a 25 MB payload budget, including base64 overhead. A request contains one video, limited to 1 GB through S3; combined S3 media can total 2 GB. PDF and DOCX inputs remain limited to five documents, with a combined allowance of 25 MB for direct upload or 2 GB through S3.
Video understanding is based on sampled visual frames. The first-generation guide specifically gives Premier a one-frame-per-second sampling rate up to 3,200 frames, a different allowance from the 960-frame strategy of Nova Lite and Pro. This is useful for scene summaries and questions about events over time, while brief actions between sampled frames may escape observation. Provide a relevant clip or time range and identify the details to track. For a long sequence, segmented analysis followed by a text summary can preserve focus, though splitting can lose context across segment boundaries. The documented model modalities do not include audio input, so spoken information should be supplied as text.
Premier supports response streaming, tool-oriented and retrieval-augmented workflows, and prompt caching in Amazon’s documented serving profile. Explicit caching requires at least 1K tokens per checkpoint and permits up to four checkpoints with five-minute retention. The producer limits prompt caching to 20K tokens, primarily for text prompts; that cache allowance is distinct from the full context window. Give an agent the task, the allowed tools and their argument descriptions, then let the application execute requested actions and return observations before the next model step. Its reasoning role does not imply that it can run an external system without that execution layer. The first-generation guidance supports explaining a solution in stages through prompting; Nova 2 Lite’s separate low, medium and high extended-thinking controls are not part of this edition’s documented interface. For a report or tool result, request explicit fields and examples of the desired structure; a requested JSON shape is distinct from enforced structured output.
A distinctive Premier role is teaching smaller Nova models through distillation. Amazon describes using Premier’s responses as training examples for specialised Nova Micro, Lite and Pro variants, then comparing the smaller model’s behaviour on the target task. That is a model-customisation workflow rather than a change to the identity of a normal Premier response. In ordinary use, supply the authoritative facts and require the answer to separate observations, assumptions and missing evidence. Nova can generate plausible claims that contradict a source, and generated code does not include automatic security scanning, so the useful artifact should carry enough evidence and detail to be checked against its inputs. The producer also states that this model does not identify or name people in images, documents or videos.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits amazon/nova-premier-v1 | 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 $0.005 / 1K tokens Output · Output tokens $0.025 / 1K tokens Input · Cache read $0.00125 / 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 $0.005 / 1K tokens Output · Output tokens $0.025 / 1K tokens Input · Cache read $0.00125 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "amazon/nova-premier-v1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'amazon/nova-premier-v1', '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': 'amazon/nova-premier-v1', '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 amazon/nova-premier-v1
Use the method paths shown above.
Technical example in English
Compare two rollout proposals\n\nCompare these rollout notes for a support team. Plan A: train all 40 agents on Monday, migrate Tuesday, no rollback rehearsal. Plan B: train 10 agents, pilot for two days, rehearse rollback, then migrate the rest. Prepare a decision memo with evidence, trade-offs and one question the notes cannot answer.A short recommendation, a two-plan comparison table and one explicitly unanswered question.Check every stated advantage against the notes; do not invent costs, outage rates or pilot results.