Amazon Nova Pro is the balanced multimodal understanding model in Amazon’s first-generation Nova family. It combines text, image and video understanding for tasks ranging from document question answering and visual analysis to software work and agent workflows. Its output is text: an explanation, extracted information, code, a plan or a tool request. Pro sits between the lighter Nova Lite and the more demanding long-context work addressed by Premier; this profile describes the original Pro v1 edition rather than a Nova 2 model.
The first-generation Nova guide lists a 300K-token context window and a maximum output of 10K tokens. Its documented knowledge cutoff is October 2024. A practical workflow can combine reference passages, document content, visual evidence and recent conversation, then return a compact result. For a technical review, supply the relevant code, observed behaviour and constraints and ask for a proposed change with reasons. For a report, name the sources and fields to compare. Separate the evidence from instructions so the model can distinguish what the documents state from the conclusion you want it to investigate.
Amazon documents Pro’s ability to answer visual questions, classify or summarise images and return bounding boxes for specified objects. The first-generation image guide uses a [0, 1000) coordinate scale, converted to original image dimensions by the consuming application. Images are rescaled automatically, with a documented maximum resolution of 8,000 × 8,000 pixels. This supports work such as identifying an element in a screenshot or describing a diagram. Preserve readable text and key visual context, and ask for the relevant observations before requesting an interpretation.
The supported producer image formats include PNG, JPG/JPEG, GIF and WebP. The document workflow accepts PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-based formats contribute text, while PDF and DOCX can be interpreted together with visual elements such as charts and tables. The document guide permits up to five documents and limits each text document to 4.5 MB. It excludes PDF content using CMYK or SVG images and unsupported encodings such as JPEG2000 and JBIG2. Where a task needs only the words in a PDF, extracted text provides a simpler input than page-level visual reading. 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.
Pro can analyse common video formats including MP4, MOV, MKV and WebM. Its version1 sampling strategy uses one frame per second for clips up to 16 minutes, then 960 frames distributed across longer clips. That favours scene-level summaries over precise analysis of very rapid actions, especially as the video grows longer. Amazon recommends keeping higher-motion clips below 16 minutes and low-motion clips below one hour. Supply a relevant segment and identify the visible event or relationship to inspect; a transcript should carry spoken information because the documented input modalities do not include audio. The producer also states that this model does not identify or name people in images, documents or videos.
Pro supports response streaming, client-executed function calling and retrieval-augmented tasks. It also supports 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. Describe the tools and their arguments, let the application execute requests, and return observations or errors before asking the model to continue. First-generation Nova can be prompted to work through a solution in stages, but that is distinct from Nova 2 Lite’s separately configured extended-thinking modes and built-in tools. Pro also serves as a distillation teacher for Nova Micro and Lite, and Amazon documents custom fine-tuning of Pro; those custom models retain their own identities.
The version1 guide describes training across more than 200 languages with optimisation for 15, including English, German, Spanish, French, Italian, Japanese, Korean, Arabic, Simplified Chinese, Russian, Hindi, Portuguese, Dutch, Turkish and Hebrew. State the required language and terminology rather than assuming uniform performance across dialects. For a reusable workflow, specify the final structure and which source evidence each field should carry. Pro can return plausible but incorrect claims or code that has not been executed; supplying explicit facts and keeping tool results distinct from proposals makes the output easier to use and verify.
", "aboutText": "Amazon Nova Pro is the balanced multimodal understanding model in Amazon’s first-generation Nova family. It combines text, image and video understanding for tasks ranging from document question answering and visual analysis to software work and agent workflows. Its output is text: an explanation, extracted information, code, a plan or a tool request. Pro sits between the lighter Nova Lite and the more demanding long-context work addressed by Premier; this profile describes the original Pro v1 edition rather than a Nova 2 model.\n\nThe first-generation Nova guide lists a 300K-token context window and a maximum output of 10K tokens. Its documented knowledge cutoff is October 2024. A practical workflow can combine reference passages, document content, visual evidence and recent conversation, then return a compact result. For a technical review, supply the relevant code, observed behaviour and constraints and ask for a proposed change with reasons. For a report, name the sources and fields to compare. Separate the evidence from instructions so the model can distinguish what the documents state from the conclusion you want it to investigate.\n\nAmazon documents Pro’s ability to answer visual questions, classify or summarise images and return bounding boxes for specified objects. The first-generation image guide uses a [0, 1000) coordinate scale, converted to original image dimensions by the consuming application. Images are rescaled automatically, with a documented maximum resolution of 8,000 × 8,000 pixels. This supports work such as identifying an element in a screenshot or describing a diagram. Preserve readable text and key visual context, and ask for the relevant observations before requesting an interpretation.\n\nThe supported producer image formats include PNG, JPG/JPEG, GIF and WebP. The document workflow accepts PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-based formats contribute text, while PDF and DOCX can be interpreted together with visual elements such as charts and tables. The document guide permits up to five documents and limits each text document to 4.5 MB. It excludes PDF content using CMYK or SVG images and unsupported encodings such as JPEG2000 and JBIG2. Where a task needs only the words in a PDF, extracted text provides a simpler input than page-level visual reading. 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\nPro can analyse common video formats including MP4, MOV, MKV and WebM. Its version1 sampling strategy uses one frame per second for clips up to 16 minutes, then 960 frames distributed across longer clips. That favours scene-level summaries over precise analysis of very rapid actions, especially as the video grows longer. Amazon recommends keeping higher-motion clips below 16 minutes and low-motion clips below one hour. Supply a relevant segment and identify the visible event or relationship to inspect; a transcript should carry spoken information because the documented input modalities do not include audio. The producer also states that this model does not identify or name people in images, documents or videos.\n\nPro supports response streaming, client-executed function calling and retrieval-augmented tasks. It also supports 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. Describe the tools and their arguments, let the application execute requests, and return observations or errors before asking the model to continue. First-generation Nova can be prompted to work through a solution in stages, but that is distinct from Nova 2 Lite’s separately configured extended-thinking modes and built-in tools. Pro also serves as a distillation teacher for Nova Micro and Lite, and Amazon documents custom fine-tuning of Pro; those custom models retain their own identities.\n\nThe version1 guide describes training across more than 200 languages with optimisation for 15, including English, German, Spanish, French, Italian, Japanese, Korean, Arabic, Simplified Chinese, Russian, Hindi, Portuguese, Dutch, Turkish and Hebrew. State the required language and terminology rather than assuming uniform performance across dialects. For a reusable workflow, specify the final structure and which source evidence each field should carry. Pro can return plausible but incorrect claims or code that has not been executed; supplying explicit facts and keeping tool results distinct from proposals makes the output easier to use and verify.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Compare supplier delivery terms\n\nCompare these supplier notes for a purchasing manager. Note A: 120 units, delivery within 14 calendar days, damaged units reported within 48 hours. Note B: 120 units, delivery within 10 business days, damage reported within five calendar days. Give a three-row comparison and identify what prevents a reliable delivery-date comparison.A table covering quantity, delivery timing and damage reporting, followed by one clarification about the delivery calendar or start date.The answer preserves calendar versus business days and does not invent arrival dates.amazon/nova-pro-v1Amazon Nova Pro is the balanced first-generation Nova model for reasoning across text, images, documents and video. It produces text for visual analysis, software tasks, document workflows and agents that combine supplied evidence with tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Amazon Nova Pro is the balanced multimodal understanding model in Amazon’s first-generation Nova family. It combines text, image and video understanding for tasks ranging from document question answering and visual analysis to software work and agent workflows. Its output is text: an explanation, extracted information, code, a plan or a tool request. Pro sits between the lighter Nova Lite and the more demanding long-context work addressed by Premier; this profile describes the original Pro v1 edition rather than a Nova 2 model.
The first-generation Nova guide lists a 300K-token context window and a maximum output of 10K tokens. Its documented knowledge cutoff is October 2024. A practical workflow can combine reference passages, document content, visual evidence and recent conversation, then return a compact result. For a technical review, supply the relevant code, observed behaviour and constraints and ask for a proposed change with reasons. For a report, name the sources and fields to compare. Separate the evidence from instructions so the model can distinguish what the documents state from the conclusion you want it to investigate.
Amazon documents Pro’s ability to answer visual questions, classify or summarise images and return bounding boxes for specified objects. The first-generation image guide uses a [0, 1000) coordinate scale, converted to original image dimensions by the consuming application. Images are rescaled automatically, with a documented maximum resolution of 8,000 × 8,000 pixels. This supports work such as identifying an element in a screenshot or describing a diagram. Preserve readable text and key visual context, and ask for the relevant observations before requesting an interpretation.
The supported producer image formats include PNG, JPG/JPEG, GIF and WebP. The document workflow accepts PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-based formats contribute text, while PDF and DOCX can be interpreted together with visual elements such as charts and tables. The document guide permits up to five documents and limits each text document to 4.5 MB. It excludes PDF content using CMYK or SVG images and unsupported encodings such as JPEG2000 and JBIG2. Where a task needs only the words in a PDF, extracted text provides a simpler input than page-level visual reading. 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.
Pro can analyse common video formats including MP4, MOV, MKV and WebM. Its version1 sampling strategy uses one frame per second for clips up to 16 minutes, then 960 frames distributed across longer clips. That favours scene-level summaries over precise analysis of very rapid actions, especially as the video grows longer. Amazon recommends keeping higher-motion clips below 16 minutes and low-motion clips below one hour. Supply a relevant segment and identify the visible event or relationship to inspect; a transcript should carry spoken information because the documented input modalities do not include audio. The producer also states that this model does not identify or name people in images, documents or videos.
Pro supports response streaming, client-executed function calling and retrieval-augmented tasks. It also supports 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. Describe the tools and their arguments, let the application execute requests, and return observations or errors before asking the model to continue. First-generation Nova can be prompted to work through a solution in stages, but that is distinct from Nova 2 Lite’s separately configured extended-thinking modes and built-in tools. Pro also serves as a distillation teacher for Nova Micro and Lite, and Amazon documents custom fine-tuning of Pro; those custom models retain their own identities.
The version1 guide describes training across more than 200 languages with optimisation for 15, including English, German, Spanish, French, Italian, Japanese, Korean, Arabic, Simplified Chinese, Russian, Hindi, Portuguese, Dutch, Turkish and Hebrew. State the required language and terminology rather than assuming uniform performance across dialects. For a reusable workflow, specify the final structure and which source evidence each field should carry. Pro can return plausible but incorrect claims or code that has not been executed; supplying explicit facts and keeping tool results distinct from proposals makes the output easier to use and verify.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits amazon/nova-pro-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 $0.0016 / 1K tokens Output · Output tokens $0.0064 / 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 $0.0016 / 1K tokens Output · Output tokens $0.0064 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "amazon/nova-pro-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-pro-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-pro-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-pro-v1
Use the method paths shown above.
amazon/nova-pro-v1Amazon Nova Pro is the balanced first-generation Nova model for reasoning across text, images, documents and video. It produces text for visual analysis, software tasks, document workflows and agents that combine supplied evidence with tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Amazon Nova Pro is the balanced multimodal understanding model in Amazon’s first-generation Nova family. It combines text, image and video understanding for tasks ranging from document question answering and visual analysis to software work and agent workflows. Its output is text: an explanation, extracted information, code, a plan or a tool request. Pro sits between the lighter Nova Lite and the more demanding long-context work addressed by Premier; this profile describes the original Pro v1 edition rather than a Nova 2 model.
The first-generation Nova guide lists a 300K-token context window and a maximum output of 10K tokens. Its documented knowledge cutoff is October 2024. A practical workflow can combine reference passages, document content, visual evidence and recent conversation, then return a compact result. For a technical review, supply the relevant code, observed behaviour and constraints and ask for a proposed change with reasons. For a report, name the sources and fields to compare. Separate the evidence from instructions so the model can distinguish what the documents state from the conclusion you want it to investigate.
Amazon documents Pro’s ability to answer visual questions, classify or summarise images and return bounding boxes for specified objects. The first-generation image guide uses a [0, 1000) coordinate scale, converted to original image dimensions by the consuming application. Images are rescaled automatically, with a documented maximum resolution of 8,000 × 8,000 pixels. This supports work such as identifying an element in a screenshot or describing a diagram. Preserve readable text and key visual context, and ask for the relevant observations before requesting an interpretation.
The supported producer image formats include PNG, JPG/JPEG, GIF and WebP. The document workflow accepts PDF, DOC/DOCX, CSV, XLS/XLSX, HTML, TXT and Markdown. Text-based formats contribute text, while PDF and DOCX can be interpreted together with visual elements such as charts and tables. The document guide permits up to five documents and limits each text document to 4.5 MB. It excludes PDF content using CMYK or SVG images and unsupported encodings such as JPEG2000 and JBIG2. Where a task needs only the words in a PDF, extracted text provides a simpler input than page-level visual reading. 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.
Pro can analyse common video formats including MP4, MOV, MKV and WebM. Its version1 sampling strategy uses one frame per second for clips up to 16 minutes, then 960 frames distributed across longer clips. That favours scene-level summaries over precise analysis of very rapid actions, especially as the video grows longer. Amazon recommends keeping higher-motion clips below 16 minutes and low-motion clips below one hour. Supply a relevant segment and identify the visible event or relationship to inspect; a transcript should carry spoken information because the documented input modalities do not include audio. The producer also states that this model does not identify or name people in images, documents or videos.
Pro supports response streaming, client-executed function calling and retrieval-augmented tasks. It also supports 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. Describe the tools and their arguments, let the application execute requests, and return observations or errors before asking the model to continue. First-generation Nova can be prompted to work through a solution in stages, but that is distinct from Nova 2 Lite’s separately configured extended-thinking modes and built-in tools. Pro also serves as a distillation teacher for Nova Micro and Lite, and Amazon documents custom fine-tuning of Pro; those custom models retain their own identities.
The version1 guide describes training across more than 200 languages with optimisation for 15, including English, German, Spanish, French, Italian, Japanese, Korean, Arabic, Simplified Chinese, Russian, Hindi, Portuguese, Dutch, Turkish and Hebrew. State the required language and terminology rather than assuming uniform performance across dialects. For a reusable workflow, specify the final structure and which source evidence each field should carry. Pro can return plausible but incorrect claims or code that has not been executed; supplying explicit facts and keeping tool results distinct from proposals makes the output easier to use and verify.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits amazon/nova-pro-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 $0.0016 / 1K tokens Output · Output tokens $0.0064 / 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 $0.0016 / 1K tokens Output · Output tokens $0.0064 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "amazon/nova-pro-v1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-pro-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-pro-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-pro-v1
Use the method paths shown above.
Technical example in English
Compare supplier delivery terms\n\nCompare these supplier notes for a purchasing manager. Note A: 120 units, delivery within 14 calendar days, damaged units reported within 48 hours. Note B: 120 units, delivery within 10 business days, damage reported within five calendar days. Give a three-row comparison and identify what prevents a reliable delivery-date comparison.A table covering quantity, delivery timing and damage reporting, followed by one clarification about the delivery calendar or start date.The answer preserves calendar versus business days and does not invent arrival dates.