Perceptron Mk1 is Perceptron’s model for image and video understanding and embodied reasoning. It analyses visual source material in relation to a written question and returns text and structured spatial or temporal annotations. Its maker profile has a 32K multimodal context and a hybrid reasoning mode that can be turned off for tasks that do not need a thinking trace.
The manufacturer develops Mk1 to explain events across time rather than only label a frame. A sports sequence, a cooking demonstration or an operator’s task can produce a structured account of what happened and when. The producer documents dynamic video analysis at up to two frames per second. This sampling profile is distinct from the source video’s original frame rate.
For an event-location task, describe the action and the interval you need. An illustrative instruction is: “Identify the moments where the item is placed on the shelf, return the time intervals and explain the visible evidence for each.” Keep the source video and time references together so a clipping annotation or event interval can be checked before another application uses it.
Mk1 supports in-context visual learning from a reference image or video, followed by locating matching instances in new material. Define what makes an instance relevant and preserve the reference label. For a comparison, provide both pieces of media and state the criteria: the object, action, condition or document detail to compare.
This is a way to prepare the task through supplied examples rather than an assumption that a separate fine-tuning process has run. If the scenes differ, ask the output to identify which input supports each finding. A visible similarity should remain distinct from an inferred conclusion about an event.
The producer’s image capabilities include pointing, counting, text recognition and reading analogue or digital instruments. For an instrument, preserve its scale, units and readable markings; for a count, define the region and category. Mk1 also extracts complex documents into HTML, JSON or Markdown while preserving layout relationships, tables and hierarchy.
Provide a readable page image and state the fields or question. A useful result retains the source association and distinguishes the extracted wording from interpretation. Small text, occlusion and ambiguous scene evidence should be addressed in how the source is prepared and the answer is reviewed.
The maker trains points, boxes, polygons, tracks and clips as first-class structured outputs alongside text. These annotations can supply targets, constraints, task boundaries or observed success/failure information to a surrounding robotics or analysis workflow. A multi-camera task should label the views and preserve the association between each annotation and its source.
The model interprets the observations and produces the grounded result; the application or control system decides how to use it and performs any physical or interface action. A proposed target or annotated interval is distinct from an executed operation or an exported media file.
Budget video representation, image content, the prompt, history and generated output within the 32K context. Ask for the final artifact and the evidence that establishes each result, rather than expecting an unrelated source collection to define its own goal. Check coordinates, time intervals and extracted values against the original media.
Mk1 retains its own named edition and visual profile. Native audio input, the current Mk1.5 request constraints and its new tool and tracking workflow details should not be inferred for this earlier release. The useful deliverable is a reviewable scene description, document record or spatial/temporal annotation tied to the supplied visual evidence.
", "aboutText": "Perceptron Mk1 is Perceptron’s model for image and video understanding and embodied reasoning. It analyses visual source material in relation to a written question and returns text and structured spatial or temporal annotations. Its maker profile has a 32K multimodal context and a hybrid reasoning mode that can be turned off for tasks that do not need a thinking trace.\n\n### Temporal reasoning and grounding\n\nThe manufacturer develops Mk1 to explain events across time rather than only label a frame. A sports sequence, a cooking demonstration or an operator’s task can produce a structured account of what happened and when. The producer documents dynamic video analysis at up to two frames per second. This sampling profile is distinct from the source video’s original frame rate.\n\nFor an event-location task, describe the action and the interval you need. An illustrative instruction is: “Identify the moments where the item is placed on the shelf, return the time intervals and explain the visible evidence for each.” Keep the source video and time references together so a clipping annotation or event interval can be checked before another application uses it.\n\n### Reference examples and comparison\n\nMk1 supports in-context visual learning from a reference image or video, followed by locating matching instances in new material. Define what makes an instance relevant and preserve the reference label. For a comparison, provide both pieces of media and state the criteria: the object, action, condition or document detail to compare.\n\nThis is a way to prepare the task through supplied examples rather than an assumption that a separate fine-tuning process has run. If the scenes differ, ask the output to identify which input supports each finding. A visible similarity should remain distinct from an inferred conclusion about an event.\n\n### Image and document tasks\n\nThe producer’s image capabilities include pointing, counting, text recognition and reading analogue or digital instruments. For an instrument, preserve its scale, units and readable markings; for a count, define the region and category. Mk1 also extracts complex documents into HTML, JSON or Markdown while preserving layout relationships, tables and hierarchy.\n\nProvide a readable page image and state the fields or question. A useful result retains the source association and distinguishes the extracted wording from interpretation. Small text, occlusion and ambiguous scene evidence should be addressed in how the source is prepared and the answer is reviewed.\n\n### Spatial primitives and embodied work\n\nThe maker trains points, boxes, polygons, tracks and clips as first-class structured outputs alongside text. These annotations can supply targets, constraints, task boundaries or observed success/failure information to a surrounding robotics or analysis workflow. A multi-camera task should label the views and preserve the association between each annotation and its source.\n\nThe model interprets the observations and produces the grounded result; the application or control system decides how to use it and performs any physical or interface action. A proposed target or annotated interval is distinct from an executed operation or an exported media file.\n\n### Limits and edition scope\n\nBudget video representation, image content, the prompt, history and generated output within the 32K context. Ask for the final artifact and the evidence that establishes each result, rather than expecting an unrelated source collection to define its own goal. Check coordinates, time intervals and extracted values against the original media.\n\nMk1 retains its own named edition and visual profile. Native audio input, the current Mk1.5 request constraints and its new tool and tracking workflow details should not be inferred for this earlier release. The useful deliverable is a reviewable scene description, document record or spatial/temporal annotation tied to the supplied visual evidence.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Annotate a transcribed event sequence\n\nUse these written observations from clip C: [00:02] hand grips a cup; [00:05] cup rests on shelf; [00:08] hand releases cup; [00:11] hand leaves frame. Return the interval from shelf contact to release and cite the two observations that bound it. State that you are using notes rather than inspecting video.A textual interval annotation with source timestamps, bounding evidence and the stated notes-only basis.Check the interval uses contact and release timestamps rather than grip or departure.perceptron/perceptron-mk1Perceptron Mk1 is Perceptron’s image and video model for temporal understanding, spatial grounding and embodied reasoning. It produces text and structured annotations for scenes, documents and visible actions, with a 32K multimodal context and optional reasoning.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Perceptron Mk1 is Perceptron’s model for image and video understanding and embodied reasoning. It analyses visual source material in relation to a written question and returns text and structured spatial or temporal annotations. Its maker profile has a 32K multimodal context and a hybrid reasoning mode that can be turned off for tasks that do not need a thinking trace.
The manufacturer develops Mk1 to explain events across time rather than only label a frame. A sports sequence, a cooking demonstration or an operator’s task can produce a structured account of what happened and when. The producer documents dynamic video analysis at up to two frames per second. This sampling profile is distinct from the source video’s original frame rate.
For an event-location task, describe the action and the interval you need. An illustrative instruction is: “Identify the moments where the item is placed on the shelf, return the time intervals and explain the visible evidence for each.” Keep the source video and time references together so a clipping annotation or event interval can be checked before another application uses it.
Mk1 supports in-context visual learning from a reference image or video, followed by locating matching instances in new material. Define what makes an instance relevant and preserve the reference label. For a comparison, provide both pieces of media and state the criteria: the object, action, condition or document detail to compare.
This is a way to prepare the task through supplied examples rather than an assumption that a separate fine-tuning process has run. If the scenes differ, ask the output to identify which input supports each finding. A visible similarity should remain distinct from an inferred conclusion about an event.
The producer’s image capabilities include pointing, counting, text recognition and reading analogue or digital instruments. For an instrument, preserve its scale, units and readable markings; for a count, define the region and category. Mk1 also extracts complex documents into HTML, JSON or Markdown while preserving layout relationships, tables and hierarchy.
Provide a readable page image and state the fields or question. A useful result retains the source association and distinguishes the extracted wording from interpretation. Small text, occlusion and ambiguous scene evidence should be addressed in how the source is prepared and the answer is reviewed.
The maker trains points, boxes, polygons, tracks and clips as first-class structured outputs alongside text. These annotations can supply targets, constraints, task boundaries or observed success/failure information to a surrounding robotics or analysis workflow. A multi-camera task should label the views and preserve the association between each annotation and its source.
The model interprets the observations and produces the grounded result; the application or control system decides how to use it and performs any physical or interface action. A proposed target or annotated interval is distinct from an executed operation or an exported media file.
Budget video representation, image content, the prompt, history and generated output within the 32K context. Ask for the final artifact and the evidence that establishes each result, rather than expecting an unrelated source collection to define its own goal. Check coordinates, time intervals and extracted values against the original media.
Mk1 retains its own named edition and visual profile. Native audio input, the current Mk1.5 request constraints and its new tool and tracking workflow details should not be inferred for this earlier release. The useful deliverable is a reviewable scene description, document record or spatial/temporal annotation tied to the supplied visual evidence.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits perceptron/perceptron-mk1 | 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 $0.0003 / 1K tokens Output · Output tokens $0.003 / 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 $0.0003 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "perceptron/perceptron-mk1", "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='perceptron/perceptron-mk1',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='perceptron/perceptron-mk1',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 perceptron/perceptron-mk1
Use the method paths shown above.
perceptron/perceptron-mk1Perceptron Mk1 is Perceptron’s image and video model for temporal understanding, spatial grounding and embodied reasoning. It produces text and structured annotations for scenes, documents and visible actions, with a 32K multimodal context and optional reasoning.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Perceptron Mk1 is Perceptron’s model for image and video understanding and embodied reasoning. It analyses visual source material in relation to a written question and returns text and structured spatial or temporal annotations. Its maker profile has a 32K multimodal context and a hybrid reasoning mode that can be turned off for tasks that do not need a thinking trace.
The manufacturer develops Mk1 to explain events across time rather than only label a frame. A sports sequence, a cooking demonstration or an operator’s task can produce a structured account of what happened and when. The producer documents dynamic video analysis at up to two frames per second. This sampling profile is distinct from the source video’s original frame rate.
For an event-location task, describe the action and the interval you need. An illustrative instruction is: “Identify the moments where the item is placed on the shelf, return the time intervals and explain the visible evidence for each.” Keep the source video and time references together so a clipping annotation or event interval can be checked before another application uses it.
Mk1 supports in-context visual learning from a reference image or video, followed by locating matching instances in new material. Define what makes an instance relevant and preserve the reference label. For a comparison, provide both pieces of media and state the criteria: the object, action, condition or document detail to compare.
This is a way to prepare the task through supplied examples rather than an assumption that a separate fine-tuning process has run. If the scenes differ, ask the output to identify which input supports each finding. A visible similarity should remain distinct from an inferred conclusion about an event.
The producer’s image capabilities include pointing, counting, text recognition and reading analogue or digital instruments. For an instrument, preserve its scale, units and readable markings; for a count, define the region and category. Mk1 also extracts complex documents into HTML, JSON or Markdown while preserving layout relationships, tables and hierarchy.
Provide a readable page image and state the fields or question. A useful result retains the source association and distinguishes the extracted wording from interpretation. Small text, occlusion and ambiguous scene evidence should be addressed in how the source is prepared and the answer is reviewed.
The maker trains points, boxes, polygons, tracks and clips as first-class structured outputs alongside text. These annotations can supply targets, constraints, task boundaries or observed success/failure information to a surrounding robotics or analysis workflow. A multi-camera task should label the views and preserve the association between each annotation and its source.
The model interprets the observations and produces the grounded result; the application or control system decides how to use it and performs any physical or interface action. A proposed target or annotated interval is distinct from an executed operation or an exported media file.
Budget video representation, image content, the prompt, history and generated output within the 32K context. Ask for the final artifact and the evidence that establishes each result, rather than expecting an unrelated source collection to define its own goal. Check coordinates, time intervals and extracted values against the original media.
Mk1 retains its own named edition and visual profile. Native audio input, the current Mk1.5 request constraints and its new tool and tracking workflow details should not be inferred for this earlier release. The useful deliverable is a reviewable scene description, document record or spatial/temporal annotation tied to the supplied visual evidence.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits perceptron/perceptron-mk1 | 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 $0.0003 / 1K tokens Output · Output tokens $0.003 / 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 $0.0003 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "perceptron/perceptron-mk1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'perceptron/perceptron-mk1', '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': 'perceptron/perceptron-mk1', '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 perceptron/perceptron-mk1
Use the method paths shown above.
Technical example in English
Annotate a transcribed event sequence\n\nUse these written observations from clip C: [00:02] hand grips a cup; [00:05] cup rests on shelf; [00:08] hand releases cup; [00:11] hand leaves frame. Return the interval from shelf contact to release and cite the two observations that bound it. State that you are using notes rather than inspecting video.A textual interval annotation with source timestamps, bounding evidence and the stated notes-only basis.Check the interval uses contact and release timestamps rather than grip or departure.