Perceptron Mk1.5 is Perceptron’s multimodal model for visual understanding, temporal grounding and embodied-agent tasks. It accepts text, images, video and audio and returns text, spatial or temporal annotations, structured responses and function-call content. Its current maker specification lists a 36,864-token context and an 8,192-token maximum output; those exact limits are more specific than the launch article’s rounded 32K description.
A defining addition is tracking objects through video as timestamped geometry. Give the target a clear description and state what the result should establish, such as when an item enters a scene, where it moves or which interval contains a particular action. For first-person footage, the producer emphasises hand tracking and segmentation into subtasks, useful for analysing what an operator is doing over time.
The documented outputs include points, boxes and polygons for spatial grounding, clips for temporal intervals and track containers for object movement. Track is a container in generated annotation markup, not a separate annotation-format value. Track waypoints can be sparse: a returned track does not guarantee a box for every source frame or continuous visibility of the object. Retain the original media and coordinate or timestamp association so those results can be checked against the actual scene.
Mk1.5 adds native audio understanding, including transcription, sound-event detection, summaries and questions about a recording. The producer accepts WAV, MP3 and FLAC. Its per-item audio limit is 16,384 audio tokens, approximately 21.8 minutes at the documented rate of about 750 tokens per minute. Audio shares context with other inputs and the output budget, so a request can fill the context before that per-item limit is reached.
For a video whose soundtrack matters, the maker’s workflow explicitly enables audio in video. State whether the task concerns speech, a sound event, the visible scene or their relationship. The output is text and structured content; Mk1.5 does not generate speech audio. For transcription, preserve the requested language and timing association rather than treating a visual caption as a transcript.
The producer supports comparisons across media inputs. Label the items and retain asset associations. The optional asset_idx identifies a media occurrence available at that point in the conversation, not a persistent file identifier. If no explicit or inherited selector is present, an annotation refers to the last available asset at generation time. These conventions matter when a task compares two cameras, pages or recordings. The producer’s request limit is 256 media units. Each frame in a video_frames group counts toward that limit, although the group occupies one asset index; enabling a video’s soundtrack does not add another asset.
The maker supports final responses constrained by JSON Schema or a regex. Define the fields or pattern and review the returned values against the source. It also documents Multilook for independent prompts over shared context, a separate producer workflow from ordinary single-completion chat.
Mk1.5 can choose supplied functions described with names, purposes and JSON Schemas. The application executes the proposed calls and returns observations. Define allowed actions and a completion criterion for an embodied or interface task, then use the new visual state or tool result as the evidence for the next step. Reasoning effort is configurable in the producer profile.
Function tools cannot be declared in the same request as JSON Schema or regex-constrained output; the maker instructs requesting a constrained final answer after the tool loop. Inspect the finish reason before using the result, since length termination can mean incomplete output.
A useful artifact is a grounded scene explanation, timed transcript, object annotation or evidence-backed action proposal. Check geometry against the media, keep observed details distinct from interpretation and retain Mk1.5’s exact audio, tracking and tool capabilities separately from the earlier Mk1 edition.
", "aboutText": "Perceptron Mk1.5 is Perceptron’s multimodal model for visual understanding, temporal grounding and embodied-agent tasks. It accepts text, images, video and audio and returns text, spatial or temporal annotations, structured responses and function-call content. Its current maker specification lists a 36,864-token context and an 8,192-token maximum output; those exact limits are more specific than the launch article’s rounded 32K description.\n\n### Video and object tracking\n\nA defining addition is tracking objects through video as timestamped geometry. Give the target a clear description and state what the result should establish, such as when an item enters a scene, where it moves or which interval contains a particular action. For first-person footage, the producer emphasises hand tracking and segmentation into subtasks, useful for analysing what an operator is doing over time.\n\nThe documented outputs include points, boxes and polygons for spatial grounding, clips for temporal intervals and track containers for object movement. Track is a container in generated annotation markup, not a separate annotation-format value. Track waypoints can be sparse: a returned track does not guarantee a box for every source frame or continuous visibility of the object. Retain the original media and coordinate or timestamp association so those results can be checked against the actual scene.\n\n### Audio and combined evidence\n\nMk1.5 adds native audio understanding, including transcription, sound-event detection, summaries and questions about a recording. The producer accepts WAV, MP3 and FLAC. Its per-item audio limit is 16,384 audio tokens, approximately 21.8 minutes at the documented rate of about 750 tokens per minute. Audio shares context with other inputs and the output budget, so a request can fill the context before that per-item limit is reached.\n\nFor a video whose soundtrack matters, the maker’s workflow explicitly enables audio in video. State whether the task concerns speech, a sound event, the visible scene or their relationship. The output is text and structured content; Mk1.5 does not generate speech audio. For transcription, preserve the requested language and timing association rather than treating a visual caption as a transcript.\n\n### Multiple assets and structured answers\n\nThe producer supports comparisons across media inputs. Label the items and retain asset associations. The optional asset_idx identifies a media occurrence available at that point in the conversation, not a persistent file identifier. If no explicit or inherited selector is present, an annotation refers to the last available asset at generation time. These conventions matter when a task compares two cameras, pages or recordings. The producer’s request limit is 256 media units. Each frame in a video_frames group counts toward that limit, although the group occupies one asset index; enabling a video’s soundtrack does not add another asset.\n\nThe maker supports final responses constrained by JSON Schema or a regex. Define the fields or pattern and review the returned values against the source. It also documents Multilook for independent prompts over shared context, a separate producer workflow from ordinary single-completion chat.\n\n### Functions and reasoning\n\nMk1.5 can choose supplied functions described with names, purposes and JSON Schemas. The application executes the proposed calls and returns observations. Define allowed actions and a completion criterion for an embodied or interface task, then use the new visual state or tool result as the evidence for the next step. Reasoning effort is configurable in the producer profile.\n\nFunction tools cannot be declared in the same request as JSON Schema or regex-constrained output; the maker instructs requesting a constrained final answer after the tool loop. Inspect the finish reason before using the result, since length termination can mean incomplete output.\n\nA useful artifact is a grounded scene explanation, timed transcript, object annotation or evidence-backed action proposal. Check geometry against the media, keep observed details distinct from interpretation and retain Mk1.5’s exact audio, tracking and tool capabilities separately from the earlier Mk1 edition.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Summarize a timed handling sequence\n\nUse these written frame notes, not unseen footage: 00:02 operator picks up a red box; 00:05 places it on scale; 00:08 removes it; 00:11 places it on shelf. Return the ordered subtasks and the observed interval when the box is on the scale. State the sampling limitation instead of claiming exact continuous motion between notes.An ordered subtask list and a scale interval explicitly bounded by the supplied observations.Timestamps stay attached to their notes, and the answer does not invent intermediate geometry or continuous visibility.perceptron/perceptron-mk1.5Perceptron Mk1.5 understands text, images, video and audio for visual and embodied tasks. It returns text, spatial or temporal annotations, object tracks and proposed function calls, with a 36,864-token producer context and an 8,192-token maximum output.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Perceptron Mk1.5 is Perceptron’s multimodal model for visual understanding, temporal grounding and embodied-agent tasks. It accepts text, images, video and audio and returns text, spatial or temporal annotations, structured responses and function-call content. Its current maker specification lists a 36,864-token context and an 8,192-token maximum output; those exact limits are more specific than the launch article’s rounded 32K description.
A defining addition is tracking objects through video as timestamped geometry. Give the target a clear description and state what the result should establish, such as when an item enters a scene, where it moves or which interval contains a particular action. For first-person footage, the producer emphasises hand tracking and segmentation into subtasks, useful for analysing what an operator is doing over time.
The documented outputs include points, boxes and polygons for spatial grounding, clips for temporal intervals and track containers for object movement. Track is a container in generated annotation markup, not a separate annotation-format value. Track waypoints can be sparse: a returned track does not guarantee a box for every source frame or continuous visibility of the object. Retain the original media and coordinate or timestamp association so those results can be checked against the actual scene.
Mk1.5 adds native audio understanding, including transcription, sound-event detection, summaries and questions about a recording. The producer accepts WAV, MP3 and FLAC. Its per-item audio limit is 16,384 audio tokens, approximately 21.8 minutes at the documented rate of about 750 tokens per minute. Audio shares context with other inputs and the output budget, so a request can fill the context before that per-item limit is reached.
For a video whose soundtrack matters, the maker’s workflow explicitly enables audio in video. State whether the task concerns speech, a sound event, the visible scene or their relationship. The output is text and structured content; Mk1.5 does not generate speech audio. For transcription, preserve the requested language and timing association rather than treating a visual caption as a transcript.
The producer supports comparisons across media inputs. Label the items and retain asset associations. The optional asset_idx identifies a media occurrence available at that point in the conversation, not a persistent file identifier. If no explicit or inherited selector is present, an annotation refers to the last available asset at generation time. These conventions matter when a task compares two cameras, pages or recordings. The producer’s request limit is 256 media units. Each frame in a video_frames group counts toward that limit, although the group occupies one asset index; enabling a video’s soundtrack does not add another asset.
The maker supports final responses constrained by JSON Schema or a regex. Define the fields or pattern and review the returned values against the source. It also documents Multilook for independent prompts over shared context, a separate producer workflow from ordinary single-completion chat.
Mk1.5 can choose supplied functions described with names, purposes and JSON Schemas. The application executes the proposed calls and returns observations. Define allowed actions and a completion criterion for an embodied or interface task, then use the new visual state or tool result as the evidence for the next step. Reasoning effort is configurable in the producer profile.
Function tools cannot be declared in the same request as JSON Schema or regex-constrained output; the maker instructs requesting a constrained final answer after the tool loop. Inspect the finish reason before using the result, since length termination can mean incomplete output.
A useful artifact is a grounded scene explanation, timed transcript, object annotation or evidence-backed action proposal. Check geometry against the media, keep observed details distinct from interpretation and retain Mk1.5’s exact audio, tracking and tool capabilities separately from the earlier Mk1 edition.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits perceptron/perceptron-mk1.5 | 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-mk1.5", "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-mk1.5',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-mk1.5',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-mk1.5
Use the method paths shown above.
perceptron/perceptron-mk1.5Perceptron Mk1.5 understands text, images, video and audio for visual and embodied tasks. It returns text, spatial or temporal annotations, object tracks and proposed function calls, with a 36,864-token producer context and an 8,192-token maximum output.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Perceptron Mk1.5 is Perceptron’s multimodal model for visual understanding, temporal grounding and embodied-agent tasks. It accepts text, images, video and audio and returns text, spatial or temporal annotations, structured responses and function-call content. Its current maker specification lists a 36,864-token context and an 8,192-token maximum output; those exact limits are more specific than the launch article’s rounded 32K description.
A defining addition is tracking objects through video as timestamped geometry. Give the target a clear description and state what the result should establish, such as when an item enters a scene, where it moves or which interval contains a particular action. For first-person footage, the producer emphasises hand tracking and segmentation into subtasks, useful for analysing what an operator is doing over time.
The documented outputs include points, boxes and polygons for spatial grounding, clips for temporal intervals and track containers for object movement. Track is a container in generated annotation markup, not a separate annotation-format value. Track waypoints can be sparse: a returned track does not guarantee a box for every source frame or continuous visibility of the object. Retain the original media and coordinate or timestamp association so those results can be checked against the actual scene.
Mk1.5 adds native audio understanding, including transcription, sound-event detection, summaries and questions about a recording. The producer accepts WAV, MP3 and FLAC. Its per-item audio limit is 16,384 audio tokens, approximately 21.8 minutes at the documented rate of about 750 tokens per minute. Audio shares context with other inputs and the output budget, so a request can fill the context before that per-item limit is reached.
For a video whose soundtrack matters, the maker’s workflow explicitly enables audio in video. State whether the task concerns speech, a sound event, the visible scene or their relationship. The output is text and structured content; Mk1.5 does not generate speech audio. For transcription, preserve the requested language and timing association rather than treating a visual caption as a transcript.
The producer supports comparisons across media inputs. Label the items and retain asset associations. The optional asset_idx identifies a media occurrence available at that point in the conversation, not a persistent file identifier. If no explicit or inherited selector is present, an annotation refers to the last available asset at generation time. These conventions matter when a task compares two cameras, pages or recordings. The producer’s request limit is 256 media units. Each frame in a video_frames group counts toward that limit, although the group occupies one asset index; enabling a video’s soundtrack does not add another asset.
The maker supports final responses constrained by JSON Schema or a regex. Define the fields or pattern and review the returned values against the source. It also documents Multilook for independent prompts over shared context, a separate producer workflow from ordinary single-completion chat.
Mk1.5 can choose supplied functions described with names, purposes and JSON Schemas. The application executes the proposed calls and returns observations. Define allowed actions and a completion criterion for an embodied or interface task, then use the new visual state or tool result as the evidence for the next step. Reasoning effort is configurable in the producer profile.
Function tools cannot be declared in the same request as JSON Schema or regex-constrained output; the maker instructs requesting a constrained final answer after the tool loop. Inspect the finish reason before using the result, since length termination can mean incomplete output.
A useful artifact is a grounded scene explanation, timed transcript, object annotation or evidence-backed action proposal. Check geometry against the media, keep observed details distinct from interpretation and retain Mk1.5’s exact audio, tracking and tool capabilities separately from the earlier Mk1 edition.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits perceptron/perceptron-mk1.5 | 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 $0.003 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "perceptron/perceptron-mk1.5",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-mk1.5', '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-mk1.5', '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-mk1.5
Use the method paths shown above.
Technical example in English
Summarize a timed handling sequence\n\nUse these written frame notes, not unseen footage: 00:02 operator picks up a red box; 00:05 places it on scale; 00:08 removes it; 00:11 places it on shelf. Return the ordered subtasks and the observed interval when the box is on the scale. State the sampling limitation instead of claiming exact continuous motion between notes.An ordered subtask list and a scale interval explicitly bounded by the supplied observations.Timestamps stay attached to their notes, and the answer does not invent intermediate geometry or continuous visibility.