Magnum v4 72B is Anthracite’s prose-focused fine-tune of Qwen2.5-72B-Instruct. The producer describes it as the experimental instruct-based model that began the v4 family. It works with written prompts and conversation to produce text, with particular attention to narrative voice and character interaction. This edition is distinct from the other sizes in the Magnum v4 series.
The published checkpoint uses a causal language-model architecture and an 80-layer configuration with 64 query attention heads and eight key/value heads. Its maximum position count is 32,768, and the training recipe also uses a sequence length of 32,768. This is the configuration of the Magnum release itself; it does not inherit a larger extended-context setting simply because the base model supports one.
Anthracite’s native prompting examples use ChatML with separate system, user and assistant turns. The system part can provide the character description, personality and scenario, while the user turn supplies the next contribution to the exchange. The producer’s narrative template asks the assistant to retain the persona while allowing it to develop, introduce events and secondary characters, and include dialogue, action and thoughts where appropriate.
The same template leaves the user’s character and choices to the user. It also discourages repetitive output and excessive ornamental prose unless the persona calls for that style. An out-of-character request switches the response to neutral plain text. These are concrete prompting choices for an interactive writing task, rather than separate automatic model modes.
For a character scene, prepare the character’s objective, the setting, the relationship to the other speaker and the last exchange. Request one continuation with a clear stopping point so the user has room to respond. For a prose revision, supply a paragraph and identify the change in tone or pacing, then ask for the revised passage while preserving the events and the speaker’s intent. A follow-up can provide a new character decision or editorial note without replacing the established scene.
The producer publishes a full-parameter fine-tuning recipe and a mixture of conversational and writing data. Use the finished output as a scene, dialogue turn or revision draft, and keep a compact record of the story facts that the next turn must retain. The creator’s emphasis is prose and narrative interaction; the base model’s name does not by itself establish additional visual, reasoning-control or tool-execution features for this fine-tuned edition.
", "aboutText": "Magnum v4 72B is Anthracite’s prose-focused fine-tune of Qwen2.5-72B-Instruct. The producer describes it as the experimental instruct-based model that began the v4 family. It works with written prompts and conversation to produce text, with particular attention to narrative voice and character interaction. This edition is distinct from the other sizes in the Magnum v4 series.\n\nThe published checkpoint uses a causal language-model architecture and an 80-layer configuration with 64 query attention heads and eight key/value heads. Its maximum position count is 32,768, and the training recipe also uses a sequence length of 32,768. This is the configuration of the Magnum release itself; it does not inherit a larger extended-context setting simply because the base model supports one.\n\nAnthracite’s native prompting examples use ChatML with separate system, user and assistant turns. The system part can provide the character description, personality and scenario, while the user turn supplies the next contribution to the exchange. The producer’s narrative template asks the assistant to retain the persona while allowing it to develop, introduce events and secondary characters, and include dialogue, action and thoughts where appropriate.\n\nThe same template leaves the user’s character and choices to the user. It also discourages repetitive output and excessive ornamental prose unless the persona calls for that style. An out-of-character request switches the response to neutral plain text. These are concrete prompting choices for an interactive writing task, rather than separate automatic model modes.\n\nFor a character scene, prepare the character’s objective, the setting, the relationship to the other speaker and the last exchange. Request one continuation with a clear stopping point so the user has room to respond. For a prose revision, supply a paragraph and identify the change in tone or pacing, then ask for the revised passage while preserving the events and the speaker’s intent. A follow-up can provide a new character decision or editorial note without replacing the established scene.\n\nThe producer publishes a full-parameter fine-tuning recipe and a mixture of conversational and writing data. Use the finished output as a scene, dialogue turn or revision draft, and keep a compact record of the story facts that the next turn must retain. The creator’s emphasis is prose and narrative interaction; the base model’s name does not by itself establish additional visual, reasoning-control or tool-execution features for this fine-tuned edition.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
A restrained character voice\n\nPlay archivist Nera in a quiet fantasy scene. She values precision and hides concern behind dry humour. I control her former apprentice, who asks to borrow a forbidden map. Write Nera's next two replies with a small physical action between them; end with a question and leave my character's reactions to me.Two replies in Nera's voice and a brief action beat, ending at a point where the player can respond.The replies retain dry humour and do not invent the apprentice's answer or actions.anthracite-org/magnum-v4-72bAnthracite’s Magnum v4 72B is a Qwen2.5-based text model tuned for expressive prose and character conversations. Its published ChatML templates guide narrative exchanges, dialogue and out-of-character replies, with a 32,768-position configuration.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Magnum v4 72B is Anthracite’s prose-focused fine-tune of Qwen2.5-72B-Instruct. The producer describes it as the experimental instruct-based model that began the v4 family. It works with written prompts and conversation to produce text, with particular attention to narrative voice and character interaction. This edition is distinct from the other sizes in the Magnum v4 series.
The published checkpoint uses a causal language-model architecture and an 80-layer configuration with 64 query attention heads and eight key/value heads. Its maximum position count is 32,768, and the training recipe also uses a sequence length of 32,768. This is the configuration of the Magnum release itself; it does not inherit a larger extended-context setting simply because the base model supports one.
Anthracite’s native prompting examples use ChatML with separate system, user and assistant turns. The system part can provide the character description, personality and scenario, while the user turn supplies the next contribution to the exchange. The producer’s narrative template asks the assistant to retain the persona while allowing it to develop, introduce events and secondary characters, and include dialogue, action and thoughts where appropriate.
The same template leaves the user’s character and choices to the user. It also discourages repetitive output and excessive ornamental prose unless the persona calls for that style. An out-of-character request switches the response to neutral plain text. These are concrete prompting choices for an interactive writing task, rather than separate automatic model modes.
For a character scene, prepare the character’s objective, the setting, the relationship to the other speaker and the last exchange. Request one continuation with a clear stopping point so the user has room to respond. For a prose revision, supply a paragraph and identify the change in tone or pacing, then ask for the revised passage while preserving the events and the speaker’s intent. A follow-up can provide a new character decision or editorial note without replacing the established scene.
The producer publishes a full-parameter fine-tuning recipe and a mixture of conversational and writing data. Use the finished output as a scene, dialogue turn or revision draft, and keep a compact record of the story facts that the next turn must retain. The creator’s emphasis is prose and narrative interaction; the base model’s name does not by itself establish additional visual, reasoning-control or tool-execution features for this fine-tuned edition.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits anthracite-org/magnum-v4-72b | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.005 / 1K tokens Output · Output tokens $0.01 / 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 $0.005 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "anthracite-org/magnum-v4-72b", "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='anthracite-org/magnum-v4-72b',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='anthracite-org/magnum-v4-72b',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 anthracite-org/magnum-v4-72b
Use the method paths shown above.
anthracite-org/magnum-v4-72bAnthracite’s Magnum v4 72B is a Qwen2.5-based text model tuned for expressive prose and character conversations. Its published ChatML templates guide narrative exchanges, dialogue and out-of-character replies, with a 32,768-position configuration.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Magnum v4 72B is Anthracite’s prose-focused fine-tune of Qwen2.5-72B-Instruct. The producer describes it as the experimental instruct-based model that began the v4 family. It works with written prompts and conversation to produce text, with particular attention to narrative voice and character interaction. This edition is distinct from the other sizes in the Magnum v4 series.
The published checkpoint uses a causal language-model architecture and an 80-layer configuration with 64 query attention heads and eight key/value heads. Its maximum position count is 32,768, and the training recipe also uses a sequence length of 32,768. This is the configuration of the Magnum release itself; it does not inherit a larger extended-context setting simply because the base model supports one.
Anthracite’s native prompting examples use ChatML with separate system, user and assistant turns. The system part can provide the character description, personality and scenario, while the user turn supplies the next contribution to the exchange. The producer’s narrative template asks the assistant to retain the persona while allowing it to develop, introduce events and secondary characters, and include dialogue, action and thoughts where appropriate.
The same template leaves the user’s character and choices to the user. It also discourages repetitive output and excessive ornamental prose unless the persona calls for that style. An out-of-character request switches the response to neutral plain text. These are concrete prompting choices for an interactive writing task, rather than separate automatic model modes.
For a character scene, prepare the character’s objective, the setting, the relationship to the other speaker and the last exchange. Request one continuation with a clear stopping point so the user has room to respond. For a prose revision, supply a paragraph and identify the change in tone or pacing, then ask for the revised passage while preserving the events and the speaker’s intent. A follow-up can provide a new character decision or editorial note without replacing the established scene.
The producer publishes a full-parameter fine-tuning recipe and a mixture of conversational and writing data. Use the finished output as a scene, dialogue turn or revision draft, and keep a compact record of the story facts that the next turn must retain. The creator’s emphasis is prose and narrative interaction; the base model’s name does not by itself establish additional visual, reasoning-control or tool-execution features for this fine-tuned edition.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits anthracite-org/magnum-v4-72b | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.005 / 1K tokens Output · Output tokens $0.01 / 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 $0.005 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "anthracite-org/magnum-v4-72b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'anthracite-org/magnum-v4-72b', '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': 'anthracite-org/magnum-v4-72b', '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 anthracite-org/magnum-v4-72b
Use the method paths shown above.
Technical example in English
A restrained character voice\n\nPlay archivist Nera in a quiet fantasy scene. She values precision and hides concern behind dry humour. I control her former apprentice, who asks to borrow a forbidden map. Write Nera's next two replies with a small physical action between them; end with a question and leave my character's reactions to me.Two replies in Nera's voice and a brief action beat, ending at a point where the player can respond.The replies retain dry humour and do not invent the apprentice's answer or actions.