GLM-4-Plus is the high-capability text model in Z.ai’s GLM-4 line. Its focus combines language understanding, logical reasoning, instruction following and long-text processing. The manufacturer lists text as both input and output, a 128K-token context window and a maximum output of 4K tokens. A long input and a compact result are therefore separate parts of its profile: a large document set can support a focused summary, comparison or extraction result.
A document assistant can receive named sections and a question, then produce a concise analysis tied to those sections. Define the intended audience and decision before requesting the answer: for instance, compare two procedures, list the conditions that apply to a case or identify contradictory requirements. Keep source passages separate from your instructions so the response can distinguish evidence from the requested analysis.
The GLM-4 description lists streaming, function calling, context caching, structured formats such as JSON and interaction with MCP tools and data sources. Streaming makes generated text available incrementally. Structured output helps when the result should contain named fields rather than an open-ended essay: a summary, extracted identifiers, source section labels and questions that remain unresolved.
Tool use connects the language model to application-supplied actions. The application describes the functions, executes the selected call and returns its result for the next step. This can support a lookup followed by a report, or a search result that becomes evidence for an answer. The model’s text is distinct from the execution of the external action. Repeated instructions or document prefixes can participate in the manufacturer’s context-caching mechanism; cache reuse is not itself evidence that a specific request hit the cache.
Translation is described as more than converting isolated words: the manufacturer includes mixed-language text, tone, slang, emoji and specialist terms while considering cultural differences. Give the source passage, target audience and terminology that should remain unchanged. For editing, ask for a particular artifact—a revised letter, product description or concise explanation—and state which facts must be preserved.
Semantic classification and field extraction use the supplied material as their basis. Define the categories or required fields first, then give the documents. For example, an application can request project identifiers and clause categories together with the relevant section labels. An explicit missing-value rule prevents the output schema from becoming a reason to invent absent data.
The manufacturer also describes marketing material, analytical risk reports and itinerary planning. For writing, supply the actual product or campaign facts and the intended format. For analytical work, give the relevant reports and comparison criteria; current information should arrive through an application-provided search or data tool. For an itinerary, specify preferences and timing constraints so the output is a plan for the described situation rather than a generic travel essay.
GLM-4-Plus uses model-assisted synthetic data and PPO-based post-training to develop mathematical and coding reasoning and better reflect human preferences. For long text, its preparation adjusts the mixture of short and long material to strengthen reasoning over extended inputs. These are preparation choices of this specific Plus model. They do not turn its text-only profile into the image understanding of a separately named GLM-4V edition.
Use the larger context to supply the material that actually supports the question, with stable section names and a clear output contract. A practical request is to compare two documents, list agreements and conflicts, and identify the passages behind each conclusion. Keep the final artifact within the 4K output profile: ask for a decision brief or structured comparison, then continue with a defined follow-up if a particular section needs expansion. Valid JSON structure and factually correct field values are separate checks.
", "aboutText": "### Overview and model profile\n\nGLM-4-Plus is the high-capability text model in Z.ai’s GLM-4 line. Its focus combines language understanding, logical reasoning, instruction following and long-text processing. The manufacturer lists text as both input and output, a 128K-token context window and a maximum output of 4K tokens. A long input and a compact result are therefore separate parts of its profile: a large document set can support a focused summary, comparison or extraction result.\n\nA document assistant can receive named sections and a question, then produce a concise analysis tied to those sections. Define the intended audience and decision before requesting the answer: for instance, compare two procedures, list the conditions that apply to a case or identify contradictory requirements. Keep source passages separate from your instructions so the response can distinguish evidence from the requested analysis.\n\n### Capability support\n\nThe GLM-4 description lists streaming, function calling, context caching, structured formats such as JSON and interaction with MCP tools and data sources. Streaming makes generated text available incrementally. Structured output helps when the result should contain named fields rather than an open-ended essay: a summary, extracted identifiers, source section labels and questions that remain unresolved.\n\nTool use connects the language model to application-supplied actions. The application describes the functions, executes the selected call and returns its result for the next step. This can support a lookup followed by a report, or a search result that becomes evidence for an answer. The model’s text is distinct from the execution of the external action. Repeated instructions or document prefixes can participate in the manufacturer’s context-caching mechanism; cache reuse is not itself evidence that a specific request hit the cache.\n\n### Recommended scenarios\n\nTranslation is described as more than converting isolated words: the manufacturer includes mixed-language text, tone, slang, emoji and specialist terms while considering cultural differences. Give the source passage, target audience and terminology that should remain unchanged. For editing, ask for a particular artifact—a revised letter, product description or concise explanation—and state which facts must be preserved.\n\nSemantic classification and field extraction use the supplied material as their basis. Define the categories or required fields first, then give the documents. For example, an application can request project identifiers and clause categories together with the relevant section labels. An explicit missing-value rule prevents the output schema from becoming a reason to invent absent data.\n\nThe manufacturer also describes marketing material, analytical risk reports and itinerary planning. For writing, supply the actual product or campaign facts and the intended format. For analytical work, give the relevant reports and comparison criteria; current information should arrive through an application-provided search or data tool. For an itinerary, specify preferences and timing constraints so the output is a plan for the described situation rather than a generic travel essay.\n\n### Detailed model preparation\n\nGLM-4-Plus uses model-assisted synthetic data and PPO-based post-training to develop mathematical and coding reasoning and better reflect human preferences. For long text, its preparation adjusts the mixture of short and long material to strengthen reasoning over extended inputs. These are preparation choices of this specific Plus model. They do not turn its text-only profile into the image understanding of a separately named GLM-4V edition.\n\n### Request and output preparation\n\nUse the larger context to supply the material that actually supports the question, with stable section names and a clear output contract. A practical request is to compare two documents, list agreements and conflicts, and identify the passages behind each conclusion. Keep the final artifact within the 4K output profile: ask for a decision brief or structured comparison, then continue with a defined follow-up if a particular section needs expansion. Valid JSON structure and factually correct field values are separate checks.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Find contradictions between two procedures\n\nCompare procedure P: approve a supplier before issuing an order; emergency orders need the same approval. Procedure Q: emergency orders may be issued immediately and reviewed the next day. Prepare a decision brief identifying the conflict, the passages involved and the exact policy question an owner must resolve before the procedures can agree.A concise conflict statement, two supporting passages and one decision question.Check that the answer exposes the approval-timing conflict without silently choosing a governing procedure.glm-4-plusGLM-4-Plus is Z.ai’s text model for language understanding, logical analysis, instruction following and long documents. Its 128K context and 4K output profile suit evidence-based summaries, multilingual editing, field extraction and tool-assisted reports.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4-Plus is the high-capability text model in Z.ai’s GLM-4 line. Its focus combines language understanding, logical reasoning, instruction following and long-text processing. The manufacturer lists text as both input and output, a 128K-token context window and a maximum output of 4K tokens. A long input and a compact result are therefore separate parts of its profile: a large document set can support a focused summary, comparison or extraction result.
A document assistant can receive named sections and a question, then produce a concise analysis tied to those sections. Define the intended audience and decision before requesting the answer: for instance, compare two procedures, list the conditions that apply to a case or identify contradictory requirements. Keep source passages separate from your instructions so the response can distinguish evidence from the requested analysis.
The GLM-4 description lists streaming, function calling, context caching, structured formats such as JSON and interaction with MCP tools and data sources. Streaming makes generated text available incrementally. Structured output helps when the result should contain named fields rather than an open-ended essay: a summary, extracted identifiers, source section labels and questions that remain unresolved.
Tool use connects the language model to application-supplied actions. The application describes the functions, executes the selected call and returns its result for the next step. This can support a lookup followed by a report, or a search result that becomes evidence for an answer. The model’s text is distinct from the execution of the external action. Repeated instructions or document prefixes can participate in the manufacturer’s context-caching mechanism; cache reuse is not itself evidence that a specific request hit the cache.
Translation is described as more than converting isolated words: the manufacturer includes mixed-language text, tone, slang, emoji and specialist terms while considering cultural differences. Give the source passage, target audience and terminology that should remain unchanged. For editing, ask for a particular artifact—a revised letter, product description or concise explanation—and state which facts must be preserved.
Semantic classification and field extraction use the supplied material as their basis. Define the categories or required fields first, then give the documents. For example, an application can request project identifiers and clause categories together with the relevant section labels. An explicit missing-value rule prevents the output schema from becoming a reason to invent absent data.
The manufacturer also describes marketing material, analytical risk reports and itinerary planning. For writing, supply the actual product or campaign facts and the intended format. For analytical work, give the relevant reports and comparison criteria; current information should arrive through an application-provided search or data tool. For an itinerary, specify preferences and timing constraints so the output is a plan for the described situation rather than a generic travel essay.
GLM-4-Plus uses model-assisted synthetic data and PPO-based post-training to develop mathematical and coding reasoning and better reflect human preferences. For long text, its preparation adjusts the mixture of short and long material to strengthen reasoning over extended inputs. These are preparation choices of this specific Plus model. They do not turn its text-only profile into the image understanding of a separately named GLM-4V edition.
Use the larger context to supply the material that actually supports the question, with stable section names and a clear output contract. A practical request is to compare two documents, list agreements and conflicts, and identify the passages behind each conclusion. Keep the final artifact within the 4K output profile: ask for a decision brief or structured comparison, then continue with a defined follow-up if a particular section needs expansion. Valid JSON structure and factually correct field values are separate checks.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits glm-4-plus | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.014 / 1K tokens Output · Output tokens $0.014 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "glm-4-plus", "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='glm-4-plus',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='glm-4-plus',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 glm-4-plus
Use the method paths shown above.
glm-4-plusGLM-4-Plus is Z.ai’s text model for language understanding, logical analysis, instruction following and long documents. Its 128K context and 4K output profile suit evidence-based summaries, multilingual editing, field extraction and tool-assisted reports.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4-Plus is the high-capability text model in Z.ai’s GLM-4 line. Its focus combines language understanding, logical reasoning, instruction following and long-text processing. The manufacturer lists text as both input and output, a 128K-token context window and a maximum output of 4K tokens. A long input and a compact result are therefore separate parts of its profile: a large document set can support a focused summary, comparison or extraction result.
A document assistant can receive named sections and a question, then produce a concise analysis tied to those sections. Define the intended audience and decision before requesting the answer: for instance, compare two procedures, list the conditions that apply to a case or identify contradictory requirements. Keep source passages separate from your instructions so the response can distinguish evidence from the requested analysis.
The GLM-4 description lists streaming, function calling, context caching, structured formats such as JSON and interaction with MCP tools and data sources. Streaming makes generated text available incrementally. Structured output helps when the result should contain named fields rather than an open-ended essay: a summary, extracted identifiers, source section labels and questions that remain unresolved.
Tool use connects the language model to application-supplied actions. The application describes the functions, executes the selected call and returns its result for the next step. This can support a lookup followed by a report, or a search result that becomes evidence for an answer. The model’s text is distinct from the execution of the external action. Repeated instructions or document prefixes can participate in the manufacturer’s context-caching mechanism; cache reuse is not itself evidence that a specific request hit the cache.
Translation is described as more than converting isolated words: the manufacturer includes mixed-language text, tone, slang, emoji and specialist terms while considering cultural differences. Give the source passage, target audience and terminology that should remain unchanged. For editing, ask for a particular artifact—a revised letter, product description or concise explanation—and state which facts must be preserved.
Semantic classification and field extraction use the supplied material as their basis. Define the categories or required fields first, then give the documents. For example, an application can request project identifiers and clause categories together with the relevant section labels. An explicit missing-value rule prevents the output schema from becoming a reason to invent absent data.
The manufacturer also describes marketing material, analytical risk reports and itinerary planning. For writing, supply the actual product or campaign facts and the intended format. For analytical work, give the relevant reports and comparison criteria; current information should arrive through an application-provided search or data tool. For an itinerary, specify preferences and timing constraints so the output is a plan for the described situation rather than a generic travel essay.
GLM-4-Plus uses model-assisted synthetic data and PPO-based post-training to develop mathematical and coding reasoning and better reflect human preferences. For long text, its preparation adjusts the mixture of short and long material to strengthen reasoning over extended inputs. These are preparation choices of this specific Plus model. They do not turn its text-only profile into the image understanding of a separately named GLM-4V edition.
Use the larger context to supply the material that actually supports the question, with stable section names and a clear output contract. A practical request is to compare two documents, list agreements and conflicts, and identify the passages behind each conclusion. Keep the final artifact within the 4K output profile: ask for a decision brief or structured comparison, then continue with a defined follow-up if a particular section needs expansion. Valid JSON structure and factually correct field values are separate checks.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits glm-4-plus | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.014 / 1K tokens Output · Output tokens $0.014 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "glm-4-plus",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'glm-4-plus', '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': 'glm-4-plus', '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 glm-4-plus
Use the method paths shown above.
Technical example in English
Find contradictions between two procedures\n\nCompare procedure P: approve a supplier before issuing an order; emergency orders need the same approval. Procedure Q: emergency orders may be issued immediately and reviewed the next day. Prepare a decision brief identifying the conflict, the passages involved and the exact policy question an owner must resolve before the procedures can agree.A concise conflict statement, two supporting passages and one decision question.Check that the answer exposes the approval-timing conflict without silently choosing a governing procedure.