GLM-4-32B-0414 is the fixed 32B-class text edition in Z.ai’s GLM-4-0414 series. Its base was pre-trained on 15 trillion tokens including synthetic reasoning material. Post-training combines dialogue preference alignment, rejection sampling and reinforcement learning to develop instruction following, engineering code and function calls. Its stated work includes software tasks, text artifacts, search-based questions and reports. Input and output are text; generated code becomes a runnable or rendered artifact when the application saves and executes it.
The reasoning-focused GLM-Z1-32B-0414 and the research-oriented Rumination model are separately named editions. This entry follows the GLM-4 model’s own broader code-and-tools demonstrations rather than substituting another release’s thinking rules.
The maker demonstrates programming a moving ball inside a rotating hexagon. The GLM-4-32B-0414 example uses HTML and describes the motion, collisions and physical assumptions. This is code for a simulation, not a video-generation mode. To prepare a similar task, give the scene, movement rules, collision behavior and intended runtime, then ask for a self-contained implementation and an explanation of the assumptions. The application runs that code to inspect the result.
The examples include a drawing interface for custom function plots, with adding and removing functions and assigning colors. Another example builds a mobile machine-learning interface with training tasks, storage management and personal statistics, including charts, arranged in an HTML page. These are concrete frontend tasks with specified controls and states.
For useful output, describe the actions each control must support and the data the view should show. An interface request can ask for the page code together with the relationship between input, displayed state and result. A subsequent turn can provide the observed rendering and request a focused change while preserving the listed behavior.
The maker also demonstrates SVG illustrations, including a landscape and an explanation of a language-model training process. SVG is structured text, so the application can save it as an editable vector artifact. Supply the subject, labels, layout and required visual relationships. Ask for the SVG markup as a distinct deliverable instead of mixing the illustration’s code with a long unrelated explanation.
For research writing, the card supplies search results as observations and asks the model to organize and interpret them instead of copying them. Its instructions distinguish relevant results from irrelevant ones, favor meaningful detail when the evidence permits, use a readable structure and answer in the user’s language. The example produces an analytical report about children’s literature, covering narrative methods, themes and their effects.
A practical task can provide named excerpts and ask for a report organized around explicit questions, with each conclusion tied to the supporting material. Search and retrieval take place in the surrounding application; the returned passages become the model’s evidence. This is also useful for comparing documents or preparing an explanation from a supplied research collection.
GLM-4-32B-0414 supports external tool calls with JSON arguments. The model identifies a function and its arguments, the application executes it, and the result is returned as an observation. The maker’s demonstration repeats that loop until a final response is produced. Describe each tool’s purpose and required fields and distinguish its observation from the user’s instruction. A lookup can therefore supply data for a later comparison without pretending that the model has independently obtained live information.
The published configuration sets max_position_embeddings to 32,768 and does not include a rope_scaling entry. The maker’s worked examples use request-specific generation lengths; the card does not give a universal hard output maximum. Keep relevant code, retrieved passages and dialogue within the active context, and state whether the final result should be HTML, SVG, a code fragment, JSON arguments or a report. These are text representations produced for the described task; execution, file creation and access to external data remain application actions.
", "aboutText": "### Introduction\n\nGLM-4-32B-0414 is the fixed 32B-class text edition in Z.ai’s GLM-4-0414 series. Its base was pre-trained on 15 trillion tokens including synthetic reasoning material. Post-training combines dialogue preference alignment, rejection sampling and reinforcement learning to develop instruction following, engineering code and function calls. Its stated work includes software tasks, text artifacts, search-based questions and reports. Input and output are text; generated code becomes a runnable or rendered artifact when the application saves and executes it.\n\nThe reasoning-focused GLM-Z1-32B-0414 and the research-oriented Rumination model are separately named editions. This entry follows the GLM-4 model’s own broader code-and-tools demonstrations rather than substituting another release’s thinking rules.\n\n### Showcase: animation generation\n\nThe maker demonstrates programming a moving ball inside a rotating hexagon. The GLM-4-32B-0414 example uses HTML and describes the motion, collisions and physical assumptions. This is code for a simulation, not a video-generation mode. To prepare a similar task, give the scene, movement rules, collision behavior and intended runtime, then ask for a self-contained implementation and an explanation of the assumptions. The application runs that code to inspect the result.\n\n### Showcase: web design\n\nThe examples include a drawing interface for custom function plots, with adding and removing functions and assigning colors. Another example builds a mobile machine-learning interface with training tasks, storage management and personal statistics, including charts, arranged in an HTML page. These are concrete frontend tasks with specified controls and states.\n\nFor useful output, describe the actions each control must support and the data the view should show. An interface request can ask for the page code together with the relationship between input, displayed state and result. A subsequent turn can provide the observed rendering and request a focused change while preserving the listed behavior.\n\n### Showcase: SVG generation\n\nThe maker also demonstrates SVG illustrations, including a landscape and an explanation of a language-model training process. SVG is structured text, so the application can save it as an editable vector artifact. Supply the subject, labels, layout and required visual relationships. Ask for the SVG markup as a distinct deliverable instead of mixing the illustration’s code with a long unrelated explanation.\n\n### Search-based writing\n\nFor research writing, the card supplies search results as observations and asks the model to organize and interpret them instead of copying them. Its instructions distinguish relevant results from irrelevant ones, favor meaningful detail when the evidence permits, use a readable structure and answer in the user’s language. The example produces an analytical report about children’s literature, covering narrative methods, themes and their effects.\n\nA practical task can provide named excerpts and ask for a report organized around explicit questions, with each conclusion tied to the supporting material. Search and retrieval take place in the surrounding application; the returned passages become the model’s evidence. This is also useful for comparing documents or preparing an explanation from a supplied research collection.\n\n### Function calls\n\nGLM-4-32B-0414 supports external tool calls with JSON arguments. The model identifies a function and its arguments, the application executes it, and the result is returned as an observation. The maker’s demonstration repeats that loop until a final response is produced. Describe each tool’s purpose and required fields and distinguish its observation from the user’s instruction. A lookup can therefore supply data for a later comparison without pretending that the model has independently obtained live information.\n\n### Context and result planning\n\nThe published configuration sets max_position_embeddings to 32,768 and does not include a rope_scaling entry. The maker’s worked examples use request-specific generation lengths; the card does not give a universal hard output maximum. Keep relevant code, retrieved passages and dialogue within the active context, and state whether the final result should be HTML, SVG, a code fragment, JSON arguments or a report. These are text representations produced for the described task; execution, file creation and access to external data remain application actions.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Generate an editable process diagram\n\nCreate self-contained SVG markup for a left-to-right process: Receive -> Validate -> Store. Use three labelled rectangles and two arrows; all labels must remain readable in a 720 by 180 viewBox. Use no scripts, external fonts or external images. Return SVG code and a brief explanation of how the arrows encode the required order.A standalone editable SVG code block with three named nodes and two directional arrows, followed by a short order explanation.Render the SVG locally and check the exact labels, arrow direction and absence of clipped text or external dependencies.THUDM/GLM-4-32B-0414GLM-4-32B-0414 is Z.ai’s fixed text edition for engineering code, interactive HTML/SVG artifacts, search-based reports and JSON function calls. Its model card shows concrete development workflows and an application-controlled tool loop.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4-32B-0414 is the fixed 32B-class text edition in Z.ai’s GLM-4-0414 series. Its base was pre-trained on 15 trillion tokens including synthetic reasoning material. Post-training combines dialogue preference alignment, rejection sampling and reinforcement learning to develop instruction following, engineering code and function calls. Its stated work includes software tasks, text artifacts, search-based questions and reports. Input and output are text; generated code becomes a runnable or rendered artifact when the application saves and executes it.
The reasoning-focused GLM-Z1-32B-0414 and the research-oriented Rumination model are separately named editions. This entry follows the GLM-4 model’s own broader code-and-tools demonstrations rather than substituting another release’s thinking rules.
The maker demonstrates programming a moving ball inside a rotating hexagon. The GLM-4-32B-0414 example uses HTML and describes the motion, collisions and physical assumptions. This is code for a simulation, not a video-generation mode. To prepare a similar task, give the scene, movement rules, collision behavior and intended runtime, then ask for a self-contained implementation and an explanation of the assumptions. The application runs that code to inspect the result.
The examples include a drawing interface for custom function plots, with adding and removing functions and assigning colors. Another example builds a mobile machine-learning interface with training tasks, storage management and personal statistics, including charts, arranged in an HTML page. These are concrete frontend tasks with specified controls and states.
For useful output, describe the actions each control must support and the data the view should show. An interface request can ask for the page code together with the relationship between input, displayed state and result. A subsequent turn can provide the observed rendering and request a focused change while preserving the listed behavior.
The maker also demonstrates SVG illustrations, including a landscape and an explanation of a language-model training process. SVG is structured text, so the application can save it as an editable vector artifact. Supply the subject, labels, layout and required visual relationships. Ask for the SVG markup as a distinct deliverable instead of mixing the illustration’s code with a long unrelated explanation.
For research writing, the card supplies search results as observations and asks the model to organize and interpret them instead of copying them. Its instructions distinguish relevant results from irrelevant ones, favor meaningful detail when the evidence permits, use a readable structure and answer in the user’s language. The example produces an analytical report about children’s literature, covering narrative methods, themes and their effects.
A practical task can provide named excerpts and ask for a report organized around explicit questions, with each conclusion tied to the supporting material. Search and retrieval take place in the surrounding application; the returned passages become the model’s evidence. This is also useful for comparing documents or preparing an explanation from a supplied research collection.
GLM-4-32B-0414 supports external tool calls with JSON arguments. The model identifies a function and its arguments, the application executes it, and the result is returned as an observation. The maker’s demonstration repeats that loop until a final response is produced. Describe each tool’s purpose and required fields and distinguish its observation from the user’s instruction. A lookup can therefore supply data for a later comparison without pretending that the model has independently obtained live information.
The published configuration sets max_position_embeddings to 32,768 and does not include a rope_scaling entry. The maker’s worked examples use request-specific generation lengths; the card does not give a universal hard output maximum. Keep relevant code, retrieved passages and dialogue within the active context, and state whether the final result should be HTML, SVG, a code fragment, JSON arguments or a report. These are text representations produced for the described task; execution, file creation and access to external data remain application actions.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits THUDM/GLM-4-32B-0414 | 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 $0.00014 / 1K tokens Output · Output tokens $0.00014 / 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": "THUDM/GLM-4-32B-0414", "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='THUDM/GLM-4-32B-0414',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='THUDM/GLM-4-32B-0414',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 THUDM/GLM-4-32B-0414
Use the method paths shown above.
THUDM/GLM-4-32B-0414GLM-4-32B-0414 is Z.ai’s fixed text edition for engineering code, interactive HTML/SVG artifacts, search-based reports and JSON function calls. Its model card shows concrete development workflows and an application-controlled tool loop.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4-32B-0414 is the fixed 32B-class text edition in Z.ai’s GLM-4-0414 series. Its base was pre-trained on 15 trillion tokens including synthetic reasoning material. Post-training combines dialogue preference alignment, rejection sampling and reinforcement learning to develop instruction following, engineering code and function calls. Its stated work includes software tasks, text artifacts, search-based questions and reports. Input and output are text; generated code becomes a runnable or rendered artifact when the application saves and executes it.
The reasoning-focused GLM-Z1-32B-0414 and the research-oriented Rumination model are separately named editions. This entry follows the GLM-4 model’s own broader code-and-tools demonstrations rather than substituting another release’s thinking rules.
The maker demonstrates programming a moving ball inside a rotating hexagon. The GLM-4-32B-0414 example uses HTML and describes the motion, collisions and physical assumptions. This is code for a simulation, not a video-generation mode. To prepare a similar task, give the scene, movement rules, collision behavior and intended runtime, then ask for a self-contained implementation and an explanation of the assumptions. The application runs that code to inspect the result.
The examples include a drawing interface for custom function plots, with adding and removing functions and assigning colors. Another example builds a mobile machine-learning interface with training tasks, storage management and personal statistics, including charts, arranged in an HTML page. These are concrete frontend tasks with specified controls and states.
For useful output, describe the actions each control must support and the data the view should show. An interface request can ask for the page code together with the relationship between input, displayed state and result. A subsequent turn can provide the observed rendering and request a focused change while preserving the listed behavior.
The maker also demonstrates SVG illustrations, including a landscape and an explanation of a language-model training process. SVG is structured text, so the application can save it as an editable vector artifact. Supply the subject, labels, layout and required visual relationships. Ask for the SVG markup as a distinct deliverable instead of mixing the illustration’s code with a long unrelated explanation.
For research writing, the card supplies search results as observations and asks the model to organize and interpret them instead of copying them. Its instructions distinguish relevant results from irrelevant ones, favor meaningful detail when the evidence permits, use a readable structure and answer in the user’s language. The example produces an analytical report about children’s literature, covering narrative methods, themes and their effects.
A practical task can provide named excerpts and ask for a report organized around explicit questions, with each conclusion tied to the supporting material. Search and retrieval take place in the surrounding application; the returned passages become the model’s evidence. This is also useful for comparing documents or preparing an explanation from a supplied research collection.
GLM-4-32B-0414 supports external tool calls with JSON arguments. The model identifies a function and its arguments, the application executes it, and the result is returned as an observation. The maker’s demonstration repeats that loop until a final response is produced. Describe each tool’s purpose and required fields and distinguish its observation from the user’s instruction. A lookup can therefore supply data for a later comparison without pretending that the model has independently obtained live information.
The published configuration sets max_position_embeddings to 32,768 and does not include a rope_scaling entry. The maker’s worked examples use request-specific generation lengths; the card does not give a universal hard output maximum. Keep relevant code, retrieved passages and dialogue within the active context, and state whether the final result should be HTML, SVG, a code fragment, JSON arguments or a report. These are text representations produced for the described task; execution, file creation and access to external data remain application actions.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits THUDM/GLM-4-32B-0414 | 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 $0.00014 / 1K tokens Output · Output tokens $0.00014 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "THUDM/GLM-4-32B-0414",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'THUDM/GLM-4-32B-0414', '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': 'THUDM/GLM-4-32B-0414', '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 THUDM/GLM-4-32B-0414
Use the method paths shown above.
Technical example in English
Generate an editable process diagram\n\nCreate self-contained SVG markup for a left-to-right process: Receive -> Validate -> Store. Use three labelled rectangles and two arrows; all labels must remain readable in a 720 by 180 viewBox. Use no scripts, external fonts or external images. Return SVG code and a brief explanation of how the arrows encode the required order.A standalone editable SVG code block with three named nodes and two directional arrows, followed by a short order explanation.Render the SVG locally and check the exact labels, arrow direction and absence of clipped text or external dependencies.