GLM-4.5V is Z.ai’s visual reasoning model built on GLM-4.5-Air, with 106 billion total parameters and 12 billion activated. It handles image reasoning, video understanding, GUI tasks, complex charts, long documents and visual grounding. The producer-hosted profile lists image, video, text and file inputs with text output. A useful task can request a page explanation, an extracted table, a visual location or code prepared from a screenshot. This model is distinct from GLM-4.1V-9B and the later GLM-4.6V.
Image reasoning covers scene understanding, multiple-image analysis and spatial relationships. Give each image a label and state the exact question. For a chart, preserve axes, units and legends and ask which visible values support the conclusion. For a comparison, identify the features to inspect and organise the answer by the source labels. The model can connect visual observations with a written question; input quality and the requested result matter alongside the amount of material supplied.
Grounding is a specific output workflow. The card describes bounding boxes marked by begin_of_box and end_of_box tokens, with four coordinates identifying the top-left and bottom-right corners. Values are normalised from 0 to 1,000 against the image size, rather than given directly as pixel positions. State the object or region to locate and the required box format. Keep the original image dimensions with the result so an application can map the coordinates back to that image, including when it has been resized for processing.
Video tasks include segmentation and event recognition, while document work can combine text, charts, tables and layout across multiple pages. The maker demonstrates converting a pictured table to Markdown and analysing research-report content. Prepare a concrete question, retain page or sequence identifiers and request the evidence supporting each extracted field or described event. A generated summary is a text result; collecting frames, assembling a file or applying an edit belongs to the connected environment.
GUI and webpage tasks use screen understanding for proposed interaction or code. The producer’s examples ask for HTML and CSS from a page screenshot and demonstrate a connected desktop assistant with screenshots or recordings. Give the relevant states, the permitted actions and the desired change. The model prepares code or an action description, while the application executes it and supplies the changed screen or rendered page for further inspection.
The model supports thinking and non-thinking responses. Its exact card describes a switch, and the open-model examples enable thinking by default with a template setting to disable it. Keep those settings tied to the supported workflow. The checkpoint configuration sets max_position_embeddings to 65,536; the hosted profile separately lists up to 16K output tokens. These describe different producer configurations and do not establish a universal application window. The producer also documents fine-tuning the open GLM-4.5V checkpoint for custom multimodal tasks; this is a separate customization workflow from ordinary inference. Long material and the requested answer need room within the configuration actually used.
The card identifies specific limitations in visual-code reproduction: raw HTML may lack Markdown wrapping, and character escaping can cause rendering problems. It also notes weaker pure-text question answering, occasional excessive or repetitive thinking, answer restatement and perception errors such as counting. For a code task, ask for an explicit artifact format and inspect the rendered result. For extraction or visual analysis, preserve the small labels and request values tied to visible evidence. This keeps the model’s reasoning and grounding capabilities connected to a result that can be compared with the original source.
", "aboutText": "GLM-4.5V is Z.ai’s visual reasoning model built on GLM-4.5-Air, with 106 billion total parameters and 12 billion activated. It handles image reasoning, video understanding, GUI tasks, complex charts, long documents and visual grounding. The producer-hosted profile lists image, video, text and file inputs with text output. A useful task can request a page explanation, an extracted table, a visual location or code prepared from a screenshot. This model is distinct from GLM-4.1V-9B and the later GLM-4.6V.\n\nImage reasoning covers scene understanding, multiple-image analysis and spatial relationships. Give each image a label and state the exact question. For a chart, preserve axes, units and legends and ask which visible values support the conclusion. For a comparison, identify the features to inspect and organise the answer by the source labels. The model can connect visual observations with a written question; input quality and the requested result matter alongside the amount of material supplied.\n\nGrounding is a specific output workflow. The card describes bounding boxes marked by begin_of_box and end_of_box tokens, with four coordinates identifying the top-left and bottom-right corners. Values are normalised from 0 to 1,000 against the image size, rather than given directly as pixel positions. State the object or region to locate and the required box format. Keep the original image dimensions with the result so an application can map the coordinates back to that image, including when it has been resized for processing.\n\nVideo tasks include segmentation and event recognition, while document work can combine text, charts, tables and layout across multiple pages. The maker demonstrates converting a pictured table to Markdown and analysing research-report content. Prepare a concrete question, retain page or sequence identifiers and request the evidence supporting each extracted field or described event. A generated summary is a text result; collecting frames, assembling a file or applying an edit belongs to the connected environment.\n\nGUI and webpage tasks use screen understanding for proposed interaction or code. The producer’s examples ask for HTML and CSS from a page screenshot and demonstrate a connected desktop assistant with screenshots or recordings. Give the relevant states, the permitted actions and the desired change. The model prepares code or an action description, while the application executes it and supplies the changed screen or rendered page for further inspection.\n\nThe model supports thinking and non-thinking responses. Its exact card describes a switch, and the open-model examples enable thinking by default with a template setting to disable it. Keep those settings tied to the supported workflow. The checkpoint configuration sets max_position_embeddings to 65,536; the hosted profile separately lists up to 16K output tokens. These describe different producer configurations and do not establish a universal application window. The producer also documents fine-tuning the open GLM-4.5V checkpoint for custom multimodal tasks; this is a separate customization workflow from ordinary inference. Long material and the requested answer need room within the configuration actually used.\n\nThe card identifies specific limitations in visual-code reproduction: raw HTML may lack Markdown wrapping, and character escaping can cause rendering problems. It also notes weaker pure-text question answering, occasional excessive or repetitive thinking, answer restatement and perception errors such as counting. For a code task, ask for an explicit artifact format and inspect the rendered result. For extraction or visual analysis, preserve the small labels and request values tied to visible evidence. This keeps the model’s reasoning and grounding capabilities connected to a result that can be compared with the original source.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Format a transcribed report table\n\nFrom this text transcription of page V5, produce a Markdown table: 'Experiment | control | treated; run 1 | 12 | 15; run 2 | 11 | unreadable.' Add a difference column only where both values are available. Keep V5 with the result and separate the extracted values from the calculated differences. No image is supplied.A source-labeled Markdown table with extracted numbers, calculated differences and explicit unknown values.The unreadable treated value and its difference must remain unknown rather than be estimated.z-ai/glm-4.5vGLM-4.5V is Z.ai’s 106B-A12B visual reasoning model for images, video, complex documents and GUI tasks. It returns text, supports thinking and direct responses, and can locate visual elements with coordinates normalised from 0 to 1,000.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4.5V is Z.ai’s visual reasoning model built on GLM-4.5-Air, with 106 billion total parameters and 12 billion activated. It handles image reasoning, video understanding, GUI tasks, complex charts, long documents and visual grounding. The producer-hosted profile lists image, video, text and file inputs with text output. A useful task can request a page explanation, an extracted table, a visual location or code prepared from a screenshot. This model is distinct from GLM-4.1V-9B and the later GLM-4.6V.
Image reasoning covers scene understanding, multiple-image analysis and spatial relationships. Give each image a label and state the exact question. For a chart, preserve axes, units and legends and ask which visible values support the conclusion. For a comparison, identify the features to inspect and organise the answer by the source labels. The model can connect visual observations with a written question; input quality and the requested result matter alongside the amount of material supplied.
Grounding is a specific output workflow. The card describes bounding boxes marked by begin_of_box and end_of_box tokens, with four coordinates identifying the top-left and bottom-right corners. Values are normalised from 0 to 1,000 against the image size, rather than given directly as pixel positions. State the object or region to locate and the required box format. Keep the original image dimensions with the result so an application can map the coordinates back to that image, including when it has been resized for processing.
Video tasks include segmentation and event recognition, while document work can combine text, charts, tables and layout across multiple pages. The maker demonstrates converting a pictured table to Markdown and analysing research-report content. Prepare a concrete question, retain page or sequence identifiers and request the evidence supporting each extracted field or described event. A generated summary is a text result; collecting frames, assembling a file or applying an edit belongs to the connected environment.
GUI and webpage tasks use screen understanding for proposed interaction or code. The producer’s examples ask for HTML and CSS from a page screenshot and demonstrate a connected desktop assistant with screenshots or recordings. Give the relevant states, the permitted actions and the desired change. The model prepares code or an action description, while the application executes it and supplies the changed screen or rendered page for further inspection.
The model supports thinking and non-thinking responses. Its exact card describes a switch, and the open-model examples enable thinking by default with a template setting to disable it. Keep those settings tied to the supported workflow. The checkpoint configuration sets max_position_embeddings to 65,536; the hosted profile separately lists up to 16K output tokens. These describe different producer configurations and do not establish a universal application window. The producer also documents fine-tuning the open GLM-4.5V checkpoint for custom multimodal tasks; this is a separate customization workflow from ordinary inference. Long material and the requested answer need room within the configuration actually used.
The card identifies specific limitations in visual-code reproduction: raw HTML may lack Markdown wrapping, and character escaping can cause rendering problems. It also notes weaker pure-text question answering, occasional excessive or repetitive thinking, answer restatement and perception errors such as counting. For a code task, ask for an explicit artifact format and inspect the rendered result. For extraction or visual analysis, preserve the small labels and request values tied to visible evidence. This keeps the model’s reasoning and grounding capabilities connected to a result that can be compared with the original source.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits z-ai/glm-4.5v | 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 $0.0012 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read $0.00022 / 1K tokens Input · Cache write $0 / 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 $0.0012 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read $0.00022 / 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": "z-ai/glm-4.5v", "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='z-ai/glm-4.5v',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='z-ai/glm-4.5v',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 z-ai/glm-4.5v
Use the method paths shown above.
z-ai/glm-4.5vGLM-4.5V is Z.ai’s 106B-A12B visual reasoning model for images, video, complex documents and GUI tasks. It returns text, supports thinking and direct responses, and can locate visual elements with coordinates normalised from 0 to 1,000.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4.5V is Z.ai’s visual reasoning model built on GLM-4.5-Air, with 106 billion total parameters and 12 billion activated. It handles image reasoning, video understanding, GUI tasks, complex charts, long documents and visual grounding. The producer-hosted profile lists image, video, text and file inputs with text output. A useful task can request a page explanation, an extracted table, a visual location or code prepared from a screenshot. This model is distinct from GLM-4.1V-9B and the later GLM-4.6V.
Image reasoning covers scene understanding, multiple-image analysis and spatial relationships. Give each image a label and state the exact question. For a chart, preserve axes, units and legends and ask which visible values support the conclusion. For a comparison, identify the features to inspect and organise the answer by the source labels. The model can connect visual observations with a written question; input quality and the requested result matter alongside the amount of material supplied.
Grounding is a specific output workflow. The card describes bounding boxes marked by begin_of_box and end_of_box tokens, with four coordinates identifying the top-left and bottom-right corners. Values are normalised from 0 to 1,000 against the image size, rather than given directly as pixel positions. State the object or region to locate and the required box format. Keep the original image dimensions with the result so an application can map the coordinates back to that image, including when it has been resized for processing.
Video tasks include segmentation and event recognition, while document work can combine text, charts, tables and layout across multiple pages. The maker demonstrates converting a pictured table to Markdown and analysing research-report content. Prepare a concrete question, retain page or sequence identifiers and request the evidence supporting each extracted field or described event. A generated summary is a text result; collecting frames, assembling a file or applying an edit belongs to the connected environment.
GUI and webpage tasks use screen understanding for proposed interaction or code. The producer’s examples ask for HTML and CSS from a page screenshot and demonstrate a connected desktop assistant with screenshots or recordings. Give the relevant states, the permitted actions and the desired change. The model prepares code or an action description, while the application executes it and supplies the changed screen or rendered page for further inspection.
The model supports thinking and non-thinking responses. Its exact card describes a switch, and the open-model examples enable thinking by default with a template setting to disable it. Keep those settings tied to the supported workflow. The checkpoint configuration sets max_position_embeddings to 65,536; the hosted profile separately lists up to 16K output tokens. These describe different producer configurations and do not establish a universal application window. The producer also documents fine-tuning the open GLM-4.5V checkpoint for custom multimodal tasks; this is a separate customization workflow from ordinary inference. Long material and the requested answer need room within the configuration actually used.
The card identifies specific limitations in visual-code reproduction: raw HTML may lack Markdown wrapping, and character escaping can cause rendering problems. It also notes weaker pure-text question answering, occasional excessive or repetitive thinking, answer restatement and perception errors such as counting. For a code task, ask for an explicit artifact format and inspect the rendered result. For extraction or visual analysis, preserve the small labels and request values tied to visible evidence. This keeps the model’s reasoning and grounding capabilities connected to a result that can be compared with the original source.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits z-ai/glm-4.5v | 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 $0.0012 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read $0.00022 / 1K tokens Input · Cache write $0 / 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 $0.0012 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read $0.00022 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "z-ai/glm-4.5v",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'z-ai/glm-4.5v', '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': 'z-ai/glm-4.5v', '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 z-ai/glm-4.5v
Use the method paths shown above.
Technical example in English
Format a transcribed report table\n\nFrom this text transcription of page V5, produce a Markdown table: 'Experiment | control | treated; run 1 | 12 | 15; run 2 | 11 | unreadable.' Add a difference column only where both values are available. Keep V5 with the result and separate the extracted values from the calculated differences. No image is supplied.A source-labeled Markdown table with extracted numbers, calculated differences and explicit unknown values.The unreadable treated value and its difference must remain unknown rather than be estimated.