GLM-5V-Turbo connects visual understanding with software development and agent work. Z.ai lists images, video, text and files as inputs and text as output. Its profile has a 200K-token context and up to 128K output tokens. A task can combine a screenshot or design with requirements and request code, a visual explanation or a document-based result. This is a distinct edition from GLM-5.3-Flash.
Front-end reconstruction is a main use. The maker describes recognising layout, colours, component hierarchy and interaction logic from mockups. Supply the reference states, required functions and constraints, then request editable code and an explanation. A screenshot of a defective page can help identify misalignment, component overlap or mismatched colours. The application renders the proposal and supplies the actual result for further interpretation.
A GUI workflow can go beyond one screenshot. The producer describes exploring page transitions and visual assets and using the findings to prepare code. Define the goal and available actions, return changed screens or observations and specify the finished artifact. The model plans from that feedback; the application performs navigation, clicks or other operations. A response describing an action is not evidence of its execution.
The maker describes visual-text fusion, a CogViT vision encoder and multi-token prediction, together with joint reinforcement learning across more than 30 task types. That scope includes STEM, grounding, video, GUI and coding agents. Its visual toolchain includes box drawing, screenshots and reading pages with images. These explain the development focus without assigning a parameter count or another model’s architecture to this edition.
Official task materials cover image captioning, visual grounding, document-grounded writing, comparing resumes with supplied requirements and preparing prompts from reference media. A document brief can name fields and request conclusions supported by passages. A grounding brief can specify the object and bounding-box result. A media-reference task can request a written scene or style prompt; that use does not make the model a native image or video generator.
The profile lists thinking modes, streaming, function calling and context caching. Define tools and preserve their observations with the relevant step. Label sources, code paths and video sequences, leaving room for reasoning and the answer. The examples pair media with a concrete question. Exact transport restrictions and interface controls remain tied to the documented workflow rather than to a similar-sounding GLM edition.
For a usable result, request the pages or document sections covered, what the proposed artifact contains and which differences remain in the evidence. The producer demonstrates webpage coding, website creation, document comprehension and video object tracking. Finished projects, edited files and executed interactions come from the application environment; the model prepares and refines the corresponding textual work.
", "aboutText": "GLM-5V-Turbo connects visual understanding with software development and agent work. Z.ai lists images, video, text and files as inputs and text as output. Its profile has a 200K-token context and up to 128K output tokens. A task can combine a screenshot or design with requirements and request code, a visual explanation or a document-based result. This is a distinct edition from GLM-5.3-Flash.\n\nFront-end reconstruction is a main use. The maker describes recognising layout, colours, component hierarchy and interaction logic from mockups. Supply the reference states, required functions and constraints, then request editable code and an explanation. A screenshot of a defective page can help identify misalignment, component overlap or mismatched colours. The application renders the proposal and supplies the actual result for further interpretation.\n\nA GUI workflow can go beyond one screenshot. The producer describes exploring page transitions and visual assets and using the findings to prepare code. Define the goal and available actions, return changed screens or observations and specify the finished artifact. The model plans from that feedback; the application performs navigation, clicks or other operations. A response describing an action is not evidence of its execution.\n\nThe maker describes visual-text fusion, a CogViT vision encoder and multi-token prediction, together with joint reinforcement learning across more than 30 task types. That scope includes STEM, grounding, video, GUI and coding agents. Its visual toolchain includes box drawing, screenshots and reading pages with images. These explain the development focus without assigning a parameter count or another model’s architecture to this edition.\n\nOfficial task materials cover image captioning, visual grounding, document-grounded writing, comparing resumes with supplied requirements and preparing prompts from reference media. A document brief can name fields and request conclusions supported by passages. A grounding brief can specify the object and bounding-box result. A media-reference task can request a written scene or style prompt; that use does not make the model a native image or video generator.\n\nThe profile lists thinking modes, streaming, function calling and context caching. Define tools and preserve their observations with the relevant step. Label sources, code paths and video sequences, leaving room for reasoning and the answer. The examples pair media with a concrete question. Exact transport restrictions and interface controls remain tied to the documented workflow rather than to a similar-sounding GLM edition.\n\nFor a usable result, request the pages or document sections covered, what the proposed artifact contains and which differences remain in the evidence. The producer demonstrates webpage coding, website creation, document comprehension and video object tracking. Finished projects, edited files and executed interactions come from the application environment; the model prepares and refines the corresponding textual work.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Correct a described responsive layout\n\nPropose HTML and CSS for this written mockup: a header with brand text "North Workshop" and a Book visit link; below it, a title "Repair desk" and two service sections. On narrow screens the services stack in reading order. Use semantic elements, preserve exact labels and keep the link keyboard-focusable. Return editable code and inspection criteria.An editable HTML/CSS example with a responsive service layout and explicit visual and keyboard inspection criteria.Render both wide and narrow layouts and inspect reading order, exact labels and visible keyboard focus before using the code.glm-5v-turboGLM-5V-Turbo is Z.ai’s multimodal coding model for screenshots, visual references, documents and GUI agents. Its producer profile accepts images, video, text and files, returns text and lists 200K context with up to 128K output tokens.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-5V-Turbo connects visual understanding with software development and agent work. Z.ai lists images, video, text and files as inputs and text as output. Its profile has a 200K-token context and up to 128K output tokens. A task can combine a screenshot or design with requirements and request code, a visual explanation or a document-based result. This is a distinct edition from GLM-5.3-Flash.
Front-end reconstruction is a main use. The maker describes recognising layout, colours, component hierarchy and interaction logic from mockups. Supply the reference states, required functions and constraints, then request editable code and an explanation. A screenshot of a defective page can help identify misalignment, component overlap or mismatched colours. The application renders the proposal and supplies the actual result for further interpretation.
A GUI workflow can go beyond one screenshot. The producer describes exploring page transitions and visual assets and using the findings to prepare code. Define the goal and available actions, return changed screens or observations and specify the finished artifact. The model plans from that feedback; the application performs navigation, clicks or other operations. A response describing an action is not evidence of its execution.
The maker describes visual-text fusion, a CogViT vision encoder and multi-token prediction, together with joint reinforcement learning across more than 30 task types. That scope includes STEM, grounding, video, GUI and coding agents. Its visual toolchain includes box drawing, screenshots and reading pages with images. These explain the development focus without assigning a parameter count or another model’s architecture to this edition.
Official task materials cover image captioning, visual grounding, document-grounded writing, comparing resumes with supplied requirements and preparing prompts from reference media. A document brief can name fields and request conclusions supported by passages. A grounding brief can specify the object and bounding-box result. A media-reference task can request a written scene or style prompt; that use does not make the model a native image or video generator.
The profile lists thinking modes, streaming, function calling and context caching. Define tools and preserve their observations with the relevant step. Label sources, code paths and video sequences, leaving room for reasoning and the answer. The examples pair media with a concrete question. Exact transport restrictions and interface controls remain tied to the documented workflow rather than to a similar-sounding GLM edition.
For a usable result, request the pages or document sections covered, what the proposed artifact contains and which differences remain in the evidence. The producer demonstrates webpage coding, website creation, document comprehension and video object tracking. Finished projects, edited files and executed interactions come from the application environment; the model prepares and refines the corresponding textual work.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits glm-5v-turbo | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
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 |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
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 $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"glm-5v-turbo","messages":[{"role":"user","content":"hello"}],"stream":false}')\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-5v-turbo", messages=[{"role":"user","content":"hello"}], stream=False)\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"))\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-5v-turbo, z-ai/glm-5v-turbo
/chat/completions
glm-5v-turboGLM-5V-Turbo is Z.ai’s multimodal coding model for screenshots, visual references, documents and GUI agents. Its producer profile accepts images, video, text and files, returns text and lists 200K context with up to 128K output tokens.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-5V-Turbo connects visual understanding with software development and agent work. Z.ai lists images, video, text and files as inputs and text as output. Its profile has a 200K-token context and up to 128K output tokens. A task can combine a screenshot or design with requirements and request code, a visual explanation or a document-based result. This is a distinct edition from GLM-5.3-Flash.
Front-end reconstruction is a main use. The maker describes recognising layout, colours, component hierarchy and interaction logic from mockups. Supply the reference states, required functions and constraints, then request editable code and an explanation. A screenshot of a defective page can help identify misalignment, component overlap or mismatched colours. The application renders the proposal and supplies the actual result for further interpretation.
A GUI workflow can go beyond one screenshot. The producer describes exploring page transitions and visual assets and using the findings to prepare code. Define the goal and available actions, return changed screens or observations and specify the finished artifact. The model plans from that feedback; the application performs navigation, clicks or other operations. A response describing an action is not evidence of its execution.
The maker describes visual-text fusion, a CogViT vision encoder and multi-token prediction, together with joint reinforcement learning across more than 30 task types. That scope includes STEM, grounding, video, GUI and coding agents. Its visual toolchain includes box drawing, screenshots and reading pages with images. These explain the development focus without assigning a parameter count or another model’s architecture to this edition.
Official task materials cover image captioning, visual grounding, document-grounded writing, comparing resumes with supplied requirements and preparing prompts from reference media. A document brief can name fields and request conclusions supported by passages. A grounding brief can specify the object and bounding-box result. A media-reference task can request a written scene or style prompt; that use does not make the model a native image or video generator.
The profile lists thinking modes, streaming, function calling and context caching. Define tools and preserve their observations with the relevant step. Label sources, code paths and video sequences, leaving room for reasoning and the answer. The examples pair media with a concrete question. Exact transport restrictions and interface controls remain tied to the documented workflow rather than to a similar-sounding GLM edition.
For a usable result, request the pages or document sections covered, what the proposed artifact contains and which differences remain in the evidence. The producer demonstrates webpage coding, website creation, document comprehension and video object tracking. Finished projects, edited files and executed interactions come from the application environment; the model prepares and refines the corresponding textual work.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits glm-5v-turbo | 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 $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "glm-5v-turbo",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-5v-turbo', '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-5v-turbo', '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-5v-turbo, z-ai/glm-5v-turbo
/chat/completions
z-ai/glm-5v-turboGLM-5V-Turbo is Z.ai’s multimodal coding model for screenshots, visual references, documents and GUI agents. Its producer profile accepts images, video, text and files, returns text and lists 200K context with up to 128K output tokens.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-5V-Turbo connects visual understanding with software development and agent work. Z.ai lists images, video, text and files as inputs and text as output. Its profile has a 200K-token context and up to 128K output tokens. A task can combine a screenshot or design with requirements and request code, a visual explanation or a document-based result. This is a distinct edition from GLM-5.3-Flash.
Front-end reconstruction is a main use. The maker describes recognising layout, colours, component hierarchy and interaction logic from mockups. Supply the reference states, required functions and constraints, then request editable code and an explanation. A screenshot of a defective page can help identify misalignment, component overlap or mismatched colours. The application renders the proposal and supplies the actual result for further interpretation.
A GUI workflow can go beyond one screenshot. The producer describes exploring page transitions and visual assets and using the findings to prepare code. Define the goal and available actions, return changed screens or observations and specify the finished artifact. The model plans from that feedback; the application performs navigation, clicks or other operations. A response describing an action is not evidence of its execution.
The maker describes visual-text fusion, a CogViT vision encoder and multi-token prediction, together with joint reinforcement learning across more than 30 task types. That scope includes STEM, grounding, video, GUI and coding agents. Its visual toolchain includes box drawing, screenshots and reading pages with images. These explain the development focus without assigning a parameter count or another model’s architecture to this edition.
Official task materials cover image captioning, visual grounding, document-grounded writing, comparing resumes with supplied requirements and preparing prompts from reference media. A document brief can name fields and request conclusions supported by passages. A grounding brief can specify the object and bounding-box result. A media-reference task can request a written scene or style prompt; that use does not make the model a native image or video generator.
The profile lists thinking modes, streaming, function calling and context caching. Define tools and preserve their observations with the relevant step. Label sources, code paths and video sequences, leaving room for reasoning and the answer. The examples pair media with a concrete question. Exact transport restrictions and interface controls remain tied to the documented workflow rather than to a similar-sounding GLM edition.
For a usable result, request the pages or document sections covered, what the proposed artifact contains and which differences remain in the evidence. The producer demonstrates webpage coding, website creation, document comprehension and video object tracking. Finished projects, edited files and executed interactions come from the application environment; the model prepares and refines the corresponding textual work.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits z-ai/glm-5v-turbo | 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 $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "z-ai/glm-5v-turbo", "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-5v-turbo',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-5v-turbo',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-5v-turbo, z-ai/glm-5v-turbo
/chat/completions
z-ai/glm-5v-turboGLM-5V-Turbo is Z.ai’s multimodal coding model for screenshots, visual references, documents and GUI agents. Its producer profile accepts images, video, text and files, returns text and lists 200K context with up to 128K output tokens.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-5V-Turbo connects visual understanding with software development and agent work. Z.ai lists images, video, text and files as inputs and text as output. Its profile has a 200K-token context and up to 128K output tokens. A task can combine a screenshot or design with requirements and request code, a visual explanation or a document-based result. This is a distinct edition from GLM-5.3-Flash.
Front-end reconstruction is a main use. The maker describes recognising layout, colours, component hierarchy and interaction logic from mockups. Supply the reference states, required functions and constraints, then request editable code and an explanation. A screenshot of a defective page can help identify misalignment, component overlap or mismatched colours. The application renders the proposal and supplies the actual result for further interpretation.
A GUI workflow can go beyond one screenshot. The producer describes exploring page transitions and visual assets and using the findings to prepare code. Define the goal and available actions, return changed screens or observations and specify the finished artifact. The model plans from that feedback; the application performs navigation, clicks or other operations. A response describing an action is not evidence of its execution.
The maker describes visual-text fusion, a CogViT vision encoder and multi-token prediction, together with joint reinforcement learning across more than 30 task types. That scope includes STEM, grounding, video, GUI and coding agents. Its visual toolchain includes box drawing, screenshots and reading pages with images. These explain the development focus without assigning a parameter count or another model’s architecture to this edition.
Official task materials cover image captioning, visual grounding, document-grounded writing, comparing resumes with supplied requirements and preparing prompts from reference media. A document brief can name fields and request conclusions supported by passages. A grounding brief can specify the object and bounding-box result. A media-reference task can request a written scene or style prompt; that use does not make the model a native image or video generator.
The profile lists thinking modes, streaming, function calling and context caching. Define tools and preserve their observations with the relevant step. Label sources, code paths and video sequences, leaving room for reasoning and the answer. The examples pair media with a concrete question. Exact transport restrictions and interface controls remain tied to the documented workflow rather than to a similar-sounding GLM edition.
For a usable result, request the pages or document sections covered, what the proposed artifact contains and which differences remain in the evidence. The producer demonstrates webpage coding, website creation, document comprehension and video object tracking. Finished projects, edited files and executed interactions come from the application environment; the model prepares and refines the corresponding textual work.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits z-ai/glm-5v-turbo | 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 $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0024 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read $0.00048 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "z-ai/glm-5v-turbo",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-5v-turbo', '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-5v-turbo', '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-5v-turbo, z-ai/glm-5v-turbo
/chat/completions
Technical example in English
Correct a described responsive layout\n\nPropose HTML and CSS for this written mockup: a header with brand text "North Workshop" and a Book visit link; below it, a title "Repair desk" and two service sections. On narrow screens the services stack in reading order. Use semantic elements, preserve exact labels and keep the link keyboard-focusable. Return editable code and inspection criteria.An editable HTML/CSS example with a responsive service layout and explicit visual and keyboard inspection criteria.Render both wide and narrow layouts and inspect reading order, exact labels and visible keyboard focus before using the code.