AutoGLM Phone 9B Multilingual is Z.ai’s model for an assistant that works through a smartphone interface. It combines a natural-language task with visual understanding of the current screen, plans the next step and produces the information used by a phone-agent environment to act. Its architecture is identical to GLM 4.1V 9B Thinking; the named Phone Multilingual edition remains a distinct model choice.
Project overview. The manufacturer’s Phone Agent pairs screen perception with an execution loop. The environment captures the interface, the model reasons about the task and a device-control component performs the selected operation. A new screen then supplies feedback for the following step. The published framework uses Android Debug Bridge for Android devices and provides a separate HarmonyOS control path. The model supplies perception and planning; the connected environment supplies the actual device interaction.
Multilingual distinction. The original AutoGLM Phone 9B is optimised for Chinese mobile applications. The Multilingual edition adds support for English scenarios and is intended for applications containing English or other language content. The project also provides Chinese and English instruction prompts. Preserve app names, search terms and visible interface text when describing the task; these details help tie the requested action to the screen rather than to an assumed translation of it.
Action planning. The published framework’s action vocabulary includes launching an application, tapping, typing, swiping, going back, returning home, long pressing, double tapping and waiting for a page to load. It also has a manual-takeover action. Use these as the vocabulary of a screen-based workflow: open the relevant app, locate the needed control, enter the requested text and inspect the new page. The next action should be based on the latest interface, since a loading state or a changed layout can invalidate an earlier observation.
Prepare a concrete task. State the app, the target information or outcome and the conditions that matter. For a search task, supply the exact query, selection criteria and desired result, such as a list of matching items with their visible attributes. For an office workflow, specify which screen information should be collected and how the final summary should be presented. Include the current screenshot and enough prior steps to explain where the assistant is in the process. The output can then propose the next operation or explain which visible detail prevents progress.
Human participation. The official framework provides callbacks for sensitive-operation confirmation and manual takeover during login or verification-code steps. An application can hand the phone back to the user, then continue from a newly captured screen after the person completes that step. Give a clear completion condition so the assistant can distinguish finding information, preparing an action and reaching the intended result.
Practical setup affects the workflow. Device permissions, a functioning screenshot path and text input are supplied by the surrounding environment. The producer’s Android setup uses a dedicated keyboard component for text entry, while its HarmonyOS path uses native input. Some protected screens can return a black capture. When a screen is unavailable or a control is ambiguous, obtain a usable view or human guidance before forming the next action. A model response alone does not establish that a phone operation has run; inspect the resulting screen to confirm progress.
", "aboutText": "AutoGLM Phone 9B Multilingual is Z.ai’s model for an assistant that works through a smartphone interface. It combines a natural-language task with visual understanding of the current screen, plans the next step and produces the information used by a phone-agent environment to act. Its architecture is identical to GLM 4.1V 9B Thinking; the named Phone Multilingual edition remains a distinct model choice.\n\nProject overview. The manufacturer’s Phone Agent pairs screen perception with an execution loop. The environment captures the interface, the model reasons about the task and a device-control component performs the selected operation. A new screen then supplies feedback for the following step. The published framework uses Android Debug Bridge for Android devices and provides a separate HarmonyOS control path. The model supplies perception and planning; the connected environment supplies the actual device interaction.\n\nMultilingual distinction. The original AutoGLM Phone 9B is optimised for Chinese mobile applications. The Multilingual edition adds support for English scenarios and is intended for applications containing English or other language content. The project also provides Chinese and English instruction prompts. Preserve app names, search terms and visible interface text when describing the task; these details help tie the requested action to the screen rather than to an assumed translation of it.\n\nAction planning. The published framework’s action vocabulary includes launching an application, tapping, typing, swiping, going back, returning home, long pressing, double tapping and waiting for a page to load. It also has a manual-takeover action. Use these as the vocabulary of a screen-based workflow: open the relevant app, locate the needed control, enter the requested text and inspect the new page. The next action should be based on the latest interface, since a loading state or a changed layout can invalidate an earlier observation.\n\nPrepare a concrete task. State the app, the target information or outcome and the conditions that matter. For a search task, supply the exact query, selection criteria and desired result, such as a list of matching items with their visible attributes. For an office workflow, specify which screen information should be collected and how the final summary should be presented. Include the current screenshot and enough prior steps to explain where the assistant is in the process. The output can then propose the next operation or explain which visible detail prevents progress.\n\nHuman participation. The official framework provides callbacks for sensitive-operation confirmation and manual takeover during login or verification-code steps. An application can hand the phone back to the user, then continue from a newly captured screen after the person completes that step. Give a clear completion condition so the assistant can distinguish finding information, preparing an action and reaching the intended result.\n\nPractical setup affects the workflow. Device permissions, a functioning screenshot path and text input are supplied by the surrounding environment. The producer’s Android setup uses a dedicated keyboard component for text entry, while its HarmonyOS path uses native input. Some protected screens can return a black capture. When a screen is unavailable or a control is ambiguous, obtain a usable view or human guidance before forming the next action. A model response alone does not establish that a phone operation has run; inspect the resulting screen to confirm progress.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Plan the next phone-search step\n\nUse this text transcription of the current phone screen: app 'City Library'; search field 'Search catalog'; button 'Search'; no results shown. Goal: find books matching the exact title 'The Glass Harbor'. Propose only the next input action and the screen evidence needed afterward. Preserve the title and do not claim that a search has already run.One next-action proposal and a short description of the resulting screen evidence to inspect.The response uses the exact title and distinguishes proposed text entry from an executed search or a found book.zai-org/autoglm-phone-9b-multilingualZ.ai’s vision-language model for understanding smartphone screens and planning interface actions. The Multilingual edition supports English scenarios and interfaces with other language content; a connected phone-agent environment carries out the proposed operations.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
AutoGLM Phone 9B Multilingual is Z.ai’s model for an assistant that works through a smartphone interface. It combines a natural-language task with visual understanding of the current screen, plans the next step and produces the information used by a phone-agent environment to act. Its architecture is identical to GLM 4.1V 9B Thinking; the named Phone Multilingual edition remains a distinct model choice.
Project overview. The manufacturer’s Phone Agent pairs screen perception with an execution loop. The environment captures the interface, the model reasons about the task and a device-control component performs the selected operation. A new screen then supplies feedback for the following step. The published framework uses Android Debug Bridge for Android devices and provides a separate HarmonyOS control path. The model supplies perception and planning; the connected environment supplies the actual device interaction.
Multilingual distinction. The original AutoGLM Phone 9B is optimised for Chinese mobile applications. The Multilingual edition adds support for English scenarios and is intended for applications containing English or other language content. The project also provides Chinese and English instruction prompts. Preserve app names, search terms and visible interface text when describing the task; these details help tie the requested action to the screen rather than to an assumed translation of it.
Action planning. The published framework’s action vocabulary includes launching an application, tapping, typing, swiping, going back, returning home, long pressing, double tapping and waiting for a page to load. It also has a manual-takeover action. Use these as the vocabulary of a screen-based workflow: open the relevant app, locate the needed control, enter the requested text and inspect the new page. The next action should be based on the latest interface, since a loading state or a changed layout can invalidate an earlier observation.
Prepare a concrete task. State the app, the target information or outcome and the conditions that matter. For a search task, supply the exact query, selection criteria and desired result, such as a list of matching items with their visible attributes. For an office workflow, specify which screen information should be collected and how the final summary should be presented. Include the current screenshot and enough prior steps to explain where the assistant is in the process. The output can then propose the next operation or explain which visible detail prevents progress.
Human participation. The official framework provides callbacks for sensitive-operation confirmation and manual takeover during login or verification-code steps. An application can hand the phone back to the user, then continue from a newly captured screen after the person completes that step. Give a clear completion condition so the assistant can distinguish finding information, preparing an action and reaching the intended result.
Practical setup affects the workflow. Device permissions, a functioning screenshot path and text input are supplied by the surrounding environment. The producer’s Android setup uses a dedicated keyboard component for text entry, while its HarmonyOS path uses native input. Some protected screens can return a black capture. When a screen is unavailable or a control is ambiguous, obtain a usable view or human guidance before forming the next action. A model response alone does not establish that a phone operation has run; inspect the resulting screen to confirm progress.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits zai-org/autoglm-phone-9b-multilingual | 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 $0.000072 / 1K tokens Output · Output tokens $0.000286 / 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": "zai-org/autoglm-phone-9b-multilingual", "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='zai-org/autoglm-phone-9b-multilingual',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='zai-org/autoglm-phone-9b-multilingual',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 zai-org/autoglm-phone-9b-multilingual
Use the method paths shown above.
zai-org/autoglm-phone-9b-multilingualZ.ai’s vision-language model for understanding smartphone screens and planning interface actions. The Multilingual edition supports English scenarios and interfaces with other language content; a connected phone-agent environment carries out the proposed operations.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
AutoGLM Phone 9B Multilingual is Z.ai’s model for an assistant that works through a smartphone interface. It combines a natural-language task with visual understanding of the current screen, plans the next step and produces the information used by a phone-agent environment to act. Its architecture is identical to GLM 4.1V 9B Thinking; the named Phone Multilingual edition remains a distinct model choice.
Project overview. The manufacturer’s Phone Agent pairs screen perception with an execution loop. The environment captures the interface, the model reasons about the task and a device-control component performs the selected operation. A new screen then supplies feedback for the following step. The published framework uses Android Debug Bridge for Android devices and provides a separate HarmonyOS control path. The model supplies perception and planning; the connected environment supplies the actual device interaction.
Multilingual distinction. The original AutoGLM Phone 9B is optimised for Chinese mobile applications. The Multilingual edition adds support for English scenarios and is intended for applications containing English or other language content. The project also provides Chinese and English instruction prompts. Preserve app names, search terms and visible interface text when describing the task; these details help tie the requested action to the screen rather than to an assumed translation of it.
Action planning. The published framework’s action vocabulary includes launching an application, tapping, typing, swiping, going back, returning home, long pressing, double tapping and waiting for a page to load. It also has a manual-takeover action. Use these as the vocabulary of a screen-based workflow: open the relevant app, locate the needed control, enter the requested text and inspect the new page. The next action should be based on the latest interface, since a loading state or a changed layout can invalidate an earlier observation.
Prepare a concrete task. State the app, the target information or outcome and the conditions that matter. For a search task, supply the exact query, selection criteria and desired result, such as a list of matching items with their visible attributes. For an office workflow, specify which screen information should be collected and how the final summary should be presented. Include the current screenshot and enough prior steps to explain where the assistant is in the process. The output can then propose the next operation or explain which visible detail prevents progress.
Human participation. The official framework provides callbacks for sensitive-operation confirmation and manual takeover during login or verification-code steps. An application can hand the phone back to the user, then continue from a newly captured screen after the person completes that step. Give a clear completion condition so the assistant can distinguish finding information, preparing an action and reaching the intended result.
Practical setup affects the workflow. Device permissions, a functioning screenshot path and text input are supplied by the surrounding environment. The producer’s Android setup uses a dedicated keyboard component for text entry, while its HarmonyOS path uses native input. Some protected screens can return a black capture. When a screen is unavailable or a control is ambiguous, obtain a usable view or human guidance before forming the next action. A model response alone does not establish that a phone operation has run; inspect the resulting screen to confirm progress.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits zai-org/autoglm-phone-9b-multilingual | 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 $0.000072 / 1K tokens Output · Output tokens $0.000286 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "zai-org/autoglm-phone-9b-multilingual",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'zai-org/autoglm-phone-9b-multilingual', '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': 'zai-org/autoglm-phone-9b-multilingual', '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 zai-org/autoglm-phone-9b-multilingual
Use the method paths shown above.
Technical example in English
Plan the next phone-search step\n\nUse this text transcription of the current phone screen: app 'City Library'; search field 'Search catalog'; button 'Search'; no results shown. Goal: find books matching the exact title 'The Glass Harbor'. Propose only the next input action and the screen evidence needed afterward. Preserve the title and do not claim that a search has already run.One next-action proposal and a short description of the resulting screen evidence to inspect.The response uses the exact title and distinguishes proposed text entry from an executed search or a found book.