UI-TARS-1.5-7B is ByteDance’s released 7B multimodal GUI-agent model, focused on general computer use. It combines visual perception of an interface with reasoning before action, building on the native UI-TARS architecture with reinforcement learning. The inputs in the official usage flow are an instruction, screenshots and action history; the output describes the next interface action, often with a Thought explaining the intended step. A surrounding application executes that action and supplies the next screenshot so the task can continue.
The producer distinguishes this downloadable 7B checkpoint from the larger UI-TARS-1.5 research model. The 7B release is not specifically optimised for game-based scenarios, so demonstrations and results from the larger research model should not be treated as equivalent capabilities of this edition. Its practical role is interacting with visible application controls: browser navigation, office software, file management and similar desktop workflows. Reading a screenshot and choosing an action is different from generating a video or obtaining unseen application state.
The official repository describes desktop and mobile action templates. Desktop actions cover clicks, double and right clicks, dragging, keyboard shortcuts, text entry and scrolling, with wait and finished actions for checking a changing screen or ending a task. The mobile template adds operations such as a long press, opening an app and navigating home or back. A separate grounding template asks for an Action without the Thought and is intended for lightweight action-output tasks. Choose the action vocabulary that the execution environment actually understands rather than treating every template as interchangeable.
A useful task brief names the goal, supplies the current screenshot and relevant action history, and defines what completion looks like. For example, an original editorial brief might ask the model to find a named setting, change it to a specified value and stop after the new state is visible. Request the next step against the current screen rather than a long speculative sequence. Keep instructions and any limits on allowed operations explicit; after an executed step, return the resulting screen so subsequent reasoning uses observations rather than assumptions about what happened.
Coordinate handling is a material part of the official workflow. The repository separates model prediction from post-processing that parses an action and maps its target to the screen. Its coordinate guide demonstrates converting coordinates from the resized image back to the original image dimensions. Preserve the original screenshot width and height and use the coordinate convention of the exact action template and parser. A location that appears plausible in a resized image can point to a different control if it is applied directly to the unscaled screen. The model’s action text is therefore an instruction to interpret, not an already executed mouse event.
The deployment guide provides a concrete single-step example whose result contains Thought and Action, while the repository’s desktop application is a separate execution surface. The guide’s configured input length and its sample output budget are deployment settings, not a universal claim about every integration’s context or action limit. For practical GUI work, send clear, readable screenshots with the controls and surrounding context needed for the next decision. UI-TARS can misidentify elements, describe unfamiliar interfaces incorrectly or choose a suboptimal action, particularly when the screen is ambiguous; checking the new screenshot after each action keeps those errors tied to the actual task state.
", "aboutText": "UI-TARS-1.5-7B is ByteDance’s released 7B multimodal GUI-agent model, focused on general computer use. It combines visual perception of an interface with reasoning before action, building on the native UI-TARS architecture with reinforcement learning. The inputs in the official usage flow are an instruction, screenshots and action history; the output describes the next interface action, often with a Thought explaining the intended step. A surrounding application executes that action and supplies the next screenshot so the task can continue.\n\nThe producer distinguishes this downloadable 7B checkpoint from the larger UI-TARS-1.5 research model. The 7B release is not specifically optimised for game-based scenarios, so demonstrations and results from the larger research model should not be treated as equivalent capabilities of this edition. Its practical role is interacting with visible application controls: browser navigation, office software, file management and similar desktop workflows. Reading a screenshot and choosing an action is different from generating a video or obtaining unseen application state.\n\nThe official repository describes desktop and mobile action templates. Desktop actions cover clicks, double and right clicks, dragging, keyboard shortcuts, text entry and scrolling, with wait and finished actions for checking a changing screen or ending a task. The mobile template adds operations such as a long press, opening an app and navigating home or back. A separate grounding template asks for an Action without the Thought and is intended for lightweight action-output tasks. Choose the action vocabulary that the execution environment actually understands rather than treating every template as interchangeable.\n\nA useful task brief names the goal, supplies the current screenshot and relevant action history, and defines what completion looks like. For example, an original editorial brief might ask the model to find a named setting, change it to a specified value and stop after the new state is visible. Request the next step against the current screen rather than a long speculative sequence. Keep instructions and any limits on allowed operations explicit; after an executed step, return the resulting screen so subsequent reasoning uses observations rather than assumptions about what happened.\n\nCoordinate handling is a material part of the official workflow. The repository separates model prediction from post-processing that parses an action and maps its target to the screen. Its coordinate guide demonstrates converting coordinates from the resized image back to the original image dimensions. Preserve the original screenshot width and height and use the coordinate convention of the exact action template and parser. A location that appears plausible in a resized image can point to a different control if it is applied directly to the unscaled screen. The model’s action text is therefore an instruction to interpret, not an already executed mouse event.\n\nThe deployment guide provides a concrete single-step example whose result contains Thought and Action, while the repository’s desktop application is a separate execution surface. The guide’s configured input length and its sample output budget are deployment settings, not a universal claim about every integration’s context or action limit. For practical GUI work, send clear, readable screenshots with the controls and surrounding context needed for the next decision. UI-TARS can misidentify elements, describe unfamiliar interfaces incorrectly or choose a suboptimal action, particularly when the screen is ambiguous; checking the new screenshot after each action keeps those errors tied to the actual task state.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Choose a safe next interface step\n\nGoal: enable weekly email summaries. Text description of the current settings page: a checkbox labelled Weekly summary is unchecked; a Save button is below it. History: settings opened, no changes saved. Describe the next interface action and the state to verify afterward. Use labels rather than inventing screen coordinates.One proposed action, a brief reason and the resulting visible state an application should check.Check that the answer proposes checking Weekly summary before saving and does not claim that any click was executed.bytedance/ui-tars-1.5-7bUI-TARS-1.5-7B is ByteDance’s open multimodal model for computer-use agents. It reasons over screenshots and a task, then produces the next GUI action for an application to execute; this 7B release focuses on general computer use rather than game optimisation.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
UI-TARS-1.5-7B is ByteDance’s released 7B multimodal GUI-agent model, focused on general computer use. It combines visual perception of an interface with reasoning before action, building on the native UI-TARS architecture with reinforcement learning. The inputs in the official usage flow are an instruction, screenshots and action history; the output describes the next interface action, often with a Thought explaining the intended step. A surrounding application executes that action and supplies the next screenshot so the task can continue.
The producer distinguishes this downloadable 7B checkpoint from the larger UI-TARS-1.5 research model. The 7B release is not specifically optimised for game-based scenarios, so demonstrations and results from the larger research model should not be treated as equivalent capabilities of this edition. Its practical role is interacting with visible application controls: browser navigation, office software, file management and similar desktop workflows. Reading a screenshot and choosing an action is different from generating a video or obtaining unseen application state.
The official repository describes desktop and mobile action templates. Desktop actions cover clicks, double and right clicks, dragging, keyboard shortcuts, text entry and scrolling, with wait and finished actions for checking a changing screen or ending a task. The mobile template adds operations such as a long press, opening an app and navigating home or back. A separate grounding template asks for an Action without the Thought and is intended for lightweight action-output tasks. Choose the action vocabulary that the execution environment actually understands rather than treating every template as interchangeable.
A useful task brief names the goal, supplies the current screenshot and relevant action history, and defines what completion looks like. For example, an original editorial brief might ask the model to find a named setting, change it to a specified value and stop after the new state is visible. Request the next step against the current screen rather than a long speculative sequence. Keep instructions and any limits on allowed operations explicit; after an executed step, return the resulting screen so subsequent reasoning uses observations rather than assumptions about what happened.
Coordinate handling is a material part of the official workflow. The repository separates model prediction from post-processing that parses an action and maps its target to the screen. Its coordinate guide demonstrates converting coordinates from the resized image back to the original image dimensions. Preserve the original screenshot width and height and use the coordinate convention of the exact action template and parser. A location that appears plausible in a resized image can point to a different control if it is applied directly to the unscaled screen. The model’s action text is therefore an instruction to interpret, not an already executed mouse event.
The deployment guide provides a concrete single-step example whose result contains Thought and Action, while the repository’s desktop application is a separate execution surface. The guide’s configured input length and its sample output budget are deployment settings, not a universal claim about every integration’s context or action limit. For practical GUI work, send clear, readable screenshots with the controls and surrounding context needed for the next decision. UI-TARS can misidentify elements, describe unfamiliar interfaces incorrectly or choose a suboptimal action, particularly when the screen is ambiguous; checking the new screenshot after each action keeps those errors tied to the actual task state.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits bytedance/ui-tars-1.5-7b | 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.0002 / 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "bytedance/ui-tars-1.5-7b", "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='bytedance/ui-tars-1.5-7b',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='bytedance/ui-tars-1.5-7b',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 bytedance/ui-tars-1.5-7b
Use the method paths shown above.
bytedance/ui-tars-1.5-7bUI-TARS-1.5-7B is ByteDance’s open multimodal model for computer-use agents. It reasons over screenshots and a task, then produces the next GUI action for an application to execute; this 7B release focuses on general computer use rather than game optimisation.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
UI-TARS-1.5-7B is ByteDance’s released 7B multimodal GUI-agent model, focused on general computer use. It combines visual perception of an interface with reasoning before action, building on the native UI-TARS architecture with reinforcement learning. The inputs in the official usage flow are an instruction, screenshots and action history; the output describes the next interface action, often with a Thought explaining the intended step. A surrounding application executes that action and supplies the next screenshot so the task can continue.
The producer distinguishes this downloadable 7B checkpoint from the larger UI-TARS-1.5 research model. The 7B release is not specifically optimised for game-based scenarios, so demonstrations and results from the larger research model should not be treated as equivalent capabilities of this edition. Its practical role is interacting with visible application controls: browser navigation, office software, file management and similar desktop workflows. Reading a screenshot and choosing an action is different from generating a video or obtaining unseen application state.
The official repository describes desktop and mobile action templates. Desktop actions cover clicks, double and right clicks, dragging, keyboard shortcuts, text entry and scrolling, with wait and finished actions for checking a changing screen or ending a task. The mobile template adds operations such as a long press, opening an app and navigating home or back. A separate grounding template asks for an Action without the Thought and is intended for lightweight action-output tasks. Choose the action vocabulary that the execution environment actually understands rather than treating every template as interchangeable.
A useful task brief names the goal, supplies the current screenshot and relevant action history, and defines what completion looks like. For example, an original editorial brief might ask the model to find a named setting, change it to a specified value and stop after the new state is visible. Request the next step against the current screen rather than a long speculative sequence. Keep instructions and any limits on allowed operations explicit; after an executed step, return the resulting screen so subsequent reasoning uses observations rather than assumptions about what happened.
Coordinate handling is a material part of the official workflow. The repository separates model prediction from post-processing that parses an action and maps its target to the screen. Its coordinate guide demonstrates converting coordinates from the resized image back to the original image dimensions. Preserve the original screenshot width and height and use the coordinate convention of the exact action template and parser. A location that appears plausible in a resized image can point to a different control if it is applied directly to the unscaled screen. The model’s action text is therefore an instruction to interpret, not an already executed mouse event.
The deployment guide provides a concrete single-step example whose result contains Thought and Action, while the repository’s desktop application is a separate execution surface. The guide’s configured input length and its sample output budget are deployment settings, not a universal claim about every integration’s context or action limit. For practical GUI work, send clear, readable screenshots with the controls and surrounding context needed for the next decision. UI-TARS can misidentify elements, describe unfamiliar interfaces incorrectly or choose a suboptimal action, particularly when the screen is ambiguous; checking the new screenshot after each action keeps those errors tied to the actual task state.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits bytedance/ui-tars-1.5-7b | 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.0002 / 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "bytedance/ui-tars-1.5-7b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'bytedance/ui-tars-1.5-7b', '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': 'bytedance/ui-tars-1.5-7b', '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 bytedance/ui-tars-1.5-7b
Use the method paths shown above.
Technical example in English
Choose a safe next interface step\n\nGoal: enable weekly email summaries. Text description of the current settings page: a checkbox labelled Weekly summary is unchecked; a Save button is below it. History: settings opened, no changes saved. Describe the next interface action and the state to verify afterward. Use labels rather than inventing screen coordinates.One proposed action, a brief reason and the resulting visible state an application should check.Check that the answer proposes checking Weekly summary before saving and does not claim that any click was executed.