Step R1 V Mini is StepFun’s multimodal reasoning model for image-and-text input and text output. It brings visual perception into a written reasoning task: identify what is visible, relate the relevant details and explain a conclusion. Its maker demonstrates three concrete applications—recognizing a location from a photograph, describing a dish and recipe, and counting objects under a stated condition.
Supply the image and a question that identifies the result you need. A counting task can specify which objects qualify and which should be excluded. A scene question can ask which visible features support a proposed location. A food photograph can prompt a description of the visible dish before a suggested recipe. Keeping the observation and the conclusion separate makes the answer easier to check.
For example, provide a photograph of a tray of differently shaped items and ask for the number of red circular items, with a short explanation of the counting rule. Include the entire relevant area rather than a crop that removes objects mentioned in the question. If part of the image is hidden or unclear, ask the model to state what it can distinguish before estimating the rest.
The maker’s location example combines several cues in a stadium photograph to infer the venue. That workflow is useful for describing a scene or comparing a proposed interpretation with the image. Ask for the visible clues first, then the inference they support. If a conclusion also depends on information outside the photograph, provide that information as a separate source instead of expecting the image alone to establish it.
The recipe example follows the same pattern: interpret the appearance of the food, then develop a written proposal. Supply any known ingredients, dietary requirements or preparation constraints with the image. A photograph can guide the proposal, while the user’s additional facts define requirements that appearance cannot establish.
StepFun describes joint multimodal reinforcement learning with verifiable visual rewards and extensive synthetic multimodal data. These methods target reasoning across written and visual evidence. The published examples concern reasoning and understanding; the returned artifact is an explanation, count or proposed recipe in text.
For a reusable workflow, keep the question, image and required answer format together. Request a compact observation list followed by the final result, or define the fields needed by the application. Review important counts and inferred details against the source image. Context and generation settings should follow the selected interface’s own contract; the maker’s introduction does not specify a universal output-token ceiling.
", "aboutText": "Step R1 V Mini is StepFun’s multimodal reasoning model for image-and-text input and text output. It brings visual perception into a written reasoning task: identify what is visible, relate the relevant details and explain a conclusion. Its maker demonstrates three concrete applications—recognizing a location from a photograph, describing a dish and recipe, and counting objects under a stated condition.\n\n### Ask a question about the visible evidence\n\nSupply the image and a question that identifies the result you need. A counting task can specify which objects qualify and which should be excluded. A scene question can ask which visible features support a proposed location. A food photograph can prompt a description of the visible dish before a suggested recipe. Keeping the observation and the conclusion separate makes the answer easier to check.\n\nFor example, provide a photograph of a tray of differently shaped items and ask for the number of red circular items, with a short explanation of the counting rule. Include the entire relevant area rather than a crop that removes objects mentioned in the question. If part of the image is hidden or unclear, ask the model to state what it can distinguish before estimating the rest.\n\n### Use visual clues for a reasoned explanation\n\nThe maker’s location example combines several cues in a stadium photograph to infer the venue. That workflow is useful for describing a scene or comparing a proposed interpretation with the image. Ask for the visible clues first, then the inference they support. If a conclusion also depends on information outside the photograph, provide that information as a separate source instead of expecting the image alone to establish it.\n\nThe recipe example follows the same pattern: interpret the appearance of the food, then develop a written proposal. Supply any known ingredients, dietary requirements or preparation constraints with the image. A photograph can guide the proposal, while the user’s additional facts define requirements that appearance cannot establish.\n\n### Training and task preparation\n\nStepFun describes joint multimodal reinforcement learning with verifiable visual rewards and extensive synthetic multimodal data. These methods target reasoning across written and visual evidence. The published examples concern reasoning and understanding; the returned artifact is an explanation, count or proposed recipe in text.\n\nFor a reusable workflow, keep the question, image and required answer format together. Request a compact observation list followed by the final result, or define the fields needed by the application. Review important counts and inferred details against the source image. Context and generation settings should follow the selected interface’s own contract; the maker’s introduction does not specify a universal output-token ceiling.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Count objects under an explicit rule\n\nCount confirmed red circular objects from these recorded annotations: A is a red circle; B is a red square; C is a blue circle; D is a red shape partly hidden with its outline unknown. Return the confirmed count, included identifiers and ambiguous identifiers. Exclude known nonmatching objects and do not guess D’s shape.A compact count record with included, excluded and ambiguous identifiers and a one-sentence counting rule.Check that color and shape are both required and D remains ambiguous rather than counted as a circle.step-r1-v-miniStep R1 V Mini interprets images and written questions to produce a reasoned text answer. StepFun demonstrates visual location clues, dish recognition and object counting, making it useful for questions that combine visible details with a clear reasoning task.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Step R1 V Mini is StepFun’s multimodal reasoning model for image-and-text input and text output. It brings visual perception into a written reasoning task: identify what is visible, relate the relevant details and explain a conclusion. Its maker demonstrates three concrete applications—recognizing a location from a photograph, describing a dish and recipe, and counting objects under a stated condition.
Supply the image and a question that identifies the result you need. A counting task can specify which objects qualify and which should be excluded. A scene question can ask which visible features support a proposed location. A food photograph can prompt a description of the visible dish before a suggested recipe. Keeping the observation and the conclusion separate makes the answer easier to check.
For example, provide a photograph of a tray of differently shaped items and ask for the number of red circular items, with a short explanation of the counting rule. Include the entire relevant area rather than a crop that removes objects mentioned in the question. If part of the image is hidden or unclear, ask the model to state what it can distinguish before estimating the rest.
The maker’s location example combines several cues in a stadium photograph to infer the venue. That workflow is useful for describing a scene or comparing a proposed interpretation with the image. Ask for the visible clues first, then the inference they support. If a conclusion also depends on information outside the photograph, provide that information as a separate source instead of expecting the image alone to establish it.
The recipe example follows the same pattern: interpret the appearance of the food, then develop a written proposal. Supply any known ingredients, dietary requirements or preparation constraints with the image. A photograph can guide the proposal, while the user’s additional facts define requirements that appearance cannot establish.
StepFun describes joint multimodal reinforcement learning with verifiable visual rewards and extensive synthetic multimodal data. These methods target reasoning across written and visual evidence. The published examples concern reasoning and understanding; the returned artifact is an explanation, count or proposed recipe in text.
For a reusable workflow, keep the question, image and required answer format together. Request a compact observation list followed by the final result, or define the fields needed by the application. Review important counts and inferred details against the source image. Context and generation settings should follow the selected interface’s own contract; the maker’s introduction does not specify a universal output-token ceiling.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits step-r1-v-mini | 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 $0.00484 / 1K tokens Output · Output tokens $0.022 / 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": "step-r1-v-mini", "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='step-r1-v-mini',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='step-r1-v-mini',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 step-r1-v-mini
Use the method paths shown above.
step-r1-v-miniStep R1 V Mini interprets images and written questions to produce a reasoned text answer. StepFun demonstrates visual location clues, dish recognition and object counting, making it useful for questions that combine visible details with a clear reasoning task.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Step R1 V Mini is StepFun’s multimodal reasoning model for image-and-text input and text output. It brings visual perception into a written reasoning task: identify what is visible, relate the relevant details and explain a conclusion. Its maker demonstrates three concrete applications—recognizing a location from a photograph, describing a dish and recipe, and counting objects under a stated condition.
Supply the image and a question that identifies the result you need. A counting task can specify which objects qualify and which should be excluded. A scene question can ask which visible features support a proposed location. A food photograph can prompt a description of the visible dish before a suggested recipe. Keeping the observation and the conclusion separate makes the answer easier to check.
For example, provide a photograph of a tray of differently shaped items and ask for the number of red circular items, with a short explanation of the counting rule. Include the entire relevant area rather than a crop that removes objects mentioned in the question. If part of the image is hidden or unclear, ask the model to state what it can distinguish before estimating the rest.
The maker’s location example combines several cues in a stadium photograph to infer the venue. That workflow is useful for describing a scene or comparing a proposed interpretation with the image. Ask for the visible clues first, then the inference they support. If a conclusion also depends on information outside the photograph, provide that information as a separate source instead of expecting the image alone to establish it.
The recipe example follows the same pattern: interpret the appearance of the food, then develop a written proposal. Supply any known ingredients, dietary requirements or preparation constraints with the image. A photograph can guide the proposal, while the user’s additional facts define requirements that appearance cannot establish.
StepFun describes joint multimodal reinforcement learning with verifiable visual rewards and extensive synthetic multimodal data. These methods target reasoning across written and visual evidence. The published examples concern reasoning and understanding; the returned artifact is an explanation, count or proposed recipe in text.
For a reusable workflow, keep the question, image and required answer format together. Request a compact observation list followed by the final result, or define the fields needed by the application. Review important counts and inferred details against the source image. Context and generation settings should follow the selected interface’s own contract; the maker’s introduction does not specify a universal output-token ceiling.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits step-r1-v-mini | 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 $0.00484 / 1K tokens Output · Output tokens $0.022 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "step-r1-v-mini",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'step-r1-v-mini', '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': 'step-r1-v-mini', '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 step-r1-v-mini
Use the method paths shown above.
Technical example in English
Count objects under an explicit rule\n\nCount confirmed red circular objects from these recorded annotations: A is a red circle; B is a red square; C is a blue circle; D is a red shape partly hidden with its outline unknown. Return the confirmed count, included identifiers and ambiguous identifiers. Exclude known nonmatching objects and do not guess D’s shape.A compact count record with included, excluded and ambiguous identifiers and a one-sentence counting rule.Check that color and shape are both required and D remains ambiguous rather than counted as a circle.