Solar Decide Flash is Upstage’s low-latency structured decision model, built on Solar Mini 4. Its Flash profile is described as a faster variant of Solar Decide. The model’s role is a decision over supplied text, with the result interpreted by the surrounding application.
The published profile identifies text input and decision output. Prepare a bounded task, such as screening a supplied message against a clearly stated condition or deciding how a text item should enter a workflow. Name the evidence to inspect, the criterion being applied and the decision the next step needs. Keep quoted material separate from instructions so the result can be checked against the original text.
The published context window is 524,288 tokens. Preserve the details that determine the decision, including the source identifier and any relevant exception, and remove unrelated repetition. For a long source, state which question applies to the material and retain the passages needed to interpret the answer. The hosting interface determines the accepted request structure and the usable budget for that request.
Store the decision with the original text and the criterion used to evaluate it. Review ambiguous cases against that evidence, and make the application’s next action explicit. This creates a traceable decision record instead of a result detached from the material it was meant to assess.
", "aboutText": "Solar Decide Flash is Upstage’s low-latency structured decision model, built on Solar Mini 4. Its Flash profile is described as a faster variant of Solar Decide. The model’s role is a decision over supplied text, with the result interpreted by the surrounding application.\n\n### Text input and a focused decision\n\nThe published profile identifies text input and decision output. Prepare a bounded task, such as screening a supplied message against a clearly stated condition or deciding how a text item should enter a workflow. Name the evidence to inspect, the criterion being applied and the decision the next step needs. Keep quoted material separate from instructions so the result can be checked against the original text.\n\n### Working with the context\n\nThe published context window is 524,288 tokens. Preserve the details that determine the decision, including the source identifier and any relevant exception, and remove unrelated repetition. For a long source, state which question applies to the material and retain the passages needed to interpret the answer. The hosting interface determines the accepted request structure and the usable budget for that request.\n\n### Keep the result connected to its evidence\n\nStore the decision with the original text and the criterion used to evaluate it. Review ambiguous cases against that evidence, and make the application’s next action explicit. This creates a traceable decision record instead of a result detached from the material it was meant to assess.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "e8b70e26250779c9675c8146c8608c73728eb70091710c211465239e28e080d9", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "upstage/solar-decide-flashSolar Decide Flash is Upstage’s low-latency edition for structured decisions over text. Built on Solar Mini 4, it suits focused decision steps that return a result for an application to interpret.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Solar Decide Flash is Upstage’s low-latency structured decision model, built on Solar Mini 4. Its Flash profile is described as a faster variant of Solar Decide. The model’s role is a decision over supplied text, with the result interpreted by the surrounding application.
The published profile identifies text input and decision output. Prepare a bounded task, such as screening a supplied message against a clearly stated condition or deciding how a text item should enter a workflow. Name the evidence to inspect, the criterion being applied and the decision the next step needs. Keep quoted material separate from instructions so the result can be checked against the original text.
The published context window is 524,288 tokens. Preserve the details that determine the decision, including the source identifier and any relevant exception, and remove unrelated repetition. For a long source, state which question applies to the material and retain the passages needed to interpret the answer. The hosting interface determines the accepted request structure and the usable budget for that request.
Store the decision with the original text and the criterion used to evaluate it. Review ambiguous cases against that evidence, and make the application’s next action explicit. This creates a traceable decision record instead of a result detached from the material it was meant to assess.
POST /v1/systemonetextdecisions| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits upstage/solar-decide-flash | Default— |
Fieldprovider | Typeschema | RequirementOptional | Values & limits | Default— |
Fieldquestions | Typeobject | RequirementRequired | Values & limits | Default— |
Fieldsession_id | Typestring | RequirementOptional | Values & limits | Default— |
Fieldstate | Typeschema | RequirementRequired | Values & limits | Default— |
Fieldtrace | Typeschema | RequirementOptional | Values & limits | Default— |
Fielduser | Typestring | RequirementOptional | Values & limits | Default— |
Fieldquestions.<id>.type | Typestring | RequirementRequired | Values & limits noul, choice, score | Default— |
Fieldquestions.<id>.instructions | Typestring|object|array | RequirementRequired | Values & limits | Default— |
Fieldquestions.<id>.criteria | Typeobject|array | RequirementOptional | Values & limits Conditions: choice/score: required; noul: optional. choice criteria is object; score is array with minItems1. | Default— |
Fieldquestions.<id>.criteria.true | Typestring|object|array | RequirementRequired | Values & limits Applies when: noul criteria object supplied | Default— |
Fieldquestions.<id>.criteria.false | Typestring|object|array | RequirementRequired | Values & limits Applies when: noul criteria object supplied | Default— |
noul · Required: state, questions.<id>.type=noul, questions.<id>.instructions
choice · Required: state, questions.<id>.type=choice, questions.<id>.instructions, criteria object
score · Required: state, questions.<id>.type=score, questions.<id>.instructions, criteria array with minItems1
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, state, questions |
Parametermaterial_types | Contracttext |
Parameteroptional_controls | Contractprovider, session_id, trace, user |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous
Send the exact model ID and retain the complete native response.
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 / 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 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "upstage/solar-decide-flash",\n "questions": {\n "is_bug": {\n "criteria": {\n "false": "The customer is asking a question or requesting a feature.",\n "true": "The customer describes broken or unexpected product behavior."\n },\n "instructions": "Is the customer reporting a software defect?",\n "type": "noul"\n },\n "team": {\n "criteria": {\n "account": "Login, permissions, or profile issues.",\n "frontend": "Rendering, layout, or browser compatibility issues.",\n "payments": "Checkout, billing, or payment processing issues."\n },\n "instructions": "Which team should own this ticket?",\n "type": "choice"\n },\n "urgency": {\n "criteria": [\n "Can wait for the next release",\n "Should be fixed this week",\n "Blocking revenue right now"\n ],\n "instructions": "How urgent is this ticket?",\n "type": "score"\n }\n },\n "state": {\n "customer_tier": "enterprise",\n "ticket": "My checkout page shows a blank screen after I click Pay. I have tried two browsers."\n }\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_REQUEST_FILE:?Set your actual JSON request file}"\nexport AILOOT_REQUEST_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads(Path(os.environ['AILOOT_REQUEST_FILE']).read_text(encoding='utf-8'))\nif not isinstance(p,dict): raise SystemExit('Request must be a JSON object')\np['model']='upstage/solar-decide-flash'\nPath('request.json').write_text(json.dumps(p,ensure_ascii=False),encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/systemone \\\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\nprint(json.dumps(json.loads(Path('result.json').read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\njson
Keep every complete returned response, file and content part.
Every supplied question-ID answer with its exact type, noul/choice/score value, confidence, probabilities and legend is retained. Entire original JSON is stored and returned only after settlement.
Preserve original operation and full/partial reply; do not replay POST.
| Field | Type |
|---|---|
Fieldmodel | Typestring |
Fieldid | Typestring |
Fieldprovider | Typestring |
Fieldanswers.<id>.type | Typestring |
Fieldanswers.<id>.noul | Typenumber |
Fieldanswers.<id>.choice | Typestring |
Fieldanswers.<id>.score | Typenumber |
Fieldanswers.<id>.confidence | Typenumber |
Fieldanswers.<id>.probabilities | Typeobject |
Fieldanswers.<id>.legend | Typeobject |
Fieldusage.input_tokens | Typeinteger |
Fieldusage.output_tokens | Typeinteger |
Fieldusage.cost | Typenumber |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required field, representation or value | Next stepCorrect the indicated request field. |
Ailoot Ultra upstage/solar-decide-flash
Use the method paths shown above.