Skip to content

Jev โ€‹

Updated

Endpoint: https://mmu.vod-qcloud.com/v1/systemoneAuthentication: VOD ApiToken / Bearer

Jev is a System One decision model. It does not generate prose or chat text. Instead, it takes a piece of state (state) plus a set of structured questions and returns typed answers with calibrated probabilities that your code can branch on directly. It is built to replace the "ask a generative model for JSON โ†’ parse โ†’ extract a label" step in a pipeline โ€” it is not a substitute for a chat model.

The name System One refers to fast, intuitive judgement, as opposed to generative models that reason in multiple steps: Jev acts as a fast decision function inside your workflow โ€” unstructured state (text or images) in, typed decisions ready for code branching out.

Basic Information โ€‹

ItemValue
Endpointhttps://mmu.vod-qcloud.com/v1/systemone
AuthenticationApiToken issued by the VOD application / Bearer
RequestPOST; JSON for text, multipart/form-data recommended for images
OutputTyped JSON (answer + calibrated probability); no generated text
BillingInput tokens only โ€” output tokens are free

Callable Models โ€‹

Model IDNotes
jev-1.14.0Adds image input and Box questions (experimental)
jev-1.13.0Text only; returns 400 for Box questions
jev-latestPoints to the latest version. Pin a specific version in production

Question Types โ€‹

Up to 8 questions per request. Questions are evaluated independently and share the input cost of the same state.

TypePurposeReturns
choicePick one option from a predefined set (classification / routing)Selected option, probability distribution over options, confidence
noulDecide whether a statement holds (yes / no)A probability between 0 and 1 (the probability of "yes")
scoreRate on an ordered scaleProbability-weighted score, scale legend, distribution, confidence
box (1.14+, experimental)Locate a target in an imageBounding box top / bottom / left / right (0โ€“1 ratios of image height/width), confidence
  • Choice: 2โ€“20 options, each with a short description.
  • Score: 2โ€“10 levels. The returned score is a probability-weighted expectation and may fall between two levels.
  • Noul: no separate confidence field โ€” threshold on the probability itself.
  • Box: only answers "where", never "whether". It returns four bounds even when the target is not in the image, so it must be paired with a Noul question in the same request to decide whether the target exists.

Input Limits โ€‹

Text โ€‹

ItemLimit
state (serialized)8,000 characters
instructions per question1,800 characters
criteria (serialized)2,000 characters
Standard request total64K tokens; state + the single longest question โ‰ค 32K tokens
Long context (experimental)Up to 262K tokens via a dedicated request header

Images (1.14+, experimental) โ€‹

ItemSpec
Allowed instate, instructions or criteria
FormatsPNG, JPEG (GIF, WebP and animated PNG are rejected)
Dimensions256โ€“1568 px per side; at least 78,400 total pixels
Sizeโ‰ค 16 MiB per image; โ‰ค 32 MiB of images per request
Required headerTypeSafe-Danger-Zone-Images: true (when using images or Box)

multipart/form-data is recommended for images: one JSON part named request, plus each image as its own file part. Base64 also works, but inflates image size by about one third and lowers throughput by about 14โ€“16% when upstream bandwidth is tight.

Jev rejects non-compliant images instead of resizing them โ€” validate dimensions and format on your server before uploading.

Output Characteristics โ€‹

  • Typed output: structured JSON your code can branch, sort and route on immediately โ€” no text parsing.
  • Calibrated probabilities: trained for calibration, so confidence values are statistically meaningful and can drive auto-execute thresholds. Calibration is a population-level property; it does not guarantee any single answer is correct.
  • No reasoning or explanation: only answers and probabilities are returned.

Typical Use Cases โ€‹

  • Classifying and routing support tickets
  • Scoring urgency / risk level
  • Safety checks on tool calls in agent workflows
  • Violation-type decisions in content moderation
  • Re-ranking search results
  • Detecting and locating targets in images (with Noul for existence)

Request Examples โ€‹

Ticket classification and urgency scoring (text, multiple questions) โ€‹

json
{
  "model": "jev-1.13.0",
  "state": {
    "message": "I was charged twice for my March invoice. Please refund the duplicate charge today.",
    "customer_tier": "enterprise"
  },
  "questions": {
    "category": {
      "type": "choice",
      "instructions": "What is this ticket about?",
      "criteria": {
        "billing": "Payments, invoices, or refund requests",
        "technical": "Broken product or unexpected behavior",
        "account": "Login, permissions, or profile issues",
        "other": "Anything else"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "How urgent is this ticket?",
      "criteria": [
        "Can wait for the next release",
        "Should be resolved this week",
        "Needs attention within 24 hours",
        "Needs immediate attention"
      ]
    },
    "refund_requested": {
      "type": "noul",
      "instructions": "Is the customer explicitly requesting a refund?"
    }
  }
}

Response (illustrative) โ€‹

json
{
  "category": { "choice": "billing", "confidence": 0.91 },
  "urgency": { "score": 2.6, "confidence": 0.85 },
  "refund_requested": { "noul": 0.96 }
}

Safety gate before an agent tool call (Noul) โ€‹

json
{
  "model": "jev-1.13.0",
  "state": { "action": "bash", "command": "rm -rf ./dist && npm run build" },
  "questions": {
    "allow_without_confirmation": {
      "type": "noul",
      "instructions": "Is this command safe to run without asking the user?"
    }
  }
}

Suggested thresholds: โ‰ฅ 0.9 run directly; 0.6โ€“0.9 ask the user to confirm; < 0.6 block and escalate to a human.

Locating a target in an image (Box + Noul, multipart) โ€‹

Scenario: decide whether a screenshot contains a "Submit" button and where it is. Because Box returns bounds even when the target is absent, a Noul question is required.

http
POST /v1/systemone
Content-Type: multipart/form-data; boundary=----JevBoundary
TypeSafe-Danger-Zone-Images: true

------JevBoundary
Content-Disposition: form-data; name="request"
Content-Type: application/json

{
  "model": "jev-1.14.0",
  "state": "Analyze the screenshot.",
  "questions": {
    "target_exists": {
      "type": "noul",
      "instructions": "Does the screenshot contain a 'Submit' button?"
    },
    "target_location": {
      "type": "box",
      "instructions": "the 'Submit' button in the screenshot"
    }
  }
}
------JevBoundary
Content-Disposition: form-data; name="screenshot"; filename="screen.png"
Content-Type: image/png

<raw PNG bytes>
------JevBoundary--
  • Images are sent as separate file parts. The JSON part needs no assets field โ€” just mention the image by its reference name in state / instructions (the reference name is the file part's name).
  • Write Box instructions as a description of the target, not a command โ€” e.g. the Submit button, not Locate the Submit button.

Response (illustrative) โ€‹

json
{
  "target_exists": { "noul": 0.97 },
  "target_location": {
    "box": { "top": 0.72, "bottom": 0.81, "left": 0.45, "right": 0.58 },
    "confidence": 0.89
  }
}

In your code, check existence with the target_exists probability first, then convert the Box ratios to pixels:

python
if result["target_exists"]["noul"] > 0.8:
    box = result["target_location"]["box"]
    x = box["left"] * image_width
    y = box["top"] * image_height

Quick check with curl โ€‹

Text request (Noul)

bash
curl -X POST https://mmu.vod-qcloud.com/v1/systemone \
  -H "Authorization: Bearer $YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jev-latest",
    "state": "Customer message: My checkout page shows a blank screen after I click Pay.",
    "questions": {
      "is_defect": {
        "type": "noul",
        "instructions": "Is the customer reporting a software defect?"
      }
    }
  }'

Image request (multipart, Box + Noul)

bash
curl -X POST https://mmu.vod-qcloud.com/v1/systemone \
  -H "Authorization: Bearer $YOUR_API_TOKEN" \
  -H "TypeSafe-Danger-Zone-Images: true" \
  -F 'request={
    "model": "jev-1.14.0",
    "state": "Analyze the uploaded screenshot.",
    "questions": {
      "target_exists": {
        "type": "noul",
        "instructions": "Does the screenshot contain a Submit button?"
      },
      "target_location": {
        "type": "box",
        "instructions": "the Submit button"
      }
    }
  };type=application/json' \
  -F 'screenshot=@screen.png;type=image/png'
  • request is a reserved part name and cannot be used as an image reference name.
  • The image part's name (screenshot above) must match the reference name used in state / instructions.
  • The image part's Content-Type must be image/png, image/jpeg, image/jpg or application/octet-stream.

Integration Options โ€‹

MethodNotes
HTTP APIPOST /v1/systemone; JSON for text, multipart recommended for images
Python / JS SDKHandles multipart upload and image references automatically; recommended for production
Request headerImages and Box require TypeSafe-Danger-Zone-Images: true

Known Limitations โ€‹

Capability boundaries โ€‹

Jev performs poorly on the following; use a generative model or a dedicated method instead:

  • Cannot count: not suited to exact counting or numeric calculation.
  • Cannot compare dates: ordering dates or computing intervals is unreliable.
  • Lower accuracy outside English: English is the primary training language; test other languages on real data.
  • Does not generate text: use a generative model for summaries, translation, rewriting or explanations.
  • Weaker on multimodal than text: per the official guidance, all models including Jev do worse on multimodal data than on text โ€” break questions down to their simplest elements.
  • Sensitive to adversarial content: user-controlled text in state can sway the decision; add safeguards around it.
  • Takes instructions literally: Jev answers the question you wrote, not the one you meant.

Structural limitations โ€‹

LimitationNotes
No reasoning or explanationOnly answers and probabilities
Box has no "not found" answerReturns bounds even when the target is absent; pair with a Noul in the same request
Box requires 1.14+1.13 and earlier return 400 for Box questions
Images and Box are experimentalRequest format, answers and limits may change between versions
Confidence โ‰  correctnessHigh confidence does not guarantee a single answer is right
Unstable during testingAvailability and behavior may change without notice

Not suitable for โ€‹

  • Open-ended chat, creative writing, long explanations
  • Tasks needing deep reasoning or multi-step logic chains
  • Highly regulated scenarios that require traceable reasoning
  • A drop-in replacement for general chat or multimodal models

Recommendations โ€‹

  • PoC images and Box first: both are experimental โ€” validate with real data before going live.
  • Always pair Box with Noul: never use Box alone to decide whether a target exists.
  • Pre-process images: validate dimensions and format on the server before upload.
  • Set confidence thresholds: higher thresholds for high-risk actions; route low confidence to a human.
  • Add a fallback option to Choice: include other or none.
  • Keep questions atomic: split complex judgements into several questions and combine them in code.
  • Pin the version: use a specific version in production (e.g. jev-1.14.0), not jev-latest.

Built with VitePress ยท Deployed on Tencent EdgeOne Pages