← Models
DeepSeek V4.1 Flash Jev
Calibrated answers · Text and images
Jev on DeepSeek V4.1 Flash: ask questions about a conversation or a photo and get a probability for each answer. Questions can be yes/no, multiple choice or a score on a scale, and one call can ask many of them.
Model details
| Endpoint | POST /v1/systemone |
| Question types | Yes/no, multiple choice, score |
| Input | Chat messages, optionally with JPEG or PNG images |
| Output | A probability for each option. The model generates no text. |
| Questions per call | Many. The model reads the conversation once and scores every question against it. |
| Engine latency | ~75 ms for 21 questions on an 8K-character conversation; 95-200 ms with a new photo |
| Compatibility | Text-only requests match TypeSafe's Jev API |
On Autoloops
| Hardware | 4× B200 |
| API | Jev (POST /v1/systemone) |
| Region | US |
| Pricing | $0.30 input, $0.006 cached per 1M tokens. No output tokens. |
| Model ID | deepseek-v4.1-flash |
Capabilities
- Returns calibrated probabilities for yes/no, multiple-choice and score questions
- Answers questions about photos, such as what is in them and what state things are in
- Scores many questions in one request. Repeat requests on the same conversation hit the cache.
- Returns JSON with one entry per question, so there is no free text to parse
- Bills input tokens only, with cached tokens at the cached rate
Ask questions about an image
IMG=$(base64 < photo.jpg | tr -d '\n') # JPEG or PNG
curl https://api.autoloops.ai/v1/systemone \
-H "Authorization: Bearer $AUTOLOOPS_API_KEY" \
-H "Content-Type: application/json" \
-d @- <<EOF
{
"model": "deepseek-v4.1-flash",
"state": [
{"role": "user", "content": [
{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,$IMG"}}
]}
],
"questions": {
"animal": {"type": "choice", "instructions": "Which animal is in the photo?",
"criteria": {"dog": null, "cat": null, "none": null}},
"on_sofa": {"type": "noul", "instructions": "Is the animal on the sofa?"}
}
}
EOF
# → {"answers": {"animal": {"type": "choice", "choice": "dog", "probabilities": {"dog": 0.94, …}},
# "on_sofa": {"type": "noul", "noul": 0.98}}, "usage": {…}}