Bring the whole conversation.
We support chat-format context. Send a conversation as
messages with roles, then ask questions about the
exchange—not just the last message.
OPEN MODELS. STRUCTURED DECISIONS.
Turn context into
clear decisions.
Give an open model a message and a few questions.
Get choices, scores, and answers your code can use.
A little model.
A very specific job.
Try the demo API in one request
No login. No API key. (Limited to 2k context, and 4 RPS)
Request · curl
curl https://simple-jev-demo-api.featherless.ai/v1/classifier \
-H 'Content-Type: application/json' \
-d '{
"model": "featherless-ai/gemma-4-26B-A4B-classifier",
"state": "Mia owns a red bicycle.",
"questions": {
"color": {
"type": "choice",
"instructions": "What color is Mia’s bicycle?",
"criteria": {"red": null, "blue": null}
}
}
}'
## For production usage and higher rate limits,
## please signup for a developer account at https://featherless.ai
Response · answers
{
"color": {
"type": "choice",
"choice": "red",
"confidence": 1,
"probabilities": {
"red": 1,
"blue": 1.8874485308018052e-10
}
}
}
Actual Gemma response, showing the answers field. Results
may vary. Demo limits: 2k tokens · 4 requests/second.
Full API documentation ↗
01 / TRY IT
Your context. Your questions.
Edit scenarios, build questions, and see real model responses in the interactive playground.
SEE IT IN ACTION
Small decisions. Cool demos.
MORE WAYS TO BRING CONTEXT
Conversations. Images. Decisions.
Ask about what the model sees.
Use images as context for your questions. Image and vision support is available for Gemma and Qwen models only.
The playground demonstrates text input.02 / THE IDEA
Let the model decide.
Let your code do the rest.
Use existing open language models as classifiers.
No separate
classifier head required.
Bring the context
A message, chat history, or structured state. Ask several questions about the same input.
Score the possible answers
We read the next-token logits for the allowed labels and reuse the shared prompt cache across questions.
Put the decisions to work
Your application receives structured JSON. Route a ticket, rank a result, or choose the next step.
ONE MORE THING
Your task.
Your smaller, sharper model.
Really Fancy Decision Training. Bring examples and answers—or ask a larger teacher model to label them. RFDT fine-tunes the decisions your application actually needs.
Explore RFDT
YOUR EXAMPLES
Your answersor a teacher
RFDTTrain the decision logits
A model for your task
READY FOR MORE?
Intelligence too cheap to meter.
Simple Jev models on Featherless start at
$0.03 per million input tokens, with higher limits
on developer plans. Currently in beta.
Support for hosted
fine-tuned models and fine-tuning is on the way as usage grows.
*Prices may change after beta. Refer to Featherless.ai official pricing for up-to-date information.