inference means Running a trained AI model to produce output. It's mostly used in casual online conversation. It's casual and generally safe with friends and online. It's standard online vocabulary; nothing inherently concerning about hearing it.
inference
Running a trained AI model to produce output.
Etymology timeline
Born ~2010 · 1 year of recorded useSeen in the wild
Luca M. Possati: How Light Reshapes the Mind. An Active Inference Framework for the Cognitive and Emotional Effects of Indoor Lighting https://arxiv.org/abs/2605.01290 https://arxiv.org/pdf/2605.01290 https://arxiv.or…
Patrick Aschermayr, Konstantinos Kalogeropoulos, Nikolaos Demiris: Semi-Markov Models with Particle-Based Bayesian Inference for Epidemics https://arxiv.org/abs/2605.02706 https://arxiv.org/pdf/2605.02706 https://arxi…
CellxPert: Inference-Time MCMC Steering of a Multi-Omics Single-Cell Foundation Model for In-Silico Perturbation #SingleCell 🧪🧬🖥️ https://arxiv.org/abs/2605.00930
A third type of inference, abduction, has been proposed, notably by Charles Sanders Peirce.
Inference is traditionally divided into deduction and induction, a distinction that dates at least to Aristotle (300s BC).
Definitions
Running a trained AI model to produce output. Training teaches the model; inference is every time you use it. Inference is what costs money per token.
"Our inference bill doubled after we shipped the AI search."
inference means Running a trained AI model to produce output. It's mostly used in casual online conversation. It's casual and generally safe with friends and online. It's standard online vocabulary; nothing inherently concerning about hearing it.
"inference" is slang. It means: Running a trained AI model to produce output. Register: casual. Use it in: casual conversation and online posts. Avoid in: formal writing and professional emails.
“Luca M. Possati: How Light Reshapes the Mind. An Active Inference Framework for the Cognitive and Emotional Effects of Indoor Lighting https://arxiv.org/abs/2605.01290 https://arxiv.org/pdf/2605.01290 https://arxiv.org/html/2605.01290”
— Bluesky· May 2026“Patrick Aschermayr, Konstantinos Kalogeropoulos, Nikolaos Demiris: Semi-Markov Models with Particle-Based Bayesian Inference for Epidemics https://arxiv.org/abs/2605.02706 https://arxiv.org/pdf/2605.02706 https://arxiv.org/html/2605.02706”
— Bluesky· May 2026“CellxPert: Inference-Time MCMC Steering of a Multi-Omics Single-Cell Foundation Model for In-Silico Perturbation #SingleCell 🧪🧬🖥️ https://arxiv.org/abs/2605.00930”
— Bluesky· May 2026“A third type of inference, abduction, has been proposed, notably by Charles Sanders Peirce.”
“Inference is traditionally divided into deduction and induction, a distinction that dates at least to Aristotle (300s BC).”
Comments
Specifically in AI/ML: running a trained model to produce output, as opposed to training. "Inference cost" = the cost per API call.
"Inference is most of the GPU spend."
Comments
For specific readers
Why is this section here?
Slang is read by different audiences for very different reasons. The For parents view re-explains the term in plain, non-judgemental language so a caregiver can understand what their child means without needing the surrounding subculture. The For English learners view focuses on register (when it's safe to use), formal alternatives, and common mistakes — what a textbook won't teach you.
Used in
Have a better definition?
Add your own interpretation of "inference".
⚡About Tech, Dev & AI slang
The vocabulary of software engineers, AI researchers, and anyone living in a terminal or on GitHub — from LLM to MCP, CORS to vibe coding, agentic to enshittification.
See all Tech, Dev & AI slang on Slangora.
Tags
Other words near "inference" (I)
Browse all slang words starting with I.
Related terms
People also read
Semantically related
- test-time compute69%
Using more compute at inference time — via longer chain-of-thought, sampling, or verification — to boost model quality without retraining. The OpenAI o1 + Claude extended-thinking paradigm. You pay seconds to gain accuracy.
- distillation64%
Training a smaller, cheaper model to mimic the output of a larger one. "The 1B distillation of our 70B model runs fine on a laptop." Critical for shipping AI on devices, edge inference, and cost reduction. Trade-off: distilled models lose nuanced reasoning the parent could do.
- foundation model64%
An AI model trained on comprehensive data, enabling its application across various use cases such as chatbots and generative AI.
- test-time compute63%
The amount of computational power or processing time required for an artificial intelligence system to generate a result or perform a task after it has already been trained.