AI NEWS.ccAI is happening. The future is updating.
♡ Saved tools 0
AI NEWS · Model intelligenceExplore capabilities. Make informed choices. ↗Profiles indexed first · Details continuously enriched
THE AI MODEL DIRECTORY Start exploring models here

Find your ideal AI model.

From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.

Popular searches
84,996 model profiles13202 providers / publishers45 capability categories465 with comparable prices · 30 benchmarked
TText generation▧Image generation▷Video generation⌘Code generation◖Speech synthesis♫Music generation⬡3D modeling▤Document analysis
DISCOVER & COMPARE

Explore AI models 2428

Discover models worth your attention

We present DistilCamemBERT-NER, which is DistilCamemBERT fine-tuned for the NER (Named Entity Recognition) task for the French language. The work is inspired by Jean-Baptiste/camembert-ner based on the CamemBERT model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase, for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by two** with the same consumption power thanks to DistilCamemBERT. This model performance is compared to 2 reference models (see below) with the metric f1 score. For the mean inference time measure, an AMD Ryzen 5 4500U @ 2.3GHz with 6 cores was used:

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

We present DistilCamemBERT-Sentiment, which is DistilCamemBERT fine-tuned for the sentiment analysis task for the French language. This model is built using two datasets: Amazon Reviews and Allociné.fr to minimize the bias. Indeed, Amazon reviews are similar in messages and relatively shorts, contrary to Allociné critics, who are long and rich texts. This modelization is close to tblard/tf-allocine based on CamemBERT model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase, for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by two** with the same consumption power thanks to DistilCamemBERT. The dataset comprises 204,993 reviews for training and 4,999 reviews for the test from Amazon, and 235,516 and 4,729 critics from Allocine website. The dataset is labeled into five categories:

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

This model is distilled from the zero-shot classification pipeline on the unlabeled GoEmotions dataset using this script. It was trained with mixed precision for 10 epochs and otherwise used the default script arguments. The model can be used like any other model trained on GoEmotions, but will likely not perform as well as a model trained with full supervision. It is primarily intended as a demo of how an expensive NLI-based zero-shot model can be distilled to a more efficient student, allowing a classifier to be trained with only unlabeled data. Note that although the GoEmotions dataset allow multiple labels per instance, the teacher used single-label classification to create psuedo-labels.

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

This is the cointegrated/rubert-tiny model fine-tuned for classification of sentiment for short Russian texts. The problem is formulated as multiclass classification: `negative` vs `neutral` vs `positive`. We trained the model on the datasets collected by Smetanin. We have converted all training data into a 3-class format and have up- and downsampled the training data to balance both the sources and the classes. The training code is available as a Colab notebook. The metrics on the balanced test set are the following:

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

This is the cointegrated/rubert-tiny model fine-tuned for classification of toxicity and inappropriateness for short informal Russian texts, such as comments in social networks. The problem is formulated as multilabel classification with the following classes: - `non-toxic`: the text does NOT contain insults, obscenities, and threats, in the sense of the OK ML Cup competition. - `insult` - `obscenity` - `threat` - `dangerous`: the text is inappropriate, in the sense of Babakov et.al., i.e. it can harm the reputation of the speaker. The function below estimates the probability that the text is either toxic OR dangerous:

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

This is the cointegrated/rubert-tiny2 model fine-tuned for classification of emotions in Russian sentences. The task is multilabel classification, because one sentence can contain multiple emotions. The model on the CEDR dataset described in the paper "Data-Driven Model for Emotion Detection in Russian Texts" by Sboev et al. The model has been trained with Adam optimizer for 40 epochs with learning rate `1e-5` and batch size 64 in this notebook.

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

laya

convaiinnovations

**Multilingual, non-autoregressive System 1 decision model.** Give it a **state** (text, email, ticket, or JSON) and **typed questions**; it returns typed answers with mathematically calibrated probabilities in a single forward pass (~33 ms) across 100+ languages. Trained with reinforcement learning against strictly proper scoring rules (**RLCD**), so reporting honest probabilities is the only way to maximise reward. It never generates text, so there is nothing to parse and nothing to hallucinate. Python 3.10 or newer. Optional extras: `laya[serve]` (HTTP server), `laya[mcp]` (MCP server), `laya[langchain]` (LangChain and LangGraph), `laya[onnx]` (ONNX Runtime), `laya[fast]` (TileLang GPU fast path). Platform-by-platform setup is in the GitHub README. **Long documents.** `laya-multilingual` reads up to 8,192 tokens with `max_len=8192`. Measured accuracy and time by document length (benchmark script):

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

laya-multilingual

convaiinnovations

Non-autoregressive **System 1 decision model** covering 100+ languages. Give it a **state** (text, email, ticket, or JSON) and **typed questions**; it returns typed answers with probabilities in a single forward pass. No text generation, so nothing to parse and nothing to hallucinate. Part of the Laya family — **use this checkpoint for anything that is not English.** > **Long documents: `laya-multilingual` reads up to 8,192 tokens.** It ships with a 1,024-token limit that cuts long documents off, so pass `max_len=8192` for them: > > > > In the table below, 16 to 18 of 20 requests were answered correctly with up to about 4,000 tokens of text before them; beyond that results vary (8 to 17 of 20), so check long-document accuracy on your own data. Short inputs give identical answers with `max_len=8192`, and speed follows the input's real length, not the limit: short inputs are unchanged, and a 4,000-token input takes about 1.7 s on an Apple GPU.

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

laya-typed-decisions

convaiinnovations

Non-autoregressive **System 1 decision model**, fine-tuned on the typed-decisions workflows: agent-trace observability, customer service, invoice processing and security incidents. **+3.9 points over Jev's published 0.727, above the 0.735 teacher ceiling**, with 2.4x better Brier and 1.6x better score MAE. Jev figures are third-party published, not measured here — there is no TypeSafe API access in this project, and sample sizes and prompts differ. Treat the comparison as indicative.

Text analysis
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗
COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ
How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

AI NEWS · From information to decisions

Follow trends. Find tools. Explore models.

Explore AI news ↗Discover AI tools ↗