Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
NewsCatcher addresses the frustrations of inconsistent news data and poor integration. We provide clean, normalized, near-real-time articles from 150,000+ global sources in 50+ languages, including hyper-local coverage. Covering over 98% of each website, we extract all essential data points, ensuring you get the critical information you need.
We enrich this data by adding sentiment scores, detecting named entities, summarizing, classifying, deduplicating, and clustering similar articles into events. This maximizes the value of news content while reducing post-processing time and costs.
Beyond traditional news, our BeyondNews and Local News APIs extend coverage further, surfacing government data, policy changes, and official announcements before they become news, plus thousands of hyperlocal outlets, university newspapers, and local government portals across multiple countries.
NewsCatcher helps enterprises seamlessly integrate news insights into workflows by building custom pipelines with LLM fine-tuning, resulting in a clean, relevant feed with a low false-positive rate.
Customers gain full transparency into our data collection and the models we use. We offer monitoring services to ensure customers understand our system's operation and responsiveness to new data sources, including detailed explanations of the models and embeddings applied.
Description
Tev1 is a rapid decision-making and classification model developed by Together AI, which has been fine-tuned from Qwen3.5 4B. Its user-friendly interface allows for the input of a state, a question, and between 2 to 24 labeled choices, enabling the model to output a single letter that can be mapped back to a semantic key by software. This design is particularly beneficial for various production tasks, such as managing support ticket routing, assessing automated returns, enforcing policy guidelines, sentiment analysis, document categorization, and integrating precise decision-making steps into larger agent workflows. With a parameter count of 4.7B and a 32.8K-token context window, the model operates with non-thinking generation to ensure fast and reliable classification. It has been trained on a diverse set of 37,840 examples covering areas such as intent detection, boolean comprehension, sentiment evaluation, policy application, as well as categorizing news and academic papers. The recommended configuration suggests using a temperature setting of 0 along with a minimal output budget, ensuring that the responses are both consistent and straightforward to interpret. In summary, Tev1 stands out as a versatile tool that efficiently addresses a wide range of classification needs.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
CatchAll
Yes
Company Watchlist
Yes
Python
No
Qwen3.5
No
TypeScript
No
Integrations
CatchAll
No
Company Watchlist
No
Python
Yes
Qwen3.5
Yes
TypeScript
Yes
Pricing Details
$10,000 per month
Our pricing varies based on several factors, including the specific product, call volume, speed, service level agreements (SLA), historical data access, and optional add-ons such as translation services, custom pipelines, and dedicated resources. For a tailored quote, please contact our sales team.
Free Trial
Yes
Free Version
No
Pricing Details
$0.04 per 1M tokens
Free Trial
No
Free Version
Yes
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
NewsCatcher
Country
United States
Website
newscatcherapi.com
Vendor Details
Company Name
Together AI
Founded
2022
Country
United States
Website
www.together.ai/models/tev1-4b-experimental