telnyx/decision-pro
AI model by Telnyx
High-performance decision model for complex reasoning and long-context tasks.
A high-intelligence decision model for complex reasoning and long-context tasks, hosted on Telnyx's owned GPUs. It is ideal for businesses needing reliable, scalable decision-making integrated into real-time agents.
Model specs
The full spec card (context, pricing per token, modalities and more) on AntSpace. Sign up free to see the full spec card.
- Price
- From 0.2 USD 0 / 1M tokens (Output included)
- Languages
- English
Category: Generative AI
- Sizes and variants
- telnyx/decision-flash, telnyx/decision-pro
- Access
- API (OpenAI-compatible)
- Input Price
- $0.200 per 1M tokens
- Output Price
- Included in input price
- Context Window
- >32k tokens
- Infrastructure
- Owned GPUs
- High-performance decision model for complex reasoning
- Supports context inputs exceeding 32k tokens
- Hosted on owned GPUs for predictable performance
- OpenAI-compatible API for seamless integration
- Input pricing includes output tokens
Overview
telnyx/decision-pro is a high-performance decision model developed by Telnyx for businesses requiring complex reasoning and long-context analysis. It is specifically designed to handle tasks that exceed the 32k token limit of the decision-flash model, making it suitable for analyzing extensive logs or large document sets. The model is delivered through Telnyx's serverless inference platform and runs on the company's own GPUs to ensure predictable performance and cost-efficiency. It integrates directly into real-time agent infrastructure via an OpenAI-compatible API. Telnyx simplifies billing for this model by including output tokens in the input token price.
Core Capabilities
- Decision Intelligence: The model is designed for high-performance decision-making tasks within real-time agent infrastructure.
- Complex Reasoning: It supports complex reasoning tasks that require analyzing extensive background data or documents.
- Extended Context Support: The model extends the capabilities of the decision-flash version by supporting larger context inputs.
Deployment and Integration
- Owned Infrastructure: The model runs on Telnyx's owned GPUs to provide predictable performance and better economics at scale.
- Serverless Inference: It is delivered via a serverless inference platform for simplified deployment.
- OpenAI Compatibility: The API is fully compatible with OpenAI standards for easy integration.
Use cases
- Businesses analyze extensive logs and documents to make high-intelligence decisions within real-time agent workflows.
- Developers integrate complex reasoning capabilities into AI agents using an OpenAI-compatible API.
- Organizations process large context inputs exceeding 32k tokens for detailed data analysis and choice-making.
Specifications
- Sizes and variants
- telnyx/decision-flash, telnyx/decision-pro
- Access
- API (OpenAI-compatible)
- Input Price
- $0.200 per 1M tokens
- Output Price
- Included in input price
- Context Window
- >32k tokens
- Infrastructure
- Owned GPUs
- Interface
- OpenAI-compatible API
How it works
- Sign Up: Users sign up for a Telnyx account to access the Inference API.
- API Integration: The model is accessed via an OpenAI-compatible API endpoint.
- Usage and Billing: Users pay $0.200 per 1M input tokens with output tokens included in the rate.
Pricing
- telnyx/decision-pro Input tokens
- $0.200 / 1M tokens (Output included)
Added by AntSpace from public sources (telnyx.com).