Responses API
PulseAugur coverage of Responses API — every cluster mentioning Responses API across labs, papers, and developer communities, ranked by signal.
- developed Decisions API 95%
- developed by GPT-6 Luna 90%
- uses GPT-6 Luna 90%
- competes with OpenRouter 70%
- competes with chat completions 70%
- competes with Decisions API 70%
- uses Agents API 70%
- competes with GPT-6 Luna 70%
- used by Messages API 70%
- uses chat completions 50%
- used by OpenRouter 50%
- competes with Agents API 50%
11 day(s) with sentiment data
-
OpenAI unveils GPT-6 Cyber for cybersecurity tasks, details pricing and access
OpenAI has announced GPT-6 Cyber, a specialized cybersecurity model set to launch on November 5, 2026. This model, an offshoot of GPT-6 Astra, is designed for authorized security tasks like vulnerability research and ex…
-
OpenAI launches GPT-6.1 Terra for high-volume tasks at reduced cost · 2 sources tracked
OpenAI has released GPT-6.1 Terra, a new model designed for high-volume, computer-centric tasks like invoice processing and form filling, at half the price of its predecessor, GPT-5.6 Terra. While faster and more cost-e…
-
AI Model Migration Guides Detail Parameter Changes and API Behavior
This cluster discusses the migration and configuration of various AI models, focusing on parameter handling and API interactions. Item 1 and 2 introduce concepts related to Anthropic's Claude Code and Agent SDK, suggest…
-
OpenAI launches Decisions API for structured AI agent judgments
OpenAI has released its Decisions API, a new endpoint designed to provide structured judgments instead of conversational text for AI agents. This API, running on GPT-6 Luna, aims to streamline tasks like routing, triage…
-
Red-teaming finds vulnerabilities in OpenAI's agent monitoring systems
A collaborative red-teaming exercise between METR and Redwood Research identified several vulnerabilities in OpenAI's internal agent monitoring systems. The three-week pilot, conducted from July 21st to August 11th, inv…
-
Developers explore OpenAI's new Agents API for agent backends
A developer shared their experience migrating their agent backend to OpenAI's Agents API, highlighting its potential to become a standard like the Chat Completions API. They adopted the official OpenAI package and struc…
-
OpenRouter launches Armor to vet AI agent tool calls
OpenRouter has launched Armor, a new safety classifier designed to vet agent tool calls before they are executed. Armor sits between AI models and applications, checking tool calls against user-defined rules written in …
-
LLM APIs Differently Report Streamed Token Usage
Developers integrating LLMs need to be aware of how token usage is reported in streamed responses, as it differs across APIs. OpenAI's Chat Completions API requires an explicit option to include usage data, which is sen…
-
LLM output validation: Beyond parsing to schema conformance
Multiple articles discuss the critical need for robust validation of Large Language Model (LLM) outputs, especially when they are used in production systems. They highlight that simply parsing JSON output is insufficien…
-
Meta's Muse Wonder API sets team-wide rate limits of 3,000 RPM and 4M TPM
Meta's Muse Wonder API has established rate limits of 3,000 requests per minute (RPM) and 4,000,000 tokens per minute (TPM), applicable per model and per team rather than per API key. These limits are shared across all …
-
OpenAI unveils secure tunnel for private tool integration with AI models
OpenAI has introduced a Secure MCP Tunnel Architecture designed to connect private tools to AI models like ChatGPT and Codex without exposing them to the public internet. This architecture utilizes an outbound-only conn…
-
OpenAI launches Decisions API with input-only billing
OpenAI has launched its Decisions API, a new service that charges solely for input tokens and offers output at no cost. This API is designed for tasks requiring structured outputs like classifications, routing, or scori…
-
OpenAI's API Function Calling Methods Compared
The article compares two methods for integrating function calling with large language models: OpenAI's Chat Completions API and the Responses API. It details how each API handles tool definitions, function call requests…
-
OpenAI launches Decisions API for faster text and image evaluation
OpenAI has launched a new Decisions API in public beta, designed to evaluate text and images approximately ten times faster than its standard Responses API. This new API currently supports only structured responses.
-
AI tool calling explained: Models decide, code executes
This article explains the concept of AI tool calling, where language models decide which functions to execute based on user input rather than directly running code. It details how developers describe available tools (fu…
-
OpenAI launches Decisions API for faster, structured AI classifications · 10 sources tracked
OpenAI has launched its new Decisions API, designed for rapid classification of text and images into structured outputs like yes/no probabilities, category choices, or scale ratings. This API is reportedly up to 10 time…
-
OpenAI launches Decisions API for real-time model and tool selection
OpenAI has launched its Decisions API in public beta, allowing developers to dynamically select the most appropriate model, tool, or action for their applications in real-time. This new API is designed to operate signif…
-
Model Context Protocol (MCP) offers enhanced AI insights but raises token costs
The Model Context Protocol (MCP), introduced by Anthropic and supported by OpenAI, allows AI agents to access external tools and real-time data for more specific and useful responses. While MCP enhances AI agent capabil…
-
OpenAI deprecates Assistants API, shifts to stateless model for agents
OpenAI has deprecated its Assistants API, shifting to a new stateless model centered around the Responses and Conversations APIs. This change moves state management responsibility to developers, offering more control, p…
-
OpenAI offers multiple agent development options with varying control levels
OpenAI offers several options for developers building agentic applications, each with different levels of control over the agent loop. The Responses API requires developers to manage the loop entirely, handling tool exe…