OpenAI Agents API enters public beta

BetaSep 10, 2026VerifiedAdded Sep 22, 2026

The Agents API runs agents on a managed Codex harness with OpenAI handling session orchestration, context compaction and recovery. It offers durable sessions, streaming, your own tools and MCP servers, and hosted or self-provided sandboxes.

AI agents MCP Streaming Developer tools Coding agents

Read OpenAI's release notes

https://developers.openai.com/api/docs/changelog#sep-10

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More OpenAI API releases

OpenAI APISep 10, 2026

OpenAI project API keys support expiration dates

Project API keys can now be created with an expiration date, and admins can enforce a maximum key lifetime at the organization or project level.

UpdateDeveloper toolsSource

OpenAI APISep 10, 2026

OpenAI GPT-Live 1 is generally available for full-duplex voice

GPT-Live 1 supports full-duplex voice conversations that continue while a backend model or agent handles reasoning and tools. Voice sessions cost $0.05 per minute billed per second, with backend usage charged separately.

GAAI agentsPricingDeveloper toolsSource

OpenAI APISep 10, 2026

Introducing the Agents API

Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.

UpdateAI agentsDeveloper toolsCoding agentsSource

OpenAI APISep 10, 2026

Build more natural voice experiences with GPT‑Live‑1 in the API

GPT‑Live‑1 brings natural, full-duplex voice conversations to the API, with stronger instruction following, custom voices, and telephony support.

UpdateDeveloper toolsSource

OpenAI APISep 8, 2026

OpenAI Prompt Cache Diagnostics is generally available in the Responses API

For GPT-5.6 and later, developers can compare cache reuse against a previous response, see reasons for cache misses and follow guidance to improve cache hit rates.

GALLMsDeveloper toolsSource

OpenAI APISep 8, 2026

OpenAI releases GPT Image 2.5 Sunburst and GPT Image 2.5 Flare

Sunburst targets precise image editing and Flare fast everyday generation, both via the Image API and Responses image tool. They support new xhigh and max quality settings at GPT Image 2 token rates.

UpdateLLMsPricingDeveloper toolsSource

OpenAI APISep 8, 2026

OpenAI GPT-Rosalind is GA for approved life sciences research

gpt-rosalind-research is available through the trusted-access program at $5 input, $0.50 cached input and $25 output per 1M tokens. Billing begins October 5, 2026.

GAPricingSource

OpenAI APISep 15, 2026

OpenAI API adds API key creation governance controls

Admins can allow only service-account keys, only user-owned project keys, or block new key creation at the organization or project level. Organization settings take precedence and existing keys are unaffected.

UpdateGovernanceDeveloper toolsSource

Also shipped on Sep 10, 2026

Google Cloud BigQuerySep 10, 2026

BigQuery conversational analytics adds ML.CORRELATION in preview

Conversational analytics can now use ML.CORRELATION to calculate statistical correlations between a target column and one or more metric columns in a table.

PreviewSQLSource

Google Cloud BigQuerySep 10, 2026

BigQuery ML.METRICS evaluates predictions without a stored model

The preview ML.METRICS function computes classification or regression evaluation metrics on any table or query with actual and predicted values, with no need to create or reference a stored model.

PreviewSQLGovernanceObservabilitySource

Google Cloud BigQuerySep 10, 2026

You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data

You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data. This feature is in Preview .

PreviewSource

Google Cloud BigQuerySep 10, 2026

BigQuery Data Engineering Agent integrates with BigQuery Graph

The Data Engineering Agent now uses BigQuery Graph for extra context between source and destination schemas, improving schema mapping accuracy in data engineering pipelines. It is generally available.

GAAI agentsSQLData integrationSource

Snowflake SnowflakeSep 10, 2026

Using dbt artifacts for Slim CI and defer to production in dbt Projects on Snowflake (General availability)

Slim CI, defer to production, failed-execution recovery, and concurrent execution are now generally available for dbt Projects on Snowflake. Reuse dbt artifacts from recent production executions to accelerate development, streamline CI/CD workflows, and recover from failed production runs without maintaining a separate artifact store.

GAStreamingSource

Snowflake SnowflakeSep 10, 2026

External secret providers (Preview)

External secret providers are now in preview. If your organization already keeps API keys, database passwords, and similar values in AWS Secrets Manager, Azure Key Vault, or Google Cloud Secret Manager, Snowflake can read those values when a query needs them, so you don't have to maintain a second copy in a Snowflake secret .

PreviewSQLSecurityDeveloper toolsSource