Netlify adds support for OpenAI's new GPT-6 Sol and Luna models to its AI Gateway and Agent Runners.

// 1h agoPRODUCT UPDATE

Netlify adds support for OpenAI's new GPT-6 Sol and Luna models to its AI Gateway and Agent Runners.

Netlify has updated its Agent Runners and AI Gateway to support OpenAI's newly released GPT-6 Sol and Luna models. Developers building AI agents on Netlify can seamlessly access these models through the Responses API (e.g., using the `gpt-6-sol` model tag) with zero configuration and no API keys required.

// ANALYSIS

This update reinforces Netlify's position as a premier, frictionless platform for deploying modern AI agents by bringing rapid, zero-config access to OpenAI's latest models.

–Immediate model availability: Swift integration of OpenAI's GPT-6 Sol and Luna ensures developers can immediately leverage state-of-the-art capabilities.
–Zero-config developer experience: Bypassing API key management drastically lowers the friction and security overhead of deploying complex AI features.
–Robust agent ecosystem: Combining Agent Runners with the AI Gateway provides a tightly integrated environment for shipping scalable, AI-native web applications.

// TAGS

netlifyai-gatewayagent-runnersopenaigpt-6sollunaweb-development

DISCOVERED

1h ago

2026-09-23

PUBLISHED

1h ago

2026-09-23

RELEVANCE

8/ 10

AUTHOR

Netlify

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH1h ago

Self-organizing agent teams outperform oracle routers

Researchers from Stanford, Together AI, and Emory introduced Self-Organizing Agent Teams (SAT), a framework where autonomous LLM groups learn reusable coordination strategies without hand-engineered workflows. Evaluated across five math and physics benchmarks with o3-mini, Claude Sonnet 4, and DeepSeek-V3, the self-organizing team reached 66.7% accuracy, outperforming both the strongest single model (48.8%) and an oracle router (59.0%).

BENCHMARK1h ago

DrivingBench benchmarks frontier LLMs driving real car

DrivingBench is an experimental real-world robotics benchmark created by Aditya Ramabadran, Simon Mahns, and Tobias Gessler to evaluate whether general-purpose frontier LLMs can navigate an openpilot-equipped 2022 Toyota Corolla through a cone course using Model Context Protocol tools. Across multi-attempt continuous chats testing in-context learning, OpenAI's GPT-6 Astra was the only model to achieve 100% course completion (finishing attempt 2 in 5 minutes and 22 seconds), while Claude Fable 5.1 reached 45% on attempt 3, Grok 4.6 reached 11%, and GPT-5.6 Sol reached 6%.

MODEL1h ago

Recraft launches ultra-fast V4.1 Flash image generation model on fal.ai

Recraft V4.1 Flash is now live on the fal.ai platform, offering high-speed image generation capabilities at approximately 1.5 seconds per image. This rapid generation time is tailored to enhance the creative process by enabling creators to quickly test compositions, iterate on prompts, and explore multiple design directions without long wait times.