API, routing, model access, and dashboard updates for LLM Gateway.
A new `smart` model string: choose which models it may resolve to, and let a classifier rate each request so easy prompts go to a cheap model and hard ones go to a frontier model. Existing `auto` behaviour is unchanged. Available to every organization while in beta; not available on DevPass yet.
Read more about Smart Routing →
Watch models your compliance policy blocks today and get told the moment a provider that meets your requirements starts serving them — in-app, by email, or in Slack. Downgrade alerts fire when a provider stops meeting the policy. Available on the Enterprise plan.
Read more about Compliance Alerts →
OpenAI's GPT-6 Sol and GPT-6 Luna are live on the gateway at $2 / $10 and $0.10 / $0.50 per 1M tokens — Sol at half the GPT-5.6 Sol rate, Luna at half the GPT-5.6 Luna input rate and 58% below it on output — with cache reads at 10% of input, a 1.05M-token context window, and reasoning from none to max.
Read more about GPT-6 Sol & Luna at Half the Price →
Anthropic's Claude Opus 5.5 is live on the gateway with a 1M context window, always-on adaptive thinking, and $4 / $20 per 1M tokens — 20% below Claude Opus 5 — with cache reads at $0.20.
Read more about Claude Opus 5.5 →
The new /v1/systemone endpoint returns typed decisions with calibrated probabilities instead of generated text. TypeSafe's Jev 1.13 is the first decision model, billed on input tokens only.
Read more about System One: Typed Decisions →
Perplexity retires its Sonar chat completions API on September 27. On September 25 we move perplexity/sonar to Perplexity's Agent API with no changes to your requests and lower prices, and perplexity/sonar-pro and perplexity/sonar-reasoning-pro stop being routable on September 27.
Read more about Perplexity Sonar Changes September 25 →
The official LLM Gateway extension is now on the VS Code Marketplace. Use your PAYG or DevPass key to select gateway models directly in Copilot Chat and agent mode.
Read more about Native VS Code Integration →
Generate and edit images with OpenAI's GPT Image 2.5 Sunburst and Flare. Both add xhigh and max quality settings through the images API, chat completions, and Playground.
Read more about GPT Image 2.5 Is Here →
The /v1/realtime WebSocket now opens transcription-only sessions: live speech-to-text with no speech model in the loop, billed per minute or per token against the transcription model alone. Lounge gets a Transcribe mode on the same page.
Read more about Realtime Transcription Sessions →
The models directory filters and sorts image, video, and speech models by their real unit prices and shows retirement status as chips; model pages sort providers by price, speed, or context; Seedream 5.0 Pro accepts up to 10 reference images; DevPass shows exact renewal and reset times; and Enterprise licenses warn 90 days before expiry.
Read more about Per-Unit Price Filters, Seedream References & More →
Showing 10 of 98 updates
Load more