AI Gateway logs now show session affinity

Vercel's AI Gateway logs now include a Sessions view that groups requests into sessions and shows how session affinity routed each turn, according to Vercel's documentation. Each row identifies the coding agent or app that ran the session — such as Claude Code, Codex, or Cursor — with its cost, models, providers, and cached-input share, and opening a session reveals cache hit rate, duration, and a per-turn path naming the serving provider and any earlier ones. Session affinity, which runs by default on text and chat requests, sends each turn to the provider that served the previous one so more of each prompt is read from cache; developers can group requests manually by sending the same sessionId in providerOptions.gateway or the same x-session-id header, and requests without either are grouped by a fingerprint of the conversation's opening.

AI Gateway logs https://vercel.com/docs/ai-gateway/observability-and-spend/logs now have a Sessions view https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway%2Flogs%3FgroupBy%3Dsessions&title=AI+Gateway+Sessions that groups requests into sessions and shows how session affinity routed each one. Each row shows the coding agent https://vercel.com/docs/ai-gateway/coding-agents or app that ran the session, such as Claude Code, Codex, or Cursor, along with its cost, models, providers, and how much of its input was cached across every turn. Open a session to see its cache hit rate, duration, and path. The path lists each turn with its model and timing, and names the provider serving the session along with any earlier ones. Session affinity https://vercel.com/docs/ai-gateway/models-and-providers/session-affinity sends each turn to the provider that served the one before it, so the provider already has most of the prompt in cache. A session that stays on one provider reads more of each prompt from cache https://vercel.com/docs/ai-gateway/models-and-providers/automatic-caching . Filter sessions by turns, client, model, provider, authentication, or cost. Single-turn sessions are hidden until you clear the minimum turns filter. Session affinity runs by default on text and chat requests. To group requests yourself, send the same sessionId in providerOptions.gateway , or the same x-session-id header, on every request in a conversation. Requests without one are grouped by a fingerprint of the conversation's opening and appear as fingerprinted sessions. Read the session affinity documentation https://vercel.com/docs/ai-gateway/models-and-providers/session-affinity for more information on how AI Gateway identifies sessions.