# The Gateway Charts > A weekly read of what runs through the Requesty LLM gateway: the models, labs and apps by share of tokens, who moved, speed, reliability and how requests are built. New week every Monday. Shares, rates, ranks and latency only. CC BY 4.0. - Latest week as JSON: https://www.requesty.ai/data/weekly/latest.json - RSS: https://www.requesty.ai/data/weekly/feed.xml - Send `Accept: text/markdown` to any week URL to get Markdown. ## Weeks - [Week 46, Nov 9 to 15, 2026](https://www.requesty.ai/data/weekly/2026-w46/data.md): Last week in AI. Who climbed. Who slipped. JSON: https://www.requesty.ai/data/weekly/2026-w46/data.json - deepseek-v4.1-flash held #1 on the Requesty gateway in week 46 (Nov 9 to 15, 2026) with 28.3% of tokens, up 2.27 points on the week before. - Five coding agents (OpenCode, Claude Code, Pi, DeepSeek Harness and GitHub Copilot) sent 33.4% of tokens through the Requesty gateway in week 46 (Nov 9 to 15, 2026). - 67.6% of active teams on the Requesty gateway used two or more models in week 46 (Nov 9 to 15, 2026); 58.6% used two or more labs and 60.2% two or more providers. - claude-haiku-5-5 reached its first token 1.3x sooner on the Requesty gateway in week 46 (Nov 9 to 15, 2026): a median of 1.76 s, down from 2.21 s the week before, on streaming requests. - In week 46 (Nov 9 to 15, 2026), 96.1% of requests on a fallback policy whose first attempt hit a provider error were still served by another host on the Requesty gateway, up from 86.4% the week before. - 78.1% of input tokens through the Requesty gateway in week 46 (Nov 9 to 15, 2026) were read from a prompt cache; models read 46 input tokens for every output token. - [Week 45, Nov 2 to 8, 2026](https://www.requesty.ai/data/weekly/2026-w45/data.md): Last week in AI. Who climbed. Who slipped. JSON: https://www.requesty.ai/data/weekly/2026-w45/data.json - deepseek-v4.1-flash held #1 on the Requesty gateway in week 45 (Nov 2 to 8, 2026) with 25.9% of tokens, down 3.93 points on the week before. - Five coding agents (OpenCode, Claude Code, Pi, DeepSeek Harness and GitHub Copilot) sent 33.1% of tokens through the Requesty gateway in week 45 (Nov 2 to 8, 2026). - 68.3% of active teams on the Requesty gateway used two or more models in week 45 (Nov 2 to 8, 2026); 59.7% used two or more labs and 61.7% two or more providers. - 87.5% of chat requests through the Requesty gateway in week 45 (Nov 2 to 8, 2026) never set a temperature; 77.6% left reasoning effort unset and 94.4% sent no response format. - claude-sonnet-5 reached its first token 2.3x sooner on the Requesty gateway in week 45 (Nov 2 to 8, 2026): a median of 1.69 s, down from 3.8 s the week before, on streaming requests. - In week 45 (Nov 2 to 8, 2026), 86.5% of requests on a fallback policy whose first attempt hit a provider error were still served by another host on the Requesty gateway; 94.5% of those rescues served the same model. - 77.1% of input tokens through the Requesty gateway in week 45 (Nov 2 to 8, 2026) were read from a prompt cache; models read 46 input tokens for every output token.