News tagged "long-context"

Diagram showing routing decision tree between Fast mode and Standard tier for long-context API requests

OpenAI Fast Mode Lifts Its Token Cap: What Long-Context Routing Teams Must Decide Now

Fast mode now covers prompts exceeding 272K tokens on GPT-5.6 Sol, Terra, and Luna — closing the gap that forced large-context workloads onto Standard tier, but the ramp rate limit still bites.

August 11, 2026via OpenAI API Changelog

Editorial graphic showing a long-horizon code project ingested into a single 1M-token context window with routing branch indicators

zhipu

GLM-5.2 on OpenRouter & BigModel: Zhipu's 1M-Context Coding Agent with 128K Output

Zhipu GLM-5.2 is now accessible through OpenRouter, BigModel API, and DashScope: 1M-token lossless context, 128K max output, reasoning_effort, context caching, and FrontierSWE-class performance for long-horizon coding-agent routing.

June 17, 2026via Zhipu AI / BigModel