GPT-6 Luna is the fast, cost-efficient tier of the GPT-6 series on the Felo API, at $0.10 per million input tokens. Here is what that buys across classification, extraction, chat, and subagent workloads.
GPT-6 Sol sits between the Astra flagship and the Luna fast tier at $2 per million input tokens. Here is the arithmetic of the middle rung, and the routing pattern that gets flagship outcomes without flagship spend.
Claude Opus 5.5 is now on the Felo API with a 1M-token context window, cached input rates, and an Anthropic-compatible Messages endpoint. Here is what caching actually does to the cost of a long-running agent.
Grok 4.7 is live on the Felo API with a 450,000-token maximum output — three and a half times the frontier norm. Here is what that ceiling changes for coding agents, self-verifying loops, and whole-package migrations.
Felo Agents now supports GPT-6 Astra as its reasoning model. Create agents that build slides, images, videos, and web pages — free to try.
Build AI-powered slides from the terminal using Felo Slides with Claude Code, OpenClaw, and the felo-slides npm package. A developer's guide to programmatic slide generation.
Step-by-step guide to installing Felo Skills in Google Antigravity. Get live search, web extraction, slide generation, and X/Twitter search working inside Antigravity agents in under two minutes.