5 stories tagged model routing.
LLM model routing promises cost savings by sending easy prompts to cheap models. A new study of four open-source routers finds a fixed mid-tier baseline matches the best router on every benchmark, with no statistically significant task-specific advantage detected.
AI model price war cut US token prices 25% since mid-July. OpenAI slashed Luna 80%, Anthropic halved Opus 5 vs Fable 5, as Chinese rivals close the gap.
Models tend to converge on similar answers. In Springboards tests, Flint scored 7.47 distinct replies out of 10 against LLM groupthink.
After the backlash, Claude Fable 5 guardrails are visible. Builders should log fallback events, cost and retention before trusting runs.
The same Anthropic weights sit behind Claude Fable 5 and Mythos 5; a runtime classifier decides which capability you actually get.