Google launches Gemini Decisions API and Gemini Decision 1
One request can score up to 1,000 closed-set questions for $0.10 per million input tokens, with output tokens free.
1
Stories per day · 30 days
2 RSS
Relatedinference2abliteration1acquisition1benchmark1decisions-api1deepseek1developer-tools1fallback1gemini1github-copilot1google-deepmind1jetbrains1multimodal1openai-compatible1openrouter1open-weight1reliability1sla1
15 stories, newest first · one card per story
Stories tagged #model-routing
GitHub launches Copilot Fusion to route and combine coding models
Fusion is generally available on all Copilot plans, bills each model at its normal rate, and offers a 30% discount through November 30, 2026.
1
AllModels routes abliterated DeepSeek across five inference providers
One OpenAI-compatible API falls back across providers and also exposes abliterated GLM 5.3 under a shared model ID.
1
You.com launches inference router for 12 open-weight models
The company states a 99.9% uptime SLA; the captured page does not name the 12 models.
Stripe agrees to acquire AI router OpenRouter
The New York Times puts the price at $7.5 billion, nearly six times a Series B valuation of about $1.3 billion.
1
Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options?
A new test finds typed decision models often mishandle fallback rules even without attacks.
Choosing LLMs for Strategic Agent Interactions
Selecting LLMs for strategic games is game- and opponent-specific; a stationary bandit beats more complex selectors but not the best fixed model.
LegalOn halves Codex costs while maintaining development speed
LegalOn cut estimated Codex daily costs about 65% by routing work across GPT-6 models.
Vani adds Memory, Skills, Connectors and Fast mode
Fast GPT replies use 2.5 times more allowance, and Muse Spark 1.3 was later withdrawn.
Collective Bias Mitigation via Model Routing and Collaboration
Collective Bias Mitigation routes multiple LLMs, and a committee cut age bias from 0.25 to 0.10.
Cut your AI spend with AI Gateway's Auto Router
Cloudflare’s AI Gateway Auto Router beta sends each request to a cheaper model that can still do the task.
9
So you want to use OpenRouter?
Simon Willison highlights OpenRouter pitfalls: provider routing makes the same model endpoint behave inconsistently across backends.
Sakana AI Launches Fugu Max and Fugu Ultra v2 for Cheaper, Stronger Multi-Agent Orchestration
Sakana AI released Fugu Max and Fugu Ultra v2, API-only orchestrator models that route tasks across model pools to cut costs and boost multi-step reasoning.
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
NeoHorse-1 introduces agentic post-training with intelligent routing that lifts agent benchmark scores at 4B and 9B scales, prototyping recursive self-improvement.
GitHub Introduces Project HydraFusion: Runtime Multi-Model Orchestration That Builds a Workflow Per Coding Task in Copilot CLI
GitHub's Project HydraFusion research preview builds per-task multi-model workflows (Single, Cascade, Critique) in Copilot CLI, reporting +4.9 quality at 67% lower cost on TerminalBench 2.1.
3