FreeLLMGoogle launches Gemini Decisions API with fast multimodal decision model
Gemini Decision 1 processes up to 1,000 closed‑set questions in a single pass, costing $0.10 per million input tokens.
Google DeepMind announced the Gemini Decisions API, powered by the new Gemini Decision 1 model.
The model can evaluate up to 1,000 yes/no, multiple‑choice, or rubric‑scoring questions in a single forward pass across text, images, audio, video and PDFs.
Latency is reported at 150‑250 ms end‑to‑end, and pricing is $0.10 per million input tokens with no charge for output tokens.
Gemini Decision 1 leads benchmark suites in agent routing, reasoning and multimodal understanding, achieving the lowest calibration error.
Google says internal teams already use the API for dynamic model routing in Gemini Notebook, rapid design prototyping in Stitch, and safety checks in Search.
Ce que cela signifie pour vous
The API offers developers a cheap, low‑latency way to make probabilistic decisions without token‑by‑token generation, useful for routing, grading or policy checks. While Google’s paid Gemini 4 Carbon tops FreeLLMArena’s paid model list, free‑tier users may still prefer open models such as Kimi K3 or GLM‑5.3, which remain the top‑ranked free chat options.
Sur FreeLLMArena
From our rankings on 11 Nov 2026, based on Arena's blind votes:
- Kimi K3 (Max): #1 among free chat models
Sources
- Google joins the decision-model wave with Gemini Decision 1, scoring 1,000 questions in a single pass, The Decoder, 11 Nov 2026
- Gemini Decisions API: Fast multimodal decisions, blog.google (official), 11 Nov 2026
Rédigé automatiquement à partir des sources ci‑dessus, puis vérifié par notre code : chaque nombre et chaque nom doivent y figurer, et aucune phrase ne doit copier une source. Une erreur ? Signalez‑la.
Quelle IA pouvez‑vous utiliser gratuitement aujourd’hui ?
Tous les modèles IA gratuits, classés par votes humains anonymes, avec la mémoire et la vitesse dont ils ont besoin sur votre propre GPU.