AI

Gemini Decisions API

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 11/11/2026, 22:12:24 UTC.

Briefings

Google launched Gemini Decision 1, a new API joining the decision model category alongside Jev and OpenAI. It supports text, images, audio, video, and PDFs, unlike Jev which is text-only. The model charges 10 cents per million input tokens and provides free output. It was tested on video inputs, returning confidence probabilities for yes/no questions rather than binary 1.0 or 0.0.

Key points

• Gemini Decision 1 supports five media types including video and PDFs, whereas Jev is text-only.
• The model charges 10 cents per million input tokens and provides free output.

Context

Google joined the decision model category with Gemini Decision 1, priced at 10 cents per million input tokens. It supports text, images, audio, video, and PDFs, unlike Jev which is text-only. The API was tested on video inputs, returning confidence probabilities for yes/no questions rather than binary 1.0 or 0.0.

Limitations

Evidence is limited to a single API launch and one video test case. No pricing data for output tokens, no historical performance metrics, and no user adoption statistics are provided.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 11/11/2026, 23:19:56 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeihdaov4pvoweyigfvqf6payslojdebcuuc3bvxizjqhh2wfq3s7ty