Last refreshed 2026-11-12. Next refresh: weekly.
Why use Gemini Decision 1 on Vercel AI Gateway?
Vercel AI Gateway offers Gemini Decision 1 with pay-as-you-go pricing at $0.10/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Gemini Decision 1 across 3 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport AI_GATEWAY_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],google/gemini-decision-1Request example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="google/gemini-decision-1",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "google/gemini-decision-1", not the LLMReference slug "gemini-decision-1".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Gemini Decision 1 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Google AI Studio | $0.10 | Free |
| OpenRouter | $0.10 | Free |
| Vercel AI Gateway | $0.10 | Free |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.10 |
| Output tokens | Free |
Capabilities
About Gemini Decision 1
Gemini Decision 1 is Google's first decision model, released November 11, 2026 with the Decisions API in the Gemini API and Google AI Studio. It does not generate text: given one input of text, images, audio, video or PDF and up to 1,000 typed questions per request, it returns calibrated probabilities for yes/no, choice and score (rubric) answers, with zero output tokens. Google aims it at bounded choices such as tool selection, policy checks, model routing and context grading. The input limit is 262,144 tokens.