Decision 1.1 on Vercel AI Gateway

Microsoft-Decision · Microsoft Research

Serverless

Last refreshed 2026-11-18. Next refresh: weekly.

Why use Decision 1.1 on Vercel AI Gateway?

Vercel AI Gateway offers Decision 1.1 with pay-as-you-go pricing at $0.04/1M 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 Decision 1.1 across 3 providers to find the best fit for your use case
Input / 1M
$0.042
Output / 1M
Free
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export AI_GATEWAY_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
Model ID
microsoft/decision-1.1

Request 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="microsoft/decision-1.1",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Use provider model ID "microsoft/decision-1.1", not the LLMReference slug "microsoft-decision-1.1".
  • 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 Decision 1.1 Across Providers

ProviderInput (per 1M)Output (per 1M)
OpenRouter$0.04Free
Vercel AI Gateway$0.04Free
Microsoft Foundry$0.04Free

Pricing

TypePrice (per 1M)
Input tokens$0.04
Output tokensFree

Capabilities

VisionMultimodalStructured Outputs

About Decision 1.1

Decision 1.1 is Microsoft’s decision-scoring model, generally available in Foundry. It evaluates text, JSON and up to eight images against typed questions, returning numerical decisions rather than generated explanations. It supports classification, routing, ranking, grading and yes/no judgments. Microsoft post-trained Gemma 4 26B-A4B for the model. Inputs can contain up to 32K tokens.

Get Started