decision-1Microsoft Azure AI
- api
- chat
- hosting
- US
- model lab
- Microsoft
- weights
- closed
- added
- October 2026
- model id
- azure/decision-1
capabilities 0/8
- input
- $0.04
- output
- free
- cache write
- -
- cache read
- -
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0042 |
| 1M in + 100K out | $0.0420 |
| 10M in + 1M out | $0.42 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
no published scores for this exact variant. region deployments and highspeed tiers usually share the base model's results
- retention
- none
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. Microsoft Privacy Statement
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
azure/decision-1this id pins the microsoft azure ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="azure/decision-1", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
Microsoft-Decision-1 is a small decision model post trained from Qwen3.5-9B. Instead of generating text it reads the provided state and returns a calibrated probability for each fixed answer option, for classification, routing, prioritization, verification, agent guardrails and AI judging.
questions 5
How much does decision-1 cost?
What is the context window of decision-1?
What can decision-1 do?
How do I use decision-1 with the OpenAI SDK?
Can I run decision-1 through Requesty?
more from microsoft azure ai 8
| endpoint | ctx | in /M |
|---|---|---|
| gpt-6.1-terra | 1.1M | $1.00 |
| gpt-6.1-terra | 1.1M | $1.20 |
| gpt-6.1-terra | 1.1M | $1.20 |
| gpt-6.1-terra | 1.1M | $1.20 |
| gpt-6.1-terra | 1.1M | $1.20 |
| decision-1 | 33K | $0.04 |
| decision-1 | 33K | $0.04 |
| gpt-6.1-sol | 1.1M | $2.00 |
call decision-1 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology