LLM model

GPT-5

Azure's top reasoning tier for complex, multi-step work.

Reference Cloud Wizard Azure
Open the selection wizard All models
Illustrative specs. Context window, modalities, output cost, and EU availability for GPT-5 are representative, last verified 1 Jun 2026. Verify against the provider before committing.

GPT-5 at a glance

Reach for it when smaller models measurably fail; output cost makes it expensive at scale.

Hosting Foundry Foundry (Azure)
Context window 400,000 tokens
Modalities text, vision inputs
Output cost $10 / 1M tokens

Best for

  • Agentic workflows
  • Complex reasoning and planning
  • Hard coding tasks

Is it the right model?

Match it against your requirements.

The selection wizard ranks GPT-5 against every other model for your latency, context, modality, cost, and residency needs — and shows where it wins and where something else fits better.

Open the LLM Selection Wizard

Frequently asked questions

GPT-5 specs and cost.

What is GPT-5 best for? Azure's top reasoning tier for complex, multi-step work. It fits Agentic workflows, Complex reasoning and planning, Hard coding tasks.
What context window and modalities does GPT-5 support? GPT-5 handles up to 400,000 tokens of context and supports text, vision input. It runs on Foundry (Azure).
How much does GPT-5 cost? Around $10 per 1M output tokens (illustrative, verified 1 Jun 2026). Output tokens usually dominate the bill — verify input and cached pricing against the provider before budgeting.