GPT 5.2
GPT 5.2 is the premium tier of the GPT-5.2 family, applying maximum compute for the most demanding tasks where the deepest reasoning and highest quality output are required.
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5.2-pro', prompt: 'Why is the sky blue?'})Playground
Try out GPT 5.2 by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by OpenAI
| Model |
|---|
| 1M | 2.8s | 61tps | $5.00/M | $30.00/M | Read: $0.5/M Write: — | $10.00/K + input costs | — | +4 |    | 04/24/2026 | |||
| 400K | 1.5s | 282tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10.00/K + input costs | — | +4 | | 03/17/2026 | |||
| 400K | 0.6s | 108tps | $0.20/M | $1.25/M | Read:$0.02/M Write:— | $10.00/K + input costs | — | +4 | | 03/17/2026 | |||
| 1.1M | 1.5s | 66tps | $2.50/M | $15.00/M | Read: $0.25/M Write: — | $10.00/K + input costs | — | +4 | | 03/05/2026 | |||
| 131K | 0.1s | 1852tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — | — |   +5 | 08/05/2025 | ||||
| 1M | 0.5s | 56tps | $0.10/M | $0.40/M | Read:$0.03/M Write:— | $14/K + input costs | — | +2 | | 04/14/2025 |
About GPT 5.2
GPT 5.2 was released on December 11, 2025 on AI Gateway as the premium tier of the GPT-5.2 model family. It applies the maximum compute within the GPT-5.2 family to produce deeper reasoning, more thorough analysis, and higher-quality output than the standard GPT-5.2 tier.
The pro tier is designed for the subset of tasks where the standard model's capability ceiling is a binding constraint. Complex research synthesis, high-stakes analysis, expert-level content creation, and multi-factor strategic decisions all benefit from the additional reasoning depth.
With a context window of 400K tokens and the full API feature set, GPT 5.2 handles any task the GPT-5.2 family supports, it simply applies more computation to each request, producing better results on problems that merit the investment.
What To Consider When Choosing a Provider
- Configuration: GPT 5.2 applies the most compute per request of any GPT-5.2 variant. Use it for tasks where the quality difference over standard GPT-5.2 is measurable and consequential.
- Configuration: Most teams pair GPT 5.2 with standard GPT-5.2 or mini models, routing only the hardest queries to the pro tier.
- Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use GPT 5.2
Best For
- Expert-level content creation: Technical documentation, legal drafting, and precision-critical writing
- Maximum-compute GPT-5.2 tier: Applies the most compute per request of any GPT-5.2 variant
- Selective routing pattern: Pairs with standard GPT-5.2 or mini models to handle only the hardest queries
Consider Alternatives When
- Standard workloads: GPT-5.2 for most tasks without the pro tier's premium
- Cost-sensitive applications: GPT-5 mini or GPT-5.1 instant for high-volume production
- Specialized reasoning: O3-pro for pure mathematical and scientific chain-of-thought
- Speed-critical responses: GPT-5.2 mini or GPT-5.1 instant for lower-latency workloads
Conclusion
GPT 5.2 is the premium tier of the GPT-5.2 family, available through AI Gateway. For the hardest problems where quality within the GPT-5.2 generation is the priority, it applies the most compute per request.
Frequently Asked Questions
How does GPT 5.2 differ from standard GPT-5.2?
It applies more compute per request, producing deeper reasoning and higher-quality output on hard problems. On simple tasks the difference may be minimal.
When is the pro tier justified?
For high-stakes analysis, mission-critical decisions, expert-level content, and tasks where the quality difference over standard GPT-5.2 directly impacts outcomes.
What context window does GPT 5.2 support?
400K tokens, matching the GPT-5.2 family.
How does AI Gateway handle authentication for GPT 5.2 ?
AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.
Is GPT 5.2 slower than standard GPT-5.2?
It may take longer per request due to the additional compute. For latency-sensitive applications, route only specific high-value queries to the pro tier.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.