GPT-5 pro
GPT-5 pro is the highest-capability tier in the GPT-5 family, offering extended compute for the most demanding tasks, deeper reasoning, more thorough analysis, and higher-quality output for problems where standard GPT-5 reaches its limits.
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5-pro', prompt: 'Why is the sky blue?'})Playground
Try out GPT-5 pro 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 | 1.1s | 84tps | $5.00/M | $30.00/M | Read: $0.5/M Write: — | $10.00/K + input costs | — |   | 04/24/2026 | ||||
| 400K | 1.2s | 187tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 400K | 0.4s | 20tps | $0.20/M | $1.25/M | Read:$0.02/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 1.1M | 0.5s | 71tps | $2.50/M | $15.00/M | Read: $0.25/M Write: — | $10.00/K + input costs | — | | 03/05/2026 | ||||
| 128K | 0.6s | 123tps | $1.25/M | $10.00/M | Read:$0.13/M Write:— | $10.00/K + input costs | — | | 11/12/2025 | ||||
| 400K | 3.2s | 146tps | $0.25/M | $2.00/M | Read:$0.03/M Write:— | $14/K + input costs | — | | 08/07/2025 |
About GPT-5 pro
GPT-5 pro became available on N/A as the premium tier of the GPT-5 model family on AI Gateway. It applies more compute per request than the standard GPT-5, enabling deeper reasoning, more thorough analysis, and higher-quality output on the most demanding tasks.
The pro tier exists for the subset of problems where standard GPT-5 capability is not enough. Complex research synthesis, thorough code audits, nuanced legal analysis, and multi-factor strategic planning all benefit from the additional reasoning depth GPT-5 pro provides, in exchange for higher cost and potentially longer response times.
GPT-5 pro is typically deployed selectively. Routine traffic flows through GPT-5 or GPT-5 mini, while specific high-value queries are routed to the pro tier. This pattern maintains quality where it matters while keeping overall costs manageable.
What To Consider When Choosing a Provider
- Configuration: GPT-5 pro is for tasks where quality is the only metric that matters. It applies more compute per request than standard GPT-5, producing better results on genuinely hard problems at higher per-request cost.
- Configuration: Most applications should use GPT-5 pro selectively for their hardest queries rather than as a default, pairing it with GPT-5 or GPT-5 mini for routine traffic.
- 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 pro
Best For
- Hard research problems: Complex analysis that benefits from extended deliberation and thoroughness
- Critical code review: Architectural review and security audits where missing an issue has high consequences
- High-stakes content: Legal, medical, or financial content where accuracy is paramount
- Complex multi-step planning: Strategic decisions and system design that require considering many factors
- Quality-gated workflows: Tasks where output is reviewed by humans and quality directly impacts outcomes
Consider Alternatives When
- Standard workloads: GPT-5 handles the vast majority of tasks without the pro tier's premium
- Cost-sensitive applications: GPT-5 mini for production traffic at scale
- Specialized reasoning: O3-pro for pure mathematical and scientific chain-of-thought problems
- Speed-critical responses: Any smaller model when latency matters more than quality ceiling
Conclusion
GPT-5 pro provides the highest capability within the GPT-5 family, applying premium compute to deliver stronger results on genuinely hard problems. For quality-critical applications on AI Gateway, it is the premium tier of the GPT-5 lineup.
Frequently Asked Questions
How does GPT-5 pro differ from standard GPT-5?
It applies more compute per request, enabling deeper reasoning and more thorough analysis. Improvements are most apparent on genuinely hard problems; on simple tasks the difference may be minimal.
When should I use GPT-5 pro versus GPT-5?
Use it selectively for your hardest queries, complex analysis, critical code review, high-stakes content, and tasks where quality directly impacts outcomes. Use standard GPT-5 for routine traffic.
What context window does GPT-5 pro support?
400K tokens, matching the GPT-5 family.
Is GPT-5 pro slower than GPT-5?
It may take longer per request due to the additional compute applied. For latency-sensitive applications, consider routing only specific queries to the pro tier.
How does AI Gateway handle authentication for GPT-5 pro?
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.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.