GPT 5.5 Pro
GPT 5.5 Pro is the higher-capability tier of the GPT-5.5 family, applying more compute per request for deeper analysis on the hardest tasks while keeping the same modalities and APIs as standard GPT-5.5.
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5.5-pro', prompt: 'Why is the sky blue?'})Playground
Try out GPT 5.5 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 | 2.8s | 66tps | $5.00/M | $30.00/M | Read: $0.5/M Write: — | $10.00/K + input costs | — |   | 04/24/2026 | ||||
| 400K | 1.6s | 190tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 400K | 0.4s | 17tps | $0.20/M | $1.25/M | Read:$0.02/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 1.1M | 0.9s | 55tps | $2.50/M | $15.00/M | Read: $0.25/M Write: — | $10.00/K + input costs | — | | 03/05/2026 | ||||
| 128K | 1.0s | 96tps | $1.25/M | $10.00/M | Read:$0.13/M Write:— | $10.00/K + input costs | — | | 11/12/2025 | ||||
| 131K | 0.1s | 880tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — | — |    +5 | 08/05/2025 |
About GPT 5.5 Pro
GPT 5.5 Pro became available on April 24, 2026 on AI Gateway as the higher-capability tier of the GPT-5.5 model family. It applies more compute per request than the standard GPT-5.5, producing deeper analysis and stronger output on the hardest coding, research, and knowledge-work tasks.
The pro tier supports the same modalities and APIs as standard GPT-5.5, including reasoning, tool use, web search, implicit caching, file inputs, and vision. The trade-off is higher list pricing in exchange for additional reasoning depth on tasks where the standard tier's capability ceiling is the binding constraint.
With a context window of 1M tokens and up to 128K tokens output tokens, GPT 5.5 Pro handles long inputs and produces substantial outputs in a single pass. Call it through the AI SDK, the Chat Completions API, or the Responses API. Pricing on this page reflects current rates from each provider routed through AI Gateway; compare $30 input and $180 output token pricing against standard GPT-5.5 when deciding which tier to route each request to.
What To Consider When Choosing a Provider
- Configuration: GPT 5.5 Pro is the pro tier of the GPT-5.5 family. It applies more compute per request than standard GPT-5.5, producing deeper analysis on hard problems at a higher list price. Modalities, tool support, and APIs match the standard tier.
- Configuration: Most teams route only their hardest queries to GPT 5.5 Pro and use standard GPT-5.5 for routine traffic. A small routing layer keyed on query complexity is the practical pattern.
- 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 5.5 Pro
Best For
- High-stakes analysis: Research, strategy, and complex reasoning where output quality directly drives outcomes
- Critical code review: Architectural review and security audits where missing an issue has real consequences
- Complex agentic workflows: Multi-step tasks that combine tools, browsing, and file inputs and need maximum reliability
- Expert content creation: Long-form technical, legal, or financial writing where accuracy is paramount
- Final-pass quality gates: Routing your hardest queries to GPT 5.5 Pro while standard GPT-5.5 handles routine traffic
Consider Alternatives When
- Standard workloads: GPT-5.5 handles the majority of production traffic without the pro tier premium
- Cost-sensitive applications: Earlier GPT-5.x mini or nano tiers for high-volume routine work
- Specialized coding agents: GPT-5.x codex variants for autonomous software engineering in sandboxed environments
- Pure chain-of-thought: The o-series reasoning models when mathematical or scientific reasoning dominates
Conclusion
GPT 5.5 Pro provides the higher-capability tier of the GPT-5.5 family, applying more compute to the hardest tasks while preserving the same modalities and APIs as the standard model. For quality-critical traffic routed through AI Gateway, it is the premium tier of the GPT-5.5 lineup.
Frequently Asked Questions
How does GPT 5.5 Pro differ from standard GPT-5.5?
It applies more compute per request, producing deeper analysis on hard problems. Modalities, tool support, and APIs are the same; the difference is reasoning depth and list price.
When should I use GPT 5.5 Pro versus standard GPT-5.5?
Route your hardest queries to GPT 5.5 Pro (critical code review, complex research, high-stakes analysis) and use standard GPT-5.5 for routine traffic. A routing layer keyed on query complexity is the practical pattern.
What context window does GPT 5.5 Pro support?
1M tokens, with up to 128K tokens output tokens per request, matching the rest of the GPT-5.5 family.
Which APIs can I use to call GPT 5.5 Pro?
Call GPT 5.5 Pro through the AI SDK, the Chat Completions API, or the Responses API. AI Gateway accepts requests in each format and routes them to the model.
What does GPT 5.5 Pro cost?
List pricing is $30 per million input tokens and $180 per million output tokens, with cached input at N/A. Compare these rates against standard GPT-5.5 when deciding which tier each request belongs in. Pricing on this page updates when providers change list prices.
Does GPT 5.5 Pro support zero data retention through AI Gateway?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
How does AI Gateway handle authentication for GPT 5.5 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. Additional compute per request typically increases time-to-first-token compared to standard GPT-5.5.