GPT 5.5
GPT 5.5 is the standard tier of the GPT-5.5 model family, advancing the GPT-5 series with stronger intent understanding, deeper autonomous work, and improvements across coding, research, data analysis, and document creation.
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5.5', prompt: 'Why is the sky blue?'})Playground
Try out GPT 5.5 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 |
|---|
| 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 | ||||
| 400K | 3.6s | 153tps | $0.25/M | $2.00/M | Read:$0.03/M Write:— | $14/K + input costs | — | | 08/07/2025 | ||||
| 131K | 0.1s | 880tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — | — |    +5 | 08/05/2025 |
About GPT 5.5
GPT 5.5 became available on April 24, 2026 on AI Gateway as the standard tier of the GPT-5.5 model family. OpenAI positions it as a model that understands what you're trying to do faster and can carry more of the work itself, extending the agentic gains of the GPT-5.x line.
The model excels at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, scheduling, learning, and answering everyday personal questions. It supports tool use, web search, implicit caching, file inputs, and vision, giving developers a single model that fits across coding, research, and knowledge-work pipelines.
With a context window of 1M tokens and up to 272K tokens output tokens, GPT 5.5 handles long inputs and produces substantial outputs in a single pass. Pricing is $5 per million input tokens and $30 per million output tokens, with cached input billed at $0.5. Integrate GPT 5.5 through the AI SDK, Chat Completions API, or Responses API depending on your stack.
What To Consider When Choosing a Provider
- Configuration: GPT 5.5 understands what you're trying to do faster and can carry more of the work itself than earlier GPT-5.x generations. It is a general-purpose model that handles code, research, data analysis, document creation, and conversational assistance from a single architecture.
- Configuration: It launches alongside the higher-capability pro variant. Use the standard tier for everyday production traffic and route the hardest queries to GPT-5.5 Pro when the quality difference justifies the cost.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- 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
Best For
- Code writing and debugging: Development assistance, refactoring, and bug diagnosis across substantial codebases
- Online research: Multi-source research synthesis with web search and tool use
- Data analysis: Spreadsheet generation, structured analysis, and quantitative reasoning over tabular inputs
- Document creation: Reports, plans, and long-form writing where the model carries more of the drafting work
- Agentic workflows: Complex tasks that combine tools, file inputs, vision, and multi-step planning
Consider Alternatives When
- Hardest queries: GPT-5.5 Pro applies higher capability for the most demanding analysis
- Cost optimization: Earlier GPT-5.x mini or nano tiers for high-volume routine traffic
- 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 extends the GPT-5 series with stronger intent understanding and a wider range of autonomous work, available through AI Gateway. It is the standard tier of the GPT-5.5 family for general-purpose coding, research, and knowledge work.
Frequently Asked Questions
How does GPT 5.5 improve over earlier GPT-5.x models?
It understands what you're trying to do faster and carries more of the work itself, with measurable gains in code writing and debugging, online research, data analysis, and document creation.
What context window does GPT 5.5 support?
1M tokens, with up to 272K tokens output tokens per request. That is enough for full codebases, long research dossiers, and extended conversation histories in a single call.
Which APIs can I use to call GPT 5.5?
Call GPT 5.5 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.
Does GPT 5.5 support tool use and web search?
Yes. Tags include reasoning, tool use, web search, implicit caching, file input, and vision. You can wire up function calling, browsing tools, and file or image inputs through the AI SDK or the Responses API.
What does GPT 5.5 cost?
Standard list pricing is $5 per million input tokens and $30 per million output tokens, with cached input at $0.5. Pricing on this page is sourced from each provider routed through AI Gateway and updates when those providers change list prices.
Does GPT 5.5 support zero data retention through AI Gateway?
Yes, Zero Data Retention is 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?
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.