GPT-5 mini
GPT-5 mini delivers GPT-5 family intelligence at a reduced cost tier, making advanced reasoning, coding, and multimodal capabilities accessible for high-volume production workloads where full GPT-5 pricing is impractical.
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5-mini', prompt: 'Why is the sky blue?'})Playground
Try out GPT-5 mini 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.
About GPT-5 mini
GPT-5 mini launched on August 7, 2025 alongside GPT-5, GPT-5 nano, and GPT-5 pro as part of the GPT-5 model family. It occupies the cost-performance tier that typically handles the majority of production API traffic: capable enough for most tasks, affordable enough to scale.
The model inherits the GPT-5 family's architectural improvements in reasoning, coding, and instruction following while operating at reduced compute requirements. It supports a context window of 400K tokens, multimodal input, function calling, and structured outputs, providing the full feature set developers need for production applications.
If you're migrating from GPT-4o mini or GPT-4.1 mini, GPT-5 mini is the next generation of the mid-tier model. It improves quality across the board while maintaining the economics that make high-volume deployment practical.
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 | 3.4s | 100tps | $5.00/M | $30.00/M | Read: $0.5/M Write: — | $10.00/K + input costs | — |   | 04/24/2026 | ||||
| 400K | 2.9s | 236tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 400K | 0.7s | 80tps | $0.20/M | $1.25/M | Read:$0.02/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 1.1M | 0.7s | 55tps | $2.50/M | $15.00/M | Read: $0.25/M Write: — | $10.00/K + input costs | — | | 03/05/2026 | ||||
| 128K | 1.1s | 80tps | $1.25/M | $10.00/M | Read:$0.13/M Write:— | $10.00/K + input costs | — | | 11/12/2025 | ||||
| 131K | 0.2s | 2042tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — | — |    +5 | 08/05/2025 |
What To Consider When Choosing a Provider
- Configuration: GPT-5 mini is a strong choice for most production traffic in the GPT-5 family. It provides enough capability for the vast majority of tasks while keeping per-request costs manageable at scale.
- Configuration: It sits between GPT-5 nano (fastest, cheapest) and full GPT-5 (most capable), covering the middle ground where most real-world applications operate.
- 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 mini
Best For
- Production chat interfaces: Fast, capable responses for customer-facing conversational products
- Code assistance: Strong coding support for development tools at sustainable per-request costs
- Document processing: Analyzing and summarizing documents with GPT-5 family instruction following
- Agentic workflows: Cost-effective backbone for multi-step agent pipelines with many sequential calls
- Content generation: Marketing copy, technical writing, and editorial assistance at volume
Consider Alternatives When
- Maximum capability needed: Full GPT-5 for the highest quality on complex tasks
- Minimal cost required: GPT-5 nano for classification, routing, and simple extraction
- Deep reasoning: O3 for problems requiring extended chain-of-thought deliberation
- Legacy compatibility: GPT-4o mini if you need to maintain existing integrations without migration
Conclusion
GPT-5 mini is the default production model in the GPT-5 family, balancing capability and cost for the workloads that make up the bulk of real-world API traffic. Available through AI Gateway, it is the natural upgrade path from GPT-4o mini and GPT-4.1 mini.
Frequently Asked Questions
How does GPT-5 mini compare to GPT-4o mini?
GPT-5 mini is the next generation of OpenAI's mid-tier model, delivering improved reasoning, coding, and instruction following compared to GPT-4o mini.
What context window does GPT-5 mini support?
400K tokens, enabling extensive document processing and conversation history retention.
When should I use full GPT-5 instead of mini?
When the task demands maximum capability, particularly on complex reasoning, nuanced writing, or challenging coding problems where the quality gap is measurable and consequential.
Does GPT-5 mini support function calling and structured outputs?
Yes. It supports the full API feature set including function calling, structured outputs via JSON schema, vision input, and system messages.
How does AI Gateway handle authentication for GPT-5 mini?
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 is the pricing for GPT-5 mini?
Pricing appears on this page and updates as providers adjust their rates. AI Gateway routes traffic through the configured provider.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.