o4-mini
o4-mini advances OpenAI's compact reasoning model line with stronger performance and greater efficiency than o3-mini, adding native tool use and image reasoning.
View API reference- Input and output price
- Prices from: Input $1.10, Output $4.40, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'openai/o4-mini', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out o4-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.
o4-mini
Copy link to headingProviders
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.
| Provider |
|---|
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call o4-mini through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/o4-mini', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same o4-mini request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/o4-mini', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. openai/o4-mini. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. o4-mini supports up to 100,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 200K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK openai provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/o4-mini', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['azure', 'openai'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/o4-mini', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/o4-mini', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/o4-mini', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/o4-mini', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingAbout o4-mini
o4-mini was released on April 16, 2025 alongside o3 as a cost-efficient reasoning model from OpenAI. It advances the compact reasoning model line (following o1-mini and o3-mini) with improvements across reasoning quality, efficiency, and multimodal capability.
A key advancement is native vision support: o4-mini can reason over images, diagrams, mathematical notation, and screenshots, combining visual understanding with chain-of-thought analysis. Earlier mini reasoning models were text-only. This opens up visual reasoning tasks at the affordable mini-tier pricing.
The model supports function calling and tool use, making it suitable as the reasoning layer in lightweight agent architectures. Combined with the reasoning_effort parameter, it lets you build cost-optimized pipelines that apply just enough reasoning to each request.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: o4-mini incorporates advances beyond o3-mini, including native vision support. It's a strong option for projects that need affordable chain-of-thought reasoning.
- Configuration: Unlike earlier mini reasoning models, o4-mini natively supports vision input, enabling reasoning over images, diagrams, and documents.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use o4-mini
Best for
- Affordable chain-of-thought reasoning: Per-request deliberation on technical tasks at scale
- Visual reasoning: Analyzing diagrams, charts, mathematical notation, and screenshots with step-by-step thinking
- Tool-using agents: Lightweight reasoning backbone for agents that call external tools and APIs
- Math and code reasoning: Competition-level problems and algorithmic analysis at accessible cost
- Mixed-difficulty pipelines: Using
reasoning_effortto optimize cost across varied query complexity
Consider alternatives when
- Maximum reasoning depth: O3 or o3-pro for the hardest problems requiring exhaustive deliberation
- General-purpose tasks: GPT-5 mini for workloads that don't benefit from chain-of-thought
- Coding agent workflows: Codex models for autonomous software engineering
- Non-reasoning speed: GPT-5.1 instant for the fastest possible general-purpose responses
Copy link to headingConclusion
o4-mini combines stronger reasoning performance than o3-mini with native vision and tool use at an affordable price point. For technical workloads on AI Gateway that need per-request reasoning with multimodal support, it advances the cost-efficient reasoning tier.
Copy link to headingFrequently Asked Questions
How does o4-mini improve over o3-mini?
It delivers stronger reasoning performance with greater efficiency, adds native vision support, and includes improved tool use capabilities.
Does o4-mini support image input?
Yes. Unlike earlier mini reasoning models, it natively processes images, diagrams, and visual content as part of its chain-of-thought reasoning.
What is the
reasoning_effortparameter?It controls how deeply the model reasons per request. Low effort for simple queries saves cost; high effort for hard problems enables thorough deliberation.
What context window does o4-mini support?
200K tokens, providing ample capacity for complex reasoning tasks.
How does AI Gateway handle authentication for o4-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.
When should I use o3 instead of o4-mini?
When the hardest problems require maximum reasoning depth and the quality gap between o4-mini and o3 is consequential for your application.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.