Apply your own routing policies, reduce token costs automatically, and see every routing decision in real time with Merge Gateway.
How o4 mini performs*
Intelligence - general reasoning and knowledge
26
What o4 mini costs to run
| Vendor | Input / 1M tokens | Output / 1M tokens | Zero data retention |
| --- | ---: | ---: | --- |
| OpenAI | $1.10 | $4.40 | Yes |
Test o4 mini
with Gateway’s Simulator
See a prompt's output, token spend, latency, and more with o4 mini.
Route requests to o4 mini in minutes
To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.
Install the Merge Gateway SDK
Python
1$ pip install merge-gateway-sdkSend a request
Python
1from merge_gateway import MergeGateway
2
3client = MergeGateway(api_key="YOUR_API_KEY")
4
5response = client.responses.create(
6 model="openai/gpt-5.2",
7 input=[
8 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
9 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
10 ],
11)
12
13print(response.output[0].content[0].text)Try a diffrent model
Swap the model string to route to a different provider. No other code changes needed.
Anthropic
1response = client.responses.create(
2 model="anthropic/claude-sonnet-4-20250514",
3 input=[
4 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)Point to Gateway
Python
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/openai",
6)Send a request
Use the standard chat.completions.create method. No provider prefix needed on the model name.
Python
1response = client.chat.completions.create(
2 model="gpt-5.2",
3 messages=[
4 {"role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)
8
9print(response.choices[0].message.content)Install packages
1npm install merge-gateway-ai-sdk-provider aiCreate the provider
TypeScript
1import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
2
3const gateway = createMergeGateway({
4 apiKey: "YOUR_API_KEY",
5});Send a request
Use generateText to send a request. Model names use the provider/model format.
TypeScript
1import { generateText } from "ai";
2
3const { text } = await generateText({
4 model: gateway("openai/gpt-4o"),
5 prompt: "Explain the concept of recursion in programming with a simple set of examples.",
6});
7
8console.log(text);If you already have @ai-sdk/openai installed, point it at Gateway with a base URL change:
TypeScript
1import { createOpenAI } from "@ai-sdk/openai";
2
3const gateway = createOpenAI({
4 apiKey: "YOUR_API_KEY",
5 baseURL: "https://api-gateway.merge.dev/v1/ai-sdk",
6});
7
8// All generateText/streamText calls work unchangedInstall the Merge Gateway SDK
Anthropic SDK
1from anthropic import Anthropic
2
3client = Anthropic(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/anthropic",
6)
7
8message = client.messages.create(
9 model="claude-sonnet-4-20250514",
10 max_tokens=1024,
11 messages=[
12 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
13 ],
14)
15
16print(message.content[0].text)Explore other models available in Merge Gateway
o4 mini FAQ
If you have additional questions about o4-mini, we've addressed several more below. Keep in mind that this information was written in July, 2026 and may change over time.
Heading
What other models does OpenAI offer?
OpenAI's lineup spans general-purpose GPT models and the o-series of reasoning models. Here are some other models OpenAI supports:
- GPT-5.5: the current general-purpose flagship, strong across reasoning, coding, and agentic tasks
- o3: a full-size reasoning model for the hardest multi-step problems, above o4 mini in capability and cost
- GPT Audio: a speech-focused model for audio input and output workflows
How does o4 mini differ from OpenAI's other models?
o4 mini is OpenAI's cost-efficient reasoning model, tuned for strong math, coding, and STEM performance at a fraction of the full reasoning tier's cost.
- Reasoning mode: uses extended thinking like o3, but is smaller and cheaper, trading some peak quality for speed and price
- Multimodal: accepts image input alongside text and supports tool use, unlike text-only reasoning models
- Pricing: priced well below the full-size o-series and flagship GPT models, making reasoning affordable at higher volume
- Use case fit: high-volume reasoning tasks in math, coding, and technical domains where full o3 is more than you need
Reach for o4 mini when you want genuine step-by-step reasoning at low cost and can accept a lower ceiling than the full reasoning models.
What models should I consider using alongside o4 mini?
No single model is optimal for every task. Here are models worth pairing with o4 mini depending on what your product needs:
- o3 as the escalation path for the hardest reasoning problems where o4 mini's ceiling isn't enough
- GPT-5.5 for broad general-purpose tasks that don't need extended reasoning
- Claude Opus 4.8 for demanding coding or agentic work where you want a frontier alternative
- Gemini 3.5 Flash for high-volume, low-complexity work where reasoning tokens would be wasted
- DeepSeek V4 Pro as an open-weight reasoning option to benchmark on cost
What are the challenges of using o4 mini in my product?
Like any production LLM, o4 mini comes with tradeoffs worth planning for:
- Reasoning token overhead: extended thinking increases output tokens and latency, so the low per-token price can still add up on heavy reasoning
- Quality ceiling: as a mini model, it trails full reasoning models like o3 on the hardest problems
- Provider dependency: routing all traffic to OpenAI is fragile if it has an outage or deprecates a model version
- Cost at scale: high request volumes compound token costs without active budgeting
- Prompt sensitivity: reasoning models can be sensitive to prompt structure, so test your prompts before rolling out broadly
Why should I use Merge Gateway to route LLM requests with o4 mini and every other model?
Using o4 mini through Merge Gateway gives you access to the model itself and the infrastructure layer around it:
- One API, every provider: Reach o4 mini and every other major LLM through a single endpoint and API key, swapping the model string to change providers without touching application code
- Intelligent routing and automatic failover: Merge routes around OpenAI outages automatically, and cost, latency, or quality policies can reduce spend by 40 to 60% without code changes
- Cost governance: Set hard or soft project budgets so o4 mini spend stays in plan, with every request attributed to a model, project, and tag in one billing dashboard
- Build Your Own Router: Define what "best" means with curated benchmarks or your own eval scores, and the router keeps easy tasks on o4 mini and escalates to a full reasoning model only when needed
- Security and compliance controls: Apply DLP rules and prompt injection protection before requests reach OpenAI, and enforce per-project model and region policies outside your application
How can I start routing requests to o4 mini via Merge Gateway?
Getting o4 mini running through Merge Gateway takes a few minutes:
1. Create an account and get your API key from the dashboard.
2. Install the Merge Gateway SDK: run pip install merge-gateway-sdk (Python) or npm install merge-gateway-sdk (Node). Alternatively, if you're already using the OpenAI SDK, set base_url = "https://api-gateway.merge.dev/v1/openai" and your existing code works as-is.
3. Make your first request using the provider/model format. For o4 mini, the model string is openai/o4-mini. Swap the model string to route to any other provider without changing anything else.
4. Configure a routing policy in the dashboard to set failover behavior, cost limits, and optimization strategy. Your first policy can be as simple as naming o4 mini as primary with one fallback.
Full setup instructions and SDK references are in the Merge Gateway docs.
Try o4 Mini through Merge Gateway
Route, observe, and control AI requests across providers from one API.
