openai/gpt-4.1-mini-2025-04-14

openai/gpt-4.1-mini-2025-04-14
VisionToolsJSON
by openai

OpenAI GPT-4.1 Mini: cost-efficient reasoning with 1M context, image input, and strong MATH-500 score

ctx1.05M tokens
Max output32.8K
Inputimage + text + file
Outputtext
p50 TTFT2.00 s
INPUT$0.40/ 1M tokens
OUTPUT$1.60/ 1M tokens
p50 TTFT2.00 s7d
p95 TTFT3.57 s7d
TRAFFIC7.4Ktokens / 7d

This model is a scaled-down version of OpenAI’s GPT-4.1 family, specifically released on April 14, 2025. It is engineered to deliver strong reasoning and instruction-following performance at a…

What is openai/gpt-4.1-mini-2025-04-14?

Who should use this model?

What input modalities does it support?

What is the context window and maximum output length?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-4.1-mini-2025-04-14",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_completion_tokens
  • max_tokens
  • n
  • parallel_tool_calls
  • prediction
  • presence_penalty
  • response_format
  • seed
  • service_tier
  • stop
  • stream
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_logprobs
  • top_p
  • web_search_options

Pricing

Input / 1M tokens$0.400
Output / 1M tokens$1.60
Cache read / 1M$0.100
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $7.60 · With prompt caching $6.55

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000808

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
2.00 s
Output speed
25.9 tok/s
p95 TTFT
3.57 s
Error rate
0%

Public benchmarks

20.2
AA Coding
Better than 18% of models compared
#100 of 123
14.8
AA Intelligence
Better than 16% of models compared
#104 of 125
46.3
AA Math
Better than 22% of models compared
#62 of 81
AIME
43.0
AIME 2025
46.3
GPQA Diamond
66.4
Humanity's Last Exam
4.6
IFBench
38.3
LiveCodeBench
48.3
Long-Context Recall
42.3
MATH-500
92.5
MMLU-Pro
78.1
SciCode
40.4
tau_banking
5.2
TerminalBench Hard
7.6
terminalbench_v2_1
10.1
τ²-Bench
52.9
Source: artificialanalysis.ai

How it compares

openai/gpt-4.1-mini-2025-04-14GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$0.40$21.00$60.00$5.00
Output $/M$1.60$168.00$270.00$30.00
Context1.0M400K1.1M
Quality4/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost per token for openai/gpt-4.1-mini-2025-04-14 on OrcaRouter?
OrcaRouter bills at the provider rate with zero markup: $0.40 per 1 million input tokens and $1.60 per 1 million output tokens.
What is the context window size?
The context window is 1,047,576 tokens (approximately 1 million tokens). Maximum output is 32,768 tokens per request.
What are its main strengths?
It offers a strong combination of low cost, large context window, multimodal input (text, image, file), and solid reasoning performance as shown by the MATH-500 score of 92.5.
How does it compare to GPT-4o?
GPT-4o is a more capable flagship model with audio support, but GPT-4.1 mini is often cheaper and faster. No direct benchmark comparison is provided, but the mini is designed for efficient production use.
Does OrcaRouter handle data privacy for this model?
OrcaRouter routes requests to OpenAI’s infrastructure. Data handling follows OpenAI’s policies and OrcaRouter’s own terms. You should review both providers’ privacy and data usage agreements.
How do I call this model using the OpenAI Python client?
Set openai.api_base to 'https://api.orcarouter.ai/v1', set your OrcaRouter API key, and use openai.ChatCompletion.create(model='openai/gpt-4.1-mini-2025-04-14', messages=[...]).
Can I use this model for image understanding?
Yes, it supports image inputs (via URLs or base64) for tasks like captioning, visual question answering, and OCR. Files can also be uploaded as images or text.
What are the honest limitations of this model?
It may not match the full GPT-4.1 on very complex reasoning, and its knowledge is limited to the training cutoff (April 2025). It is not suitable for safety-critical applications without human oversight.
Is there any caching discount?
No specific caching discounts are mentioned for this model on OrcaRouter. Billing is per token at the rates stated.

Embed this badge

openai/gpt-4.1-mini-2025-04-14$0.40/M in2000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-4.1-mini-2025-04-14" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-4.1-mini-2025-04-14.svg" alt="openai/gpt-4.1-mini-2025-04-14 on OrcaRouter" /> </a>
Markdown [![openai/gpt-4.1-mini-2025-04-14](https://www.orcarouter.ai/embed/openai/gpt-4.1-mini-2025-04-14.svg)](https://www.orcarouter.ai/models/openai/gpt-4.1-mini-2025-04-14)

Model card as data

GET /api/public/models/openai/gpt-4.1-mini-2025-04-14Open
Machine-readable:/llms.txt/llms-full.txt