GPT-4o-mini

openai/gpt-4o-mini
VisionToolsJSON
by OpenAI · 2024-07-18

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

ctx128K tokens
Max output16.4K
Inputtext + image + file
Outputtext
p50 TTFT4.23 s
INPUT$0.15/ 1M tokens
OUTPUT$0.60/ 1M tokens
p50 TTFT4.23 s7d
p95 TTFT10.00 s7d
TRAFFIC9.6Mtokens / 7d

GPT-4o-mini is a smaller, faster variant of OpenAI's GPT-4o model, optimized for lower computational cost while retaining multimodal capabilities. It can process text, images, and uploaded files as…

What is GPT-4o-mini?

Who should use GPT-4o-mini?

How does the model architecture differ from GPT-4o?

What input modalities are supported?

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-4o-mini",
    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$0.150
Output / 1M tokens$0.600
Cache read / 1M$0.075
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $2.85 · With prompt caching $2.59

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000303

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

Performance

p50 TTFT
4.23 s
Output speed
870 tok/s
p95 TTFT
10.00 s
Error rate
0.30%

Public benchmarks

11.4
AA Coding
Better than 7% of models compared
#114 of 123
6.9
AA Intelligence
Better than 3% of models compared
#119 of 125
14.7
AA Math
Better than 2% of models compared
#78 of 81
AIME
11.7
AIME 2025
14.7
GPQA Diamond
42.6
Humanity's Last Exam
4.0
IFBench
31.0
LiveCodeBench
23.4
MATH-500
78.9
MMLU-Pro
64.8
SciCode
22.9
tau_banking
2.9
terminalbench_v2_1
5.6
Source: artificialanalysis.ai

How it compares

GPT-4o-miniGPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$0.15$21.00$60.00$5.00
Output $/M$0.60$168.00$270.00$30.00
Context128K400K1.1M
Quality2/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use GPT-4o-mini through OrcaRouter?
Input tokens cost $0.15 per 1M, output tokens cost $0.60 per 1M, exactly matching OpenAI’s rates with zero markup.
What is the context window of GPT-4o-mini?
The context window is 128,000 tokens, and the maximum output is 16,384 tokens.
What are the main strengths of GPT-4o-mini?
It combines multimodal input (text, images, files), a large context window, fast inference, and low cost for a wide range of tasks.
How does GPT-4o-mini compare to GPT-4o?
GPT-4o-mini is roughly 94% cheaper on token pricing but may be less accurate on complex reasoning and creative generation. On MATH-500, it scores 78.9 versus GPT-4o’s higher score.
Does OrcaRouter log or store my prompts?
OrcaRouter does not log or store your prompts; all data passes through to OpenAI. Refer to OpenAI’s data usage policy for their handling.
How do I call GPT-4o-mini via OrcaRouter's API?
Use the OpenAI-compatible endpoint at https://api.orcarouter.ai/v1 with model id "openai/gpt-4o-mini". Include your OrcaRouter API key.
Can GPT-4o-mini process both text and images in the same request?
Yes, it accepts text, images, and files simultaneously within the 128K token context.
What is the speed/latency of GPT-4o-mini?
Latency is generally low—first token typically under one second for moderate prompts—but varies with context length and API load. Streaming reduces perceived latency.

Embed this badge

OpenAI: GPT-4o-mini$0.15/M in4232ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-4o-mini" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-4o-mini.svg" alt="OpenAI: GPT-4o-mini on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-4o-mini](https://www.orcarouter.ai/embed/openai/gpt-4o-mini.svg)](https://www.orcarouter.ai/models/openai/gpt-4o-mini)

Model card as data

GET /api/public/models/openai/gpt-4o-miniOpen
Machine-readable:/llms.txt/llms-full.txt