GPT-4o-mini (2024-07-18)

openai/gpt-4o-mini-2024-07-18
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 TTFT2.26 s
INPUT$0.15/ 1M tokens
OUTPUT$0.60/ 1M tokens
p50 TTFT2.26 s7d
p95 TTFT2.26 s7d
TRAFFIC44.5Ktokens / 7d

GPT-4o-mini (2024-07-18) is a lightweight multimodal model developed by OpenAI, designed for cost-efficient text and image processing. It is intended for developers and organizations that need strong…

What is GPT-4o-mini and who is it for?

What input modalities does GPT-4o-mini support?

How does the API integration work with OrcaRouter?

What are the key cost and context specifications?

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-2024-07-18",
    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
2.26 s
Output speed
87.6 tok/s
p95 TTFT
2.26 s
Error rate
0%

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-mini (2024-07-18)GPT-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 GPT-4o-mini's cost per token on OrcaRouter?
GPT-4o-mini costs $0.15 per 1 million input tokens and $0.60 per 1 million output tokens. OrcaRouter bills at the exact OpenAI provider rate with zero markup.
How large is the context window for GPT-4o-mini?
The context window is 128,000 tokens, allowing for very long inputs such as full documents or extended conversations.
What are the main strengths of GPT-4o-mini?
It offers a balance of low cost, multimodal input (text, images, files), a large context window, and solid mathematical reasoning (78.9 on MATH-500). It is faster and cheaper than full-size GPT-4 models.
How does GPT-4o-mini compare to GPT-4o?
GPT-4o-mini is cheaper ($0.15/$0.60 per million tokens vs $2.50/$10.00) but has lower benchmark scores (e.g., MATH-500 78.9 vs ~90). Both support multimodal inputs and 128k context.
Does OrcaRouter handle data privacy differently than direct OpenAI access?
OrcaRouter passes requests directly to OpenAI's API without storing or logging your data beyond standard usage monitoring. For detailed data handling, refer to OrcaRouter's privacy policy and OpenAI's data usage terms.
How do I call GPT-4o-mini via an OpenAI-compatible API?
Set the base URL to https://api.orcarouter.ai/v1 and use model ID "openai/gpt-4o-mini-2024-07-18". The API is fully compatible with the OpenAI chat completions format, including streaming.
Can I pass images and files alongside text in a single API request?
Yes. Use the multi-part content format: include a content array with type "text" and type "image_url" (for images) or type "file" (for files). Each part is converted to tokens.
Is there a minimum spend or monthly commitment required on OrcaRouter?
No. OrcaRouter charges per token with no minimums. You only pay for what you use at the provider rates with zero markup.

Embed this badge

OpenAI: GPT-4o-mini (2024-07-18)$0.15/M in2257ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-4o-mini-2024-07-18" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-4o-mini-2024-07-18.svg" alt="OpenAI: GPT-4o-mini (2024-07-18) on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-4o-mini (2024-07-18)](https://www.orcarouter.ai/embed/openai/gpt-4o-mini-2024-07-18.svg)](https://www.orcarouter.ai/models/openai/gpt-4o-mini-2024-07-18)

Model card as data

GET /api/public/models/openai/gpt-4o-mini-2024-07-18Open
Machine-readable:/llms.txt/llms-full.txt