o4 Mini API Pricing

As of October 10, 2026, o4 Mini costs $1.10 per 1M input tokens and $4.40 per 1M output tokens on OpenAI, with cache reads at $0.275 per 1M tokens. Across 4 providers on LiteLLM, the input price ranges from $1.00 to $1.10. It has a 200,000-token context window and returns up to 100,000 tokens per response.

By OpenAIModel ID o4-miniPrices updated October 10, 2026Checked October 10, 2026

Scheduled for deprecation: OpenAI lists October 23, 2026 as the deprecation date for o4-mini.

Input: $1.10 / 1M tokens
Output: $4.40 / 1M tokens
Cache read: $0.275 / 1M tokens
Context window: 200,000 tokens
Max output: 100,000 tokens
Providers: 4
Added to LiteLLM: April 2025

o4 Mini pricing by provider

9 listings across 4 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Provider	Model name in LiteLLM	Input	Output	Cache read	Cache write	Batch in	Batch out	Context
OpenAI	`o4-mini`	$1.10	$4.40	$0.275	–	$0.55	$2.20	200K
OpenAIsnapshot 2025-04-16	`o4-mini-2025-04-16`	$1.10	$4.40	$0.275	–	$0.55	$2.20	200K
OpenAIfine-tuned, snapshot 2025-04-16	`ft:o4-mini-2025-04-16`	$4.00	$16.00	$1.00	–	$2.00	$8.00	200K
Azure OpenAI	`azure/o4-mini`	$1.10	$4.40	$0.275	–	–	–	200K
Azure OpenAIsnapshot 2025-04-16	`azure/o4-mini-2025-04-16`	$1.10	$4.40	$0.275	–	$0.55	$2.20	200K
Replicate	`replicate/openai/o4-mini`	$1.00	$4.00	–	–	–	–	–
Vercel AI Gateway	`vercel_ai_gateway/openai/o4-mini`	$1.10	$4.40	$0.275	$0	–	–	200K
Azure OpenAIeu, snapshot 2025-04-16	`azure/eu/o4-mini-2025-04-16`	$1.21	$4.84	$0.303	–	$0.605	$2.42	200K
Azure OpenAIus, snapshot 2025-04-16	`azure/us/o4-mini-2025-04-16`	$1.21	$4.84	$0.303	–	$0.605	$2.42	200K

Other o4 Mini prices on OpenAI

Priority input	$2.00 per 1M tokens
Priority output	$8.00 per 1M tokens
Flex input	$0.55 per 1M tokens
Flex output	$2.20 per 1M tokens
Web search	$10.00 per 1K searches

What o4 Mini costs in practice

1,000 requests with 2,000 input and 500 output tokens each

OpenAI	$4.40
Replicate	$4.00
Azure OpenAI	$4.40
Vercel AI Gateway	$4.40
OpenAI batch	$2.20

100 long-document requests with 100,000 input and 2,000 output tokens each

OpenAI	$11.88
Replicate	$10.80
Azure OpenAI	$11.88
Vercel AI Gateway	$11.88

o4 Mini features

Function calling
Parallel tool calls
Structured output
Image input
PDF input
Reasoning
Prompt caching
Web search

Use o4 Mini with LiteLLM

Call o4 Mini through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import completion

response = completion(
    model="o4-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: o4-mini
    litellm_params:
      model: o4-mini
      api_key: os.environ/OPENAI_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "o4-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

o4 Mini FAQ

How much does o4 Mini cost?

o4 Mini costs $1.10 per 1M input tokens and $4.40 per 1M output tokens on OpenAI, with cache reads at $0.275 per 1M tokens. Batch requests cost $0.55 per 1M input tokens and $2.20 per 1M output tokens. Across 4 providers on LiteLLM, the input price ranges from $1.00 to $1.10.

What is the context window of o4 Mini?

o4 Mini has a 200,000-token context window and returns up to 100,000 tokens per response.

Which providers offer o4 Mini?

o4 Mini is available from 4 providers through LiteLLM: OpenAI, Azure OpenAI, Replicate and Vercel AI Gateway. The lowest price is on Replicate.

How do I call o4 Mini with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="o4-mini", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does o4 Mini support?

o4 Mini supports function calling, structured output, image input, PDF input, reasoning, prompt caching and web search. It does not support parallel tool calls.

When did LiteLLM add o4 Mini?

o4 Mini was added to LiteLLM's model price file in April 2025.

Is o4 Mini being deprecated?

OpenAI lists a deprecation date of October 23, 2026 for o4-mini.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: OpenAI, Azure OpenAI, Replicate, Vercel AI Gateway.

Provider pages: OpenAI, Azure OpenAI, Replicate, Vercel AI Gateway.