o3 API Pricing

As of October 10, 2026, o3 costs $2.00 per 1M input tokens and $8.00 per 1M output tokens on OpenAI, with cache reads at $0.50 per 1M tokens. It has a 200,000-token context window and returns up to 100,000 tokens per response.

By OpenAIModel ID o3Prices updated October 10, 2026Checked October 10, 2026

Input: $2.00 / 1M tokens
Output: $8.00 / 1M tokens
Cache read: $0.50 / 1M tokens
Context window: 200,000 tokens
Max output: 100,000 tokens
Providers: 4
Added to LiteLLM: April 2025

o3 pricing by provider

8 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	`o3`	$2.00	$8.00	$0.50	–	$1.00	$4.00	200K
OpenAIsnapshot 2025-04-16	`o3-2025-04-16`	$2.00	$8.00	$0.50	–	$1.00	$4.00	200K
Azure OpenAI	`azure/o3`	$2.00	$8.00	$0.50	–	–	–	200K
Azure OpenAIsnapshot 2025-04-16	`azure/o3-2025-04-16`	$2.00	$8.00	$0.50	–	$1.00	$4.00	200K
GradientAI	`gradient_ai/openai-o3`	$2.00	$8.00	–	–	–	–	200K
Vercel AI Gateway	`vercel_ai_gateway/openai/o3`	$2.00	$8.00	$0.50	$0	–	–	200K
Azure OpenAIeu, snapshot 2025-04-16	`azure/eu/o3-2025-04-16`	$2.20	$8.80	$0.55	–	$1.10	$4.40	200K
Azure OpenAIus, snapshot 2025-04-16	`azure/us/o3-2025-04-16`	$2.20	$8.80	$0.55	–	$1.10	$4.40	200K

Other o3 prices on OpenAI

Priority input	$3.50 per 1M tokens
Priority output	$14.00 per 1M tokens
Flex input	$1.00 per 1M tokens
Flex output	$4.00 per 1M tokens
Web search	$10.00 per 1K searches

What o3 costs in practice

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

OpenAI	$8.00
Azure OpenAI	$8.00
GradientAI	$8.00
Vercel AI Gateway	$8.00
OpenAI batch	$4.00

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

OpenAI	$21.60
Azure OpenAI	$21.60
GradientAI	$21.60
Vercel AI Gateway	$21.60

o3 features

Input: text, image. Output: text.

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

Use o3 with LiteLLM

Call o3 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="o3",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: o3
    litellm_params:
      model: o3
      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": "o3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

o3 FAQ

How much does o3 cost?

o3 costs $2.00 per 1M input tokens and $8.00 per 1M output tokens on OpenAI, with cache reads at $0.50 per 1M tokens. Batch requests cost $1.00 per 1M input tokens and $4.00 per 1M output tokens.

What is the context window of o3?

o3 has a 200,000-token context window and returns up to 100,000 tokens per response.

Which providers offer o3?

o3 is available from 4 providers through LiteLLM: OpenAI, Azure OpenAI, GradientAI and Vercel AI Gateway.

How do I call o3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="o3", 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 o3 support?

o3 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 o3?

o3 was added to LiteLLM's model price file in April 2025.

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, GradientAI, Vercel AI Gateway.

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