o1 API Pricing

As of October 10, 2026, o1 costs $15.00 per 1M input tokens and $60.00 per 1M output tokens on OpenAI, with cache reads at $7.50 per 1M tokens. It has a 200,000-token context window and returns up to 100,000 tokens per response.

By OpenAIModel ID o1Prices updated October 10, 2026Checked October 10, 2026

Scheduled for deprecation: OpenAI lists October 23, 2026 as the deprecation date for o1.

Input: $15.00 / 1M tokens
Output: $60.00 / 1M tokens
Cache read: $7.50 / 1M tokens
Context window: 200,000 tokens
Max output: 100,000 tokens
Providers: 4
Added to LiteLLM: December 2024

o1 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	`o1`	$15.00	$60.00	$7.50	–	$7.50	$30.00	200K
OpenAIsnapshot 2024-12-17	`o1-2024-12-17`	$15.00	$60.00	$7.50	–	$7.50	$30.00	200K
Azure OpenAI	`azure/o1`	$15.00	$60.00	$7.50	–	–	–	200K
Azure OpenAIsnapshot 2024-12-17	`azure/o1-2024-12-17`	$15.00	$60.00	$7.50	–	$7.50	$30.00	200K
Replicate	`replicate/openai/o1`	$15.00	$60.00	–	–	–	–	–
Vercel AI Gateway	`vercel_ai_gateway/openai/o1`	$15.00	$60.00	$7.50	$0	–	–	200K
Azure OpenAIeu, snapshot 2024-12-17	`azure/eu/o1-2024-12-17`	$16.50	$66.00	$8.25	–	$8.25	$33.00	200K
Azure OpenAIus, snapshot 2024-12-17	`azure/us/o1-2024-12-17`	$16.50	$66.00	$8.25	–	$8.25	$33.00	200K

What o1 costs in practice

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

OpenAI	$60.00
Azure OpenAI	$60.00
Replicate	$60.00
Vercel AI Gateway	$60.00
OpenAI batch	$30.00

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

OpenAI	$162.00
Azure OpenAI	$162.00
Replicate	$162.00
Vercel AI Gateway	$162.00

o1 features

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

Use o1 with LiteLLM

Call o1 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="o1",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: o1
    litellm_params:
      model: o1
      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": "o1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

o1 FAQ

How much does o1 cost?

o1 costs $15.00 per 1M input tokens and $60.00 per 1M output tokens on OpenAI, with cache reads at $7.50 per 1M tokens. Batch requests cost $7.50 per 1M input tokens and $30.00 per 1M output tokens.

What is the context window of o1?

o1 has a 200,000-token context window and returns up to 100,000 tokens per response.

Which providers offer o1?

o1 is available from 4 providers through LiteLLM: OpenAI, Azure OpenAI, Replicate and Vercel AI Gateway.

How do I call o1 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="o1", 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 o1 support?

o1 supports function calling, structured output, image input, PDF input, reasoning and prompt caching. It does not support parallel tool calls.

When did LiteLLM add o1?

o1 was added to LiteLLM's model price file in December 2024.

Is o1 being deprecated?

OpenAI lists a deprecation date of October 23, 2026 for o1.

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.