o1-pro
o1-proReleased 19 Mar 2025 (Mar 2025)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $150.00 | $600.00 | |
| Batch 50% off | $75.00 | $300.00 | 50% off |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$90,000
- RAG over documents2,000 requests a day, 8K in / 0.6K out$93,600
- Coding agent1,000 requests a day, 40K in / 2K out$216,000
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$252,000
Where to run it
1 host serve o1-pro. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API o1-pro | $150.00 / $600.00 | o1-pro |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| OpenAI | |||||||
| 2025-03-19 o1-pro-2025-03-19 | $150.00 / $600.00 | o1-pro-2025-03-19 | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesTextPDFs
- Produces
- Text
- Features
- Parallel tool callsPDF inputPrompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
- 94% less
- 98% less
- 98% less
Other frontier labs
- 94% less
- 98% less
- 99% less
- 97% less
Open-weight picks
- 98% less
- 99% less
- 99% less
- 100% less
Model line
Newer and older versions, at each lab's own price.
- Jun 2025o3-proLatest$20.00 / $80.00
- Mar 2025o1-proThis page$150.00 / $600.00
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="o1-pro", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "o1-pro", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/o1-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does o1-pro cost?
On OpenAI, o1-pro costs $150.00 per million input tokens and $600.00 per million output tokens.
Which APIs offer o1-pro?
o1-pro runs on 1 API: OpenAI.
What is o1-pro's context window?
200K tokens, with up to 100K tokens in one reply.
Is o1-pro being retired?
It has been retired: OpenAI retired it on 23 Oct 2026.
Is there a newer version of o1-pro?
Yes. o3-pro is the newest model in this line, released on 10 Jun 2025.
What are cheaper alternatives to o1-pro?
Models that cost less and keep most of what it can do: GPT-6.2 Astra on OpenAI (94% less), Claude Fable 5.2 on Anthropic (94% less), Gemini 4 Carbon on Google AI Studio (98% less) and Kimi K3.1 Pro on Databricks (98% less). Savings are on a mix of 3 input tokens to 1 output token.
When was o1-pro released?
OpenAI released it on 19 Mar 2025.
What is o1-pro's API model id?
Use o1-pro with OpenAI.
Sources
Raw catalog entry for o1-pro on OpenAI
{
"deprecation_date": "2026-10-23",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"successor_model": "gpt-5.6-sol",
"input_cost_per_token": 0.00015,
"input_cost_per_token_batches": 0.000075,
"litellm_provider": "openai",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "responses",
"output_cost_per_token": 0.0006,
"fedramp_uplift_multiplier": 1.1,
"output_cost_per_token_batches": 0.0003,
"source": "https://developers.openai.com/api/docs/pricing",
"supported_endpoints": [
"/v1/responses",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": false,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
}