o1
OpenAI's first dedicated reasoning model, released December 2024, using chain-of-thought to solve complex math, science and coding problems.
Key Specifications
- Context window
- 200K tokens
- Max output
- 100K tokens
- Knowledge cutoff
- Released
- Inputs
- Text, image
- Capabilities Show details
- Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON. File upload Process uploaded documents, spreadsheets, and other files. MCP Connect to services via Model Context Protocol.
Hosted API pricing
| Provider | Input /1M tokens | Output /1M tokens | Cached input /1M | Cost at 10M in + 2M out | |
|---|---|---|---|---|---|
|
OpenAI
Creator
|
$15.00 | $60.00 | $7.50 | $270.00 | View |
DigitalOcean
|
$15.00 | $60.00 | $7.50 | $270.00 | View |
Azure
|
$15.00 | $60.00 | $7.50 | $270.00 | View |
Replicate
|
$15.00 | $60.00 | $270.00 | View |
Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.
Similarly priced models
The models nearest o1 by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs o1 |
|---|---|---|---|---|---|---|
|
GPT-5.5
OpenAI
|
$9.1667 | $5.00 | $30.00 | 1M | Dec 2025 | −59% |
|
GPT-4 Turbo
OpenAI
|
$13.3333 | $10.00 | $30.00 | 128K | Dec 2023 | −41% |
Claude Fable 5
Anthropic
|
$16.6667 | $10.00 | $50.00 | 1M | Jan 2026 | −26% |
|
Claude Fable 5.1
Anthropic
|
$16.6667 | $10.00 | $50.00 | 1M | Jun 2026 | −26% |
|
GPT-6 Astra
OpenAI
|
$16.6667 | $10.00 | $50.00 | 1M | Apr 2026 | −26% |
|
o1
This model
OpenAI
|
$22.50 | $15.00 | $60.00 | 200K | Oct 2023 | |
|
o3-pro
OpenAI
|
$30.00 | $20.00 | $80.00 | 200K | Jun 2024 | +33% |
|
GPT-5 Pro
OpenAI
|
$32.50 | $15.00 | $120.00 | 400K | Sep 2024 | +44% |
|
GPT-4
OpenAI
|
$35.00 | $30.00 | $60.00 | 8K | Dec 2023 | +56% |
|
GPT-5.2 Pro
OpenAI
|
$45.50 | $21.00 | $168.00 | 400K | Aug 2025 | +102% |
|
GPT-5.4 Pro
OpenAI
|
$55.00 | $30.00 | $180.00 | 1M | Aug 2025 | +144% |
Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.
Frequently Asked Questions
What is o1 good for?
Reasoning-heavy math, science and coding problems where a long chain of thought is the point. OpenAI calls it its first dedicated reasoning model.
When is o1 not a good fit?
New projects: OpenAI plans to shut it down in October 2026. No web search or code execution, its knowledge is years old, and it sits near the top of OpenAI's price range.
What is the cheapest way to run o1?
The cheapest hosted rate is $15.00 / $60.00 per 1M tokens via OpenAI.
How does o1 compare with o3?
OpenAI says o3 is a step up from o1 in tool use: it is trained to call tools inside its chain of thought, deciding when and how to use them, and can work with images as part of its reasoning, cropping or rotating them as it thinks. Same 200K-token context and text and image input. o1 lists at 650% more per 1M input tokens and 650% more per 1M output tokens than o3. It came out 4 months earlier and has an older knowledge cutoff (October 2023 against June 2024).
Can I self-host o1?
No. OpenAI does not publish the weights; o1 is available only through hosted APIs.
More from OpenAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
o3-pro
|
200K | $20.00 | $80.00 |
|
GPT-6 Astra
|
1M | $10.00 | $50.00 |
|
GPT-5 Pro
|
400K | $15.00 | $120.00 |
|
o3-deep-research
|
200K | $10.00 | $40.00 |
|
GPT-4
|
8K | $30.00 | $60.00 |
|
GPT-4 Turbo
|
128K | $10.00 | $30.00 |
|
GPT-5.2 Pro
|
400K | $21.00 | $168.00 |
|
GPT-5.5 Pro
|
1M | $30.00 | $180.00 |