Model Library
OpenAIReleased December 5, 2024o1
OpenAI · Released December 5, 2024
Intelligence score
23
At a glance
- Intelligence
- 23
- Speed
- 131.0tokens/sec
- Latency
- 27.61stime to first token
- Input price
- $15.00per 1M tokens
- Output price
- $60.00per 1M tokens
- Context window
- 200Ktokens
- Parameters
- —
Summary
Comparison summary
o1 scores 23 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28). o1 generates output at 131.0 tokens per second (based on OpenAI's API), which is above average compared to other reasoning models in a similar price tier (median: 81.2 t/s). o1 costs $15.00 per 1M input tokens (at the higher end, median: $1.50) and $60.00 per 1M output tokens (at the higher end, median: $8.40), based on OpenAI's API.
Specifications
Technical specifications
| Model name | o1 |
|---|---|
| Provider | OpenAI |
| Release date | December 5, 2024 |
| Intelligence score | 23 |
| Speed | 131.0 tokens/sec |
| Latency (TTFT) | 27.61s |
| Input price | $15.00 / 1M tokens |
| Output price | $60.00 / 1M tokens |
| Context window | 200,000 tokens |
| Parameters | — |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: o1 |
Pricing
Token prices
Price per 1M tokens
o1, as listed in the catalog record
- Input$15.00
- Output$60.00
| Token type | Price per 1M |
|---|---|
| Input | $15.00 |
| Output | $60.00 |
Model Intelligence legacy profile: o1
FAQ · 19
Frequently asked questions
o1 was released on December 5, 2024.
o1 was created by OpenAI.
o1 scores 23 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28).
o1 generates output at 131.0 tokens per second (based on OpenAI's API), which is above average compared to other reasoning models in a similar price tier (median: 81.2 t/s).
o1 has a time to first token (TTFT) of 27.61s (based on OpenAI's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 2.78s).
o1 costs $15.00 per 1M input tokens (at the higher end, median: $1.50) and $60.00 per 1M output tokens (at the higher end, median: $8.40), based on OpenAI's API.
o1 costs $15.00 per 1M input tokens and $60.00 per 1M output tokens (based on OpenAI's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $14.25 per 1M tokens. Pricing may vary by provider.
Yes, o1 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
o1 supports text and image input.
o1 supports text only output.
Yes, o1 supports image input and can analyze, describe, and answer questions about images.
Yes, o1 is multimodal. It can process text and image input and generate text only output.
o1 has a context window of 200k tokens. This determines how much text and conversation history the model can process in a single request.
No, o1 is proprietary. The model weights are not publicly available.
o1 is a proprietary model and OpenAI has not disclosed the model size or parameter count.
o1 achieves a score of 23 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
o1 has a knowledge cutoff of October 2023. The model's training data includes information up to this date.
Yes, o1 is available via API through 2 providers.
o1 is available through 2 API providers.