about
The first commercial model to surpass PhD-level human experts on GPQA Diamond, o1-preview scored 77.3% against the 69.7% achieved by domain specialists with internet access. It introduced inference-time compute scaling, where spending more tokens on hidden chain-of-thought reasoning produces measurably better answers, placing among the top 500 US students on AIME and in the 89th percentile on Codeforces.
Licenseopenai
Context window(in thousands)128,000
Use cases for o1-preview
- PhD-level scientific reasoning: Scoring 77.3% on GPQA Diamond, 8 points above human PhD experts with internet access, o1-preview handles graduate-level physics, chemistry, and biology problems requiring multi-step inference.
- Competitive programming: Placing in the 89th percentile on Codeforces, it solves algorithmic challenges that require sustained logical reasoning, constraint analysis, and optimal solution design.
- Inference-time compute scaling: Its hidden chain-of-thought architecture produces measurably better answers when given more thinking tokens, enabling developers to trade latency for accuracy on high-stakes queries.
Quality
Arena Elo1388
MMLUN/A
MT BenchN/A
o1-preview scores 90.8% on MMLU (0-shot CoT) and 78.0% on GPQA Diamond, surpassing human PhD experts (69.7%) on the latter by 8 points. Compared to GPT-4 Turbo (86.5% MMLU) on the same sheet, the 4-point MMLU improvement understates the reasoning leap, as o1-preview's hidden chain-of-thought architecture specifically targets multi-step inference that standard benchmarks underweight.
pricing
Running o1-preview through Telnyx Inference costs $15.00 per million input tokens and $60.00 per million output tokens. Processing 100,000 PhD-level science problems at 5,000 tokens each would cost approximately $37,500. For STEM-only workloads, o1-mini ($3/$12 per million tokens) on the same sheet delivers 80% of the reasoning at 80% lower cost.
What's Twitter saying?
- Developers praise o1-preview for superior coding quality, producing fewer bugs and solving complex problems that other models couldn't, though it often generates verbose outputs and unexpectedly refactors code.
- Benchmarks and tests show strong reasoning and math performance, but it's only okay at coding—often outperformed by Claude 3.5 Sonnet—and weaker in creative writing.
- Many note o1-preview outperformed the newer o1 model in creative problem-solving and autonomy, with o1 seen as lazier, more rigid, and a regression.
Explore Our LLM Library
Discover the power and diversity of large language models available with Telnyx. Explore the options below to find the perfect model for your project.
| Organization | Model Name | Tasks | Languages Supported | Context Length | Parameters | Model Tier | License |
|---|---|---|---|---|---|---|---|
| deepseek-ai | DeepSeek-R1-Distill-Qwen-14B | text generation | English | 43,000 | 14.8B | medium | deepseek |
| fixie-ai | ultravox-v0_4_1-llama-3_1-8b | audio text-to-text | Multilingual | 8,000 | 8.7B | small | mit |
| gemma-2b-it | text generation | English | 8,192 | 2.5B | small | gemma | |
| gemma-7b-it | text generation | English | 8,192 | 8.5B | small | gemma | |
| meta-llama | Llama-3.3-70B-Instruct | text generation | Multilingual | 99,000 | 70.6B | large | llama3.3 |
| meta-llama | Llama-Guard-3-1B | safety classification | Multilingual | 128,000 | 1.5B | small | llama3.3 |
| meta-llama | Meta-Llama-3.1-70B-Instruct | text generation | Multilingual | 99,000 | 70.6B | large | llama3.1 |
| meta-llama | Meta-Llama-3.1-8B-Instruct | text generation | Multilingual | 131,072 | 8.0B | small | llama3.1 |
| minimaxai | MiniMax-M2.5 | text generation | English | 2,000,000 | 0 | large | minimaxai |
| minimaxai | MiniMax-M2.7 | text generation | English | 200,000 | 0 | large | minimaxai |
| mistralai | Mistral-7B-Instruct-v0.1 | text generation | English | 8,192 | 7.2B | small | apache-2.0 |
| mistralai | Mistral-7B-Instruct-v0.2 | text generation | English | 32,768 | 7.2B | small | apache-2.0 |
| mistralai | Mixtral-8x7B-Instruct-v0.1 | text generation | Multilingual | 32,768 | 46.7B | medium | apache-2.0 |
| moonshotai | Kimi-K2.5 | text generation | English | 256,000 | 1.0T | large | modified-mit |
| Qwen | Qwen3-235B-A22B | text generation | English | 32,768 | 235.1B | large | apache-2.0 |
| zai-org | GLM-5.1-FP8 | text generation | English | 202,752 | 753.9B | large | mit |
| anthropic | claude-3-7-sonnet-latest | text generation | Multilingual | 200,000 | 0 | large | anthropic |
| anthropic | claude-haiku-4-5 | text generation | Multilingual | 200,000 | 0 | large | anthropic |
| anthropic | claude-opus-4-6 | text generation | Multilingual | 200,000 | 0 | large | anthropic |
| anthropic | claude-sonnet-4-20250514 | text generation | Multilingual | 200,000 | 0 | large | anthropic |
| gemini-2.0-flash | text generation | Multilingual | 1,048,576 | 0 | large | ||
| gemini-2.5-flash | text generation | Multilingual | 1,048,576 | 0 | large | ||
| gemini-2.5-flash-lite | text generation | Multilingual | 1,048,576 | 0 | large | ||
| groq | gpt-oss-120b | text generation | English | 131,072 | 117.0B | large | groq |
| groq | kimi-k2-instruct | text generation | English | 131,072 | 1.0T | large | groq |
| groq | llama-3.3-70b-versatile | text generation | Multilingual | 131,072 | 70.6B | large | llama3.3 |
| groq | llama-4-maverick-17b-128e-instruct | text generation | Multilingual | 1,000,000 | 400.0B | large | llama4 |
| groq | llama-4-scout-17b-16e-instruct | text generation | Multilingual | 128,000 | 109.0B | large | llama4 |
| openai | gpt-3.5-turbo | text generation | Multilingual | 4,096 | 0 | large | openai |
| openai | gpt-4 | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4-0125-preview | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4-0314 | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4-0613 | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4-1106-preview | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4-32k-0314 | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4-turbo-preview | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4.1 | text generation | Multilingual | 1,047,576 | 0 | large | openai |
| openai | gpt-4.1-mini | text generation | Multilingual | 1,047,576 | 0 | large | openai |
| openai | gpt-4o | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-4o-mini | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | gpt-5 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5-mini | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.1 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.2 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | o1-mini | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | o1-preview | text generation | Multilingual | 128,000 | 0 | large | openai |
| openai | o3-mini | text generation | Multilingual | 200,000 | 0 | large | openai |
| xai-org | grok-2 | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-2-latest | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3 | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3-beta | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3-fast | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3-fast-beta | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3-fast-latest | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3-latest | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3-mini | text generation | Multilingual | 131,072 | 0 | large | xai |
| xai-org | grok-3-mini-fast | text generation | Multilingual | 131,072 | 0 | large | xai |
TRY IT OUT
Chat with an LLM
Powered by our own GPU infrastructure, select a large language model, add a prompt, and chat away. For unlimited chats, sign up for a free account on our Mission Control Portal here.
RESOURCES
Get started
Check out our helpful tools to help get you started.
faqs
Is o1 Preview better than o1?
o1 Preview was the early access version of OpenAI's o1 reasoning model, later superseded by the full o1 release. The full o1 offers improved accuracy and reliability over the preview version.
What is o1 Preview good for?
o1 Preview excels at STEM reasoning, mathematical problem-solving, and complex analytical tasks. It uses internal chain-of-thought reasoning before responding, making it suited for technical applications that benefit from deeper thinking.
Is o1 Preview available?
o1 Preview remains accessible through the API but has been superseded by the full o1 and o3-mini models. OpenAI recommends migrating to newer reasoning models for new projects.
How much does o1 Preview cost?
o1 Preview is priced at $15 per million input tokens and $60 per million output tokens, reflecting the additional compute used for internal reasoning. The newer o3-mini offers similar reasoning at lower cost.
Is o1 Preview better than GPT-4?
o1 Preview significantly outperforms GPT-4 on mathematical reasoning, science, and coding tasks that require step-by-step analysis. GPT-4 remains stronger for general-purpose tasks where speed matters more than maximum reasoning depth.
What is the difference between o1 Preview and o1 mini?
o1 Preview is the full reasoning model with broad capabilities, while o1 mini is a smaller, cheaper variant optimized for STEM tasks. o1 mini offers 80% cost savings with minimal accuracy loss on math and coding.