OpenAI · Model profile
o1-preview
Intelligence, Performance & Price Analysis
Source: Canonical slug: o1-preview · Canonical model registry at build time
Routing verdict
Capable everyday model
Good for routine tasks; route complex reasoning and premium workloads to stronger models.
o1-preview summary metrics
- Intelligence
- 17 scoreo1-preview scores 17 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28).
- Input Price
- $16.50 / 1M tokenso1-preview costs $16.50 per 1M input tokens (at the higher end, median: $1.50) and $66.00 per 1M output tokens (at the higher end, median: $8.40), based on the median across providers serving the model.
- Output Price
- $66.00 / 1M tokenso1-preview costs $16.50 per 1M input tokens (at the higher end, median: $1.50) and $66.00 per 1M output tokens (at the higher end, median: $8.40), based on the median across providers serving the model.
Assessment
Routing verdict and task fit
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | Viable | Intelligence score 17 handles routine reasoning but may struggle with open-ended agentic tasks. |
| Cost-sensitive pipelines | Viable | Output pricing at $66.00 is premium. Route high-volume simple tasks to cheaper alternatives. |
Evidence
Evidence charts
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- Claude Opus 4.8 (max)55.7
- GPT-5.5 (xhigh)54.8
- Claude Opus 4.7 (max)53.5
- Claude Sonnet 5 (max)53.4
- GPT-5.5 (high)53.1
- GPT-5.4 (xhigh)51.4
- GLM-5.2 (max)51.1
- GPT-5.5 (medium)50.4
- Gemini 3.5 Flash50.2
- Claude Sonnet 4.6 (max)47.2
- Gemini 3.1 Pro Preview46.5
- Qwen3.7 Max46
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- GPT-5.5 (low)43.5
- Muse Spark43.1
- Kimi K2.7 Code41.9
- Claude Sonnet 5 (Non-reasoning)41.7
| Model | Artificial Analysis Intelligence Index by Open Weights / Proprietary |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| Claude Opus 4.8 (max) | 55.7 |
| GPT-5.5 (xhigh) | 54.8 |
| Claude Opus 4.7 (max) | 53.5 |
| Claude Sonnet 5 (max) | 53.4 |
| GPT-5.5 (high) | 53.1 |
| GPT-5.4 (xhigh) | 51.4 |
| GLM-5.2 (max) | 51.1 |
| GPT-5.5 (medium) | 50.4 |
| Gemini 3.5 Flash | 50.2 |
| Claude Sonnet 4.6 (max) | 47.2 |
| Gemini 3.1 Pro Preview | 46.5 |
| Qwen3.7 Max | 46 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| GPT-5.5 (low) | 43.5 |
| Muse Spark | 43.1 |
| Kimi K2.7 Code | 41.9 |
| Claude Sonnet 5 (Non-reasoning) | 41.7 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- Claude Opus 4.8 (max)55.7
- GPT-5.5 (xhigh)54.8
- Claude Opus 4.7 (max)53.5
- Claude Sonnet 5 (max)53.4
- GPT-5.5 (high)53.1
- GPT-5.4 (xhigh)51.4
- GLM-5.2 (max)51.1
- GPT-5.5 (medium)50.4
- Gemini 3.5 Flash50.2
- Claude Sonnet 4.6 (max)47.2
- Gemini 3.1 Pro Preview46.5
- Qwen3.7 Max46
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- GPT-5.5 (low)43.5
- Muse Spark43.1
- Kimi K2.7 Code41.9
- Claude Sonnet 5 (Non-reasoning)41.7
| Model | Artificial Analysis Intelligence Index |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| Claude Opus 4.8 (max) | 55.7 |
| GPT-5.5 (xhigh) | 54.8 |
| Claude Opus 4.7 (max) | 53.5 |
| Claude Sonnet 5 (max) | 53.4 |
| GPT-5.5 (high) | 53.1 |
| GPT-5.4 (xhigh) | 51.4 |
| GLM-5.2 (max) | 51.1 |
| GPT-5.5 (medium) | 50.4 |
| Gemini 3.5 Flash | 50.2 |
| Claude Sonnet 4.6 (max) | 47.2 |
| Gemini 3.1 Pro Preview | 46.5 |
| Qwen3.7 Max | 46 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| GPT-5.5 (low) | 43.5 |
| Muse Spark | 43.1 |
| Kimi K2.7 Code | 41.9 |
| Claude Sonnet 5 (Non-reasoning) | 41.7 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- gpt-oss-120b (high)23.8
- o1-preview (this model)17
| Model | Intelligence |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| gpt-oss-120b (high) | 23.8 |
| o1-preview (this model) | 17 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)314 t/s
- Nemotron 3 Ultra250 t/s
- GLM-5.2 (max)218 t/s
- Gemini 3.5 Flash192 t/s
- Grok 4.3 (high)164 t/s
- MiniMax-M399 t/s
- GPT-5.5 (xhigh)88 t/s
- Kimi K2.676 t/s
- DeepSeek V4 Pro (max)72 t/s
- Claude Fable 5 (with fallback)71 t/s
| Model | Speed |
|---|---|
| gpt-oss-120b (high) | 314 t/s |
| Nemotron 3 Ultra | 250 t/s |
| GLM-5.2 (max) | 218 t/s |
| Gemini 3.5 Flash | 192 t/s |
| Grok 4.3 (high) | 164 t/s |
| MiniMax-M3 | 99 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| Kimi K2.6 | 76 t/s |
| DeepSeek V4 Pro (max) | 72 t/s |
| Claude Fable 5 (with fallback) | 71 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
- GPT-5.4 (xhigh)1.05M
- Gemini 3.5 Flash1M
- Claude Fable 5 (with fallback)1M
- GLM-5.2 (max)1M
- DeepSeek V4 Pro (max)1M
- Grok 4.3 (high)1M
- MiniMax-M31M
- Claude Opus 4.8 (max)1M
- Claude Opus 4.7 (max)1M
- Claude Sonnet 5 (max)1M
- Claude Sonnet 4.6 (max)1M
- Gemini 3.1 Pro Preview1M
- Qwen3.7 Max1M
- Claude Sonnet 5 (Non-reasoning)1M
- GPT-5.5 (xhigh)922k
- GPT-5.5 (high)922k
- GPT-5.5 (medium)922k
- GPT-5.5 (low)922k
- GPT-5.4 mini (xhigh)400k
- Nemotron 3 Ultra262.1k
| Model | Context Window |
|---|---|
| GPT-5.4 (xhigh) | 1.05M |
| Gemini 3.5 Flash | 1M |
| Claude Fable 5 (with fallback) | 1M |
| GLM-5.2 (max) | 1M |
| DeepSeek V4 Pro (max) | 1M |
| Grok 4.3 (high) | 1M |
| MiniMax-M3 | 1M |
| Claude Opus 4.8 (max) | 1M |
| Claude Opus 4.7 (max) | 1M |
| Claude Sonnet 5 (max) | 1M |
| Claude Sonnet 4.6 (max) | 1M |
| Gemini 3.1 Pro Preview | 1M |
| Qwen3.7 Max | 1M |
| Claude Sonnet 5 (Non-reasoning) | 1M |
| GPT-5.5 (xhigh) | 922k |
| GPT-5.5 (high) | 922k |
| GPT-5.5 (medium) | 922k |
| GPT-5.5 (low) | 922k |
| GPT-5.4 mini (xhigh) | 400k |
| Nemotron 3 Ultra | 262.1k |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Context window sizing
- Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
- DeepSeek V4 Pro (max)0.0063
- gpt-oss-120b (high)0.00454
- MiniMax-M30.0139
- Grok 4.3 (high)0.0101
- Kimi K2.7 Code0.0203
- GPT-5.5 (low)0.0475
- Grok Build 0.1 06160.0203
- GLM-5.10.0426
- Nemotron 3 Ultra0.0209
- Gemini 3.1 Pro Preview0.0329
- GPT-5.5 (medium)0.0754
- Kimi K2.60.0216
- GLM-5.2 (max)0.0268
- GPT-5.4 mini (xhigh)0.0215
- Gemini 3.5 Flash0.0884
- GPT-5.5 (high)0.0943
- GPT-5.5 (xhigh)0.107
- GPT-5.4 (xhigh)0.0722
- Qwen3.7 Max0.0343
- Claude Sonnet 4.6 (max)0.104
| Model | Cost per Intelligence Index Task |
|---|---|
| DeepSeek V4 Pro (max) | 0.0063 |
| gpt-oss-120b (high) | 0.00454 |
| MiniMax-M3 | 0.0139 |
| Grok 4.3 (high) | 0.0101 |
| Kimi K2.7 Code | 0.0203 |
| GPT-5.5 (low) | 0.0475 |
| Grok Build 0.1 0616 | 0.0203 |
| GLM-5.1 | 0.0426 |
| Nemotron 3 Ultra | 0.0209 |
| Gemini 3.1 Pro Preview | 0.0329 |
| GPT-5.5 (medium) | 0.0754 |
| Kimi K2.6 | 0.0216 |
| GLM-5.2 (max) | 0.0268 |
| GPT-5.4 mini (xhigh) | 0.0215 |
| Gemini 3.5 Flash | 0.0884 |
| GPT-5.5 (high) | 0.0943 |
| GPT-5.5 (xhigh) | 0.107 |
| GPT-5.4 (xhigh) | 0.0722 |
| Qwen3.7 Max | 0.0343 |
| Claude Sonnet 4.6 (max) | 0.104 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
- DeepSeek V4 Pro (max)$0.045
- gpt-oss-120b (high)$0.061
- MiniMax-M3$0.125
- Grok 4.3 (high)$0.139
- Nemotron 3 Ultra$0.244
- Kimi K2.6$0.346
- GLM-5.2 (max)$0.370
- Gemini 3.5 Flash$0.586
- GPT-5.5 (xhigh)$0.863
- Claude Fable 5 (with fallback)$2.75
| Model | Cost per Task |
|---|---|
| DeepSeek V4 Pro (max) | $0.045 |
| gpt-oss-120b (high) | $0.061 |
| MiniMax-M3 | $0.125 |
| Grok 4.3 (high) | $0.139 |
| Nemotron 3 Ultra | $0.244 |
| Kimi K2.6 | $0.346 |
| GLM-5.2 (max) | $0.370 |
| Gemini 3.5 Flash | $0.586 |
| GPT-5.5 (xhigh) | $0.863 |
| Claude Fable 5 (with fallback) | $2.75 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)3.5
- DeepSeek V4 Pro (max)7.2
- MiniMax-M314.5
- Grok 4.3 (high)12.5
- GPT-5.5 (low)65.2
- Grok Build 0.1 061620
- Nemotron 3 Ultra33.5
- Kimi K2.7 Code24.3
- GLM-5.140.4
- Gemini 3.1 Pro Preview49
- GLM-5.2 (max)32.9
- Kimi K2.625
- GPT-5.5 (medium)98.8
- Gemini 3.5 Flash114
- GPT-5.4 mini (xhigh)21.9
- Qwen3.7 Max47.6
- GPT-5.5 (high)118.8
- GPT-5.4 (xhigh)88.5
- GPT-5.5 (xhigh)131.8
- Claude Sonnet 4.6 (max)149.3
| Model | Cost to Run Artificial Analysis Intelligence Index |
|---|---|
| gpt-oss-120b (high) | 3.5 |
| DeepSeek V4 Pro (max) | 7.2 |
| MiniMax-M3 | 14.5 |
| Grok 4.3 (high) | 12.5 |
| GPT-5.5 (low) | 65.2 |
| Grok Build 0.1 0616 | 20 |
| Nemotron 3 Ultra | 33.5 |
| Kimi K2.7 Code | 24.3 |
| GLM-5.1 | 40.4 |
| Gemini 3.1 Pro Preview | 49 |
| GLM-5.2 (max) | 32.9 |
| Kimi K2.6 | 25 |
| GPT-5.5 (medium) | 98.8 |
| Gemini 3.5 Flash | 114 |
| GPT-5.4 mini (xhigh) | 21.9 |
| Qwen3.7 Max | 47.6 |
| GPT-5.5 (high) | 118.8 |
| GPT-5.4 (xhigh) | 88.5 |
| GPT-5.5 (xhigh) | 131.8 |
| Claude Sonnet 4.6 (max) | 149.3 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
- Cache Hit
- Input
- Output
- gpt-oss-120b (high)$0.900
- DeepSeek V4 Pro (max)$1.31
- MiniMax-M3$1.56
- Grok Build 0.1 0616$3.20
- Nemotron 3 Ultra$3.60
- Grok 4.3 (high)$3.95
- Kimi K2.6$5.11
- Kimi K2.7 Code$5.11
- GPT-5.4 mini (xhigh)$5.33
- GLM-5.2 (max)$6.06
- GLM-5.1$6.06
- Qwen3.7 Max$10.25
- Gemini 3.5 Flash$10.65
- Claude Sonnet 5 (max)$12.20
- Claude Sonnet 5 (Non-reasoning)$12.20
- Gemini 3.1 Pro Preview$14.20
- GPT-5.4 (xhigh)$17.75
- Claude Sonnet 4.6 (max)$18.30
- Claude Opus 4.8 (max)$30.50
- Claude Opus 4.7 (max)$30.50
| Model | Cache Hit | Input | Output | Total |
|---|---|---|---|---|
| gpt-oss-120b (high) | $0.150 | $0.150 | $0.600 | $0.900 |
| DeepSeek V4 Pro (max) | $0.0036 | $0.435 | $0.870 | $1.31 |
| MiniMax-M3 | $0.060 | $0.300 | $1.20 | $1.56 |
| Grok Build 0.1 0616 | $0.200 | $1.00 | $2.00 | $3.20 |
| Nemotron 3 Ultra | $0.250 | $0.675 | $2.67 | $3.60 |
| Grok 4.3 (high) | $0.200 | $1.25 | $2.50 | $3.95 |
| Kimi K2.6 | $0.160 | $0.950 | $4.00 | $5.11 |
| Kimi K2.7 Code | $0.160 | $0.950 | $4.00 | $5.11 |
| GPT-5.4 mini (xhigh) | $0.075 | $0.750 | $4.50 | $5.33 |
| GLM-5.2 (max) | $0.260 | $1.40 | $4.40 | $6.06 |
| GLM-5.1 | $0.260 | $1.40 | $4.40 | $6.06 |
| Qwen3.7 Max | $0.250 | $2.50 | $7.50 | $10.25 |
| Gemini 3.5 Flash | $0.150 | $1.50 | $9.00 | $10.65 |
| Claude Sonnet 5 (max) | $0.200 | $2.00 | $10.00 | $12.20 |
| Claude Sonnet 5 (Non-reasoning) | $0.200 | $2.00 | $10.00 | $12.20 |
| Gemini 3.1 Pro Preview | $0.200 | $2.00 | $12.00 | $14.20 |
| GPT-5.4 (xhigh) | $0.250 | $2.50 | $15.00 | $17.75 |
| Claude Sonnet 4.6 (max) | $0.300 | $3.00 | $15.00 | $18.30 |
| Claude Opus 4.8 (max) | $0.500 | $5.00 | $25.00 | $30.50 |
| Claude Opus 4.7 (max) | $0.500 | $5.00 | $25.00 | $30.50 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Specifications
Architecture and limits
| Specification | Value | Source |
|---|---|---|
| Model type | Proprietary | faq |
| Reasoning | Yes | faq |
| Input modalities | o1-preview supports text only input. | faq |
| Output modalities | o1-preview supports text only output. | faq |
| Context window | 130k tokens | faq |
| Open weights / source | No, o1-preview is proprietary. The model weights are not publicly available. | faq |
| Parameters | o1-preview is a proprietary model and OpenAI has not disclosed the model size or parameter count. | faq |
| Knowledge cutoff | o1-preview has a knowledge cutoff of October 2023. The model's training data includes information up to this date. | faq |
| API availability | Yes, o1-preview is available via API through 1 provider. | faq |
Method
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for o1-preview.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Questions
Model FAQ and technical disclosures
Models
Related
- 01OpenAIOther OpenAI models in the catalog.
- 02LeaderboardsCertified metric ranks, when published.