o1
by OpenAI · openai/o1 · #315 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:33 AM UTC · refreshed hourly
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$15.00
per 1M tokens
Output
$60.00
per 1M tokens
Blended (3:1)
$26.25
3 input : 1 output
Cache read
$7.50
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for o1 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $26.25 | $1.59 | — |
| 50% | $23.44 | $1.22 | −24% |
| 90% | $21.19 | $0.915 | −42% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.0255 | $25.50 |
| Document summary | 8,000 | 1,000 | $0.18 | $180.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.57 | $570.00 |
| Long-context analysis | 150,000 | 5,000 | $2.55 | $2,550 |
Performance
Intelligence Index
23.4
AA composite quality
Coding Index
39.7
Math Index
—
Agentic Index
—
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 84.1% |
| GPQA Diamond | 74.7% |
| Humanity's Last Exam | 7.7% |
| LiveCodeBench | 67.9% |
| SciCode | 35.8% |
| MATH-500 | 97.0% |
| AIME | 72.3% |
| IFBench | 70.3% |
| AA-LCR (Long Context Reasoning) | 59.3% |
| Terminal-Bench Hard | 12.9% |
| τ²-Bench (Telecom) | 62.6% |
Specs
Context window
200K
tokens
Max output
100K
tokens
Input modalities
text, image, file
Tokenizer
GPT