At a glance
| Provider | OpenAI |
|---|---|
| Released | 2024-12 |
| Tier | frontier |
| License | Closed / proprietary |
| Modalities | text, image |
| Context window | 200k tokens |
| Max output | 100k tokens |
| API price · input | $15.00 / 1M tokens |
| API price · output | $60.00 / 1M tokens |
Benchmark performance
How o1 stacks up against the current leader (GPT-5) and the median model in the leaderboard:
| Benchmark | o1 | GPT-5 | Median |
|---|---|---|---|
| Chatbot Arena Elo | 1355 | 1410 | 1320 |
| MMLU-Pro | 83.5 | 86.8 | 78.0 |
| GPQA Diamond | 78.0 | 87.3 | 65.0 |
| MATH | 94.8 | 96.7 | 78.3 |
| HumanEval | 89.5 | 95.1 | 92.0 |
| SWE-Bench Verified | 48.9 | 74.9 | 49.0 |
Numbers compiled from provider technical reports and Chatbot Arena. See methodology for the composite-score formula.
OpenRouter routes your requests across o1, GPT-5, Claude, Gemini, and 100+ other models behind a single API key — pay-as-you-go, no monthly minimum. Try OpenRouter → (affiliate · supports this site)
What does o1 cost in practice?
API pricing is $15.00 per 1M input tokens and $60.00 per 1M output tokens. Assuming a 50/50 input/output split, here is what that looks like at three workload sizes:
| Volume | Per day | Per month | Per year |
|---|---|---|---|
| 1M tokens/day | $37.50 | $1,125 | $13,688 |
| 10M tokens/day | $375.00 | $11,250 | $136,875 |
| 100M tokens/day | $3,750 | $112,500 | $1,368,750 |
Strengths & weaknesses
Where it shines
- GPQA: 78.0 (rank #6 of 29, above average)
- MATH: 94.8 (rank #6 of 29, above average)
Where it lags
- SWE-Bench: 48.9 (rank #14 of 18, mid-pack)
Best alternatives
The closest models to o1 by tier and benchmark score:
| Model | Score | $ in / out | Context | Action |
|---|---|---|---|---|
| Gemini 2.5 Pro |
80.9 | $1.25 / $10.00 | 2M | Try → · vs o1 |
| Claude Opus 4.1 Anthropic |
83.6 | $15.00 / $75.00 | 200k | Try → · vs o1 |
| Grok 4 xAI |
83.6 | $3.00 / $15.00 | 256k | Try → · vs o1 |
| o3 OpenAI |
83.7 | $2.00 / $8.00 | 200k | Try → · vs o1 |
| GPT-5 OpenAI |
86.0 | $1.25 / $10.00 | 400k | Try → · vs o1 |
Frequently asked questions
Is o1 a good model?
o1 scores 75.7 on the llmrank.top composite (rank #10 of 30). It is competitive with the leaders (GPT-5 tops the board at 86.0). Whether it's the right fit depends on your workload — see the use-case discussion on this page.
How much does o1 cost?
o1 is priced at $15.00 per 1M input tokens and $60.00 per 1M output tokens (USD). For a 10M-token-per-day workload split 50/50, that works out to roughly $375.00/day or $136,875/year.
What is o1's context window?
200k tokens. That covers most multi-document workloads.
Is o1 open source?
No — it is a closed (proprietary) model accessed only via the provider API.
What is o1's SWE-Bench score?
o1 scores 48.9% on SWE-Bench Verified — the benchmark that measures real-world GitHub issue resolution. Its Chatbot Arena Elo is 1355.
What are the best alternatives to o1?
Closest alternatives by tier and score: Gemini 2.5 Pro, Claude Opus 4.1, Grok 4. See the alternatives section on this page for side-by-side numbers.
Related: Gemini 2.5 Pro · Claude Opus 4.1 · Grok 4 · Full leaderboard
Spotted out-of-date numbers? Open an issue — corrections usually ship within 24h.
Try o1 now
Direct link to the official playground — or use OpenRouter to A/B test it against any other model on a single API key.