OpenAI: o1
openai/o1The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding.
Modalities
In / out per 1M$15 / $60
Context195K
ReleasedDec 17, 2024
Providers
1 provider serves this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 OpenAI | $15 | $60 | $7.50 | 1.32s | 95 tps | 100% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves o1 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what o1 costs pay-as-you-go elsewhere, not what you pay here.
Input
$15
per 1M tokens
Output
$60
per 1M tokens
Cache read
$7.50
per 1M cached tokens
Included in every pass
o1 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s10.0s20.0s30.0s40.0s
Oct 14, 4 AMOct 14, 5 AM
Median 90th percentile 99th percentile
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 14, 4 AMOct 14, 5 AM
Median 90th percentile 99th percentile
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 100%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 100%
100% 98% 97% 95%
Oct 13, 2:50 PMNow
Apps
Tools that most often run o1, by tokens this week.
Activity
77.0M tokens processed market-wide in the last month.
010.0M20.0M30.0M40.0M
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for o1?
openai/o1. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does o1 hold?
200,000 tokens per request, of which up to 100,000 can be the response.
What can it accept and return?
Input: text, image, file. Output: text.
What does o1 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $15 per 1M input tokens and $60 per 1M output tokens.
How current is its knowledge?
Training data runs to Oct 2023. Anything later has to come from your prompt or a tool call.
Who built o1?
OpenAI, in the o1 family.
Explore
Other models your pass can call.
