OpenAI: o3 Pro
openai/o3-proThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.
Modalities
In / out per 1M$20 / $80
Context195K
ReleasedJun 10, 2025
Providers
1 provider serves this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 OpenAI | $20 | $80 | Variable | 7.59s | 9 tps | 100% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves o3 Pro in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what o3 Pro costs pay-as-you-go elsewhere, not what you pay here.
Input
$20
per 1M tokens
Output
$80
per 1M tokens
Cache read
—
not published
Included in every pass
o3 Pro 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.
0.0s100.0s200.0s300.0s400.0s
Oct 13, 8 AMOct 13, 6 PMOct 13, 7 PM
Median 90th percentile 99th percentile
0 tok/s5 tok/s10 tok/s15 tok/s20 tok/s
Oct 13, 8 AMOct 13, 6 PMOct 13, 7 PM
Median 90th percentile 99th percentile
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.43%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.66%
100% 95% 90% 85%
Oct 13, 2:50 PMNow
Apps
Tools that most often run o3 Pro, by tokens this week.
Activity
18.4M tokens processed market-wide in the last month.
02.0M4.0M6.0M8.0M
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for o3 Pro?
openai/o3-pro. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does o3 Pro hold?
200,000 tokens per request, of which up to 100,000 can be the response.
What can it accept and return?
Input: text, file, image. Output: text.
What does o3 Pro cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $20 per 1M input tokens and $80 per 1M output tokens.
How current is its knowledge?
Training data runs to Jun 2024. Anything later has to come from your prompt or a tool call.
Who built o3 Pro?
OpenAI, in the o3 family.
Explore
Other models your pass can call.
