o1-pro
OpenAI · released Mar 19, 2025
- Type
- Proprietary
- Input
- $150.00
- Output
- $600.00
- Cached
- Not published
List price · per 1M tokens · OpenAI at 200K context · source ↗
Our take
Written Aug 2, 2026o1-pro is OpenAI's premium reasoning model for extended chain-of-thought work across text, images and files. It handles up to 200,000 tokens in a single request, but carries a steep per-token rate and has no measured quality data in our records.
Choose this for high-stakes reasoning tasks where extended thinking time is acceptable and cost is secondary, or for long-document analysis and multimodal inputs requiring textual reasoning output. Skip it if you need verified benchmark scores, fast throughput, or if your budget cannot absorb a premium price tier with no independent quality validation.
The case for it
- 200,000-token request limit supports long-document and multimodal reasoning workloads.
- Identical pricing on both direct and routed access, so routing choice carries no cost penalty.
The case against it
- Extremely high per-token rate with zero benchmark scores in our data to validate performance.
- Disclosed throughput of 15 tokens per second on OpenAI direct is slower than many models at far lower price points.
- No independent or first-party quality verification: no Elo, no MMLU, no coding scores, no reasoning benchmarks in our records.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up o1-pro — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes OpenAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $150.00 in / $600.00 out
- Context served
- 200K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $150.00 / $600.00 | 200K | not measured | Unknown | Unknown | Unknown |
| OpenAI | $150.00 / $600.00 | 200K | 2 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| OpenAI | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against o1-pro
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- openai-o1-pro