The Orchestrator › Models › OpenAI
OpenAI: o1
o1 is OpenAI's flagship reasoning model, designed for complex problems that require deep thinking. It provides strong reasoning capabilities with improved accuracy for complex multi-step tasks.
Specifications
| Provider | OpenAI |
| Model ID | openai/o1 |
| Context window | 200K tokens (200,000) |
| Modalities | text + image + pdf → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2024-12-05 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | openai/o1 | $15.00 | $60.00 | 200K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $15.00 | $60.00 | 200K |
Capabilities
Vision (image input)Agentic tool useStructured outputsControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs