The Orchestrator › Models › OpenAI
OpenAI: o3 Pro
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
Specifications
| Provider | OpenAI |
| Model ID | openai/o3-pro |
| Context window | 200K tokens (200,000) |
| Modalities | text + image + file → text |
| Tokenizer | GPT |
| Router sources | OpenRouter, Vercel AI Gateway |
| Released | 2025-06-10 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | openai/o3-pro | $20.00 | $80.00 | 200K |
| standard | Vercel AI Gateway | openai/o3-pro | $20.00 | $80.00 | 200K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $20.00 | $80.00 | 200K |
| 2026-11-14 | $20.00 | $80.00 | 200K |
Capabilities
Vision (image input)File inputAgentic tool useStructured outputsReasoning (always on)Controllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, max_tokens, reasoning, response_format, seed, structured_outputs, tool_choice, tools