Observed 2026-06-03 11:12. Prices are USD per 1M tokens (from OpenRouter public pricing). Input: GPT-5 Pro $15 / OpenAI o3 $2, output: $120 / $8.
✓ = the mechanically better side per row (cheaper price / longer context). Magnitude only, not a rating.
| Field | GPT-5 Pro openai/gpt-5-pro | OpenAI o3 openai/o3 |
|---|---|---|
| Input priceUSD/1M | $15 | $2✓ |
| Output priceUSD/1M | $120 | $8✓ |
| Cache readUSD/1M | Accumulating… | $0.5 |
| Context windowtokens | 400k✓ | 200k |
Source: OpenRouter /api/v1/models → collect_prices.py → Source(price)。 · GPT-5 Pro: openai/gpt-5-pro · OpenAI o3: openai/o3
Aggregated observations, not predictions. Prices change (observation time noted). © TraceBottle for AI
As observed on 2026-06-03 11:12, input is GPT-5 Pro $15 / OpenAI o3 $2 per 1M tokens — OpenAI o3 is cheaper. Output is $120 / $8 — OpenAI o3 is cheaper.
GPT-5 Pro: 400,000 tokens, OpenAI o3: 200,000 tokens (observed 2026-06-03 11:12).
Observed 2026-06-03 11:12 (UTC). Source: OpenRouter public pricing (/api/v1/models). Prices change — check each provider's official pricing for the latest. This site publishes only observed values, never predictions.