GPT-5.3 Codex charges $1.75 per 1M input tokens and $14.00 per 1M output tokens (cached input: $0.175/M). Real bills depend on your input/output split — the tables below price GPT-5.3 Codex at 1K–1M tokens across common workload shapes. Verified Aug 19, 2026
Cost by token volume
| Volume | Input-heavy (90/10) | Balanced (70/30) | Output-heavy (30/70) | All input | All output |
|---|---|---|---|---|---|
| 1,000 tokens | $0.002975 | $0.005425 | $0.0103 | $0.00175 | $0.014 |
| 10,000 tokens | $0.0298 | $0.0543 | $0.1033 | $0.0175 | $0.14 |
| 100,000 tokens | $0.2975 | $0.5425 | $1.033 | $0.175 | $1.40 |
| 1 million tokens | $2.975 | $5.425 | $10.325 | $1.75 | $14.00 |
Uncached. Volume links open interactive pages with adjustable splits.
Prompt caching impact
| Cached share of input | Chat request (4K in / 800 out) | Monthly @ 10K req/day | Savings / month |
|---|---|---|---|
| 0% | $0.0182 | $5,460.00 | — |
| 50% | $0.0151 | $4,515.00 | −$945.00 |
| 75% | $0.0135 | $4,042.50 | −$1,417.50 |
Monthly projections
| Scale | Requests / day | Chat workload / month | Agentic workload / month* |
|---|---|---|---|
| 100 req/day | 3,000 | $45.15 | $150.15 |
| 1K req/day | 30,000 | $451.50 | $1,501.50 |
| 10K req/day | 300,000 | $4,515.00 | $15,015.00 |
| 100K req/day | 3,000,000 | $45,150.00 | $150,150.00 |
Chat: 4K in / 800 out, 50% cached. *Agentic: 40K in / 1.5K out, 65% cached. Model your exact mix in the monthly cost calculator.
FAQ
1M purely input tokens cost $1.75; 1M purely output tokens cost $14.00. A typical mixed workload lands in between — see the volume table for exact splits.
A chat-style request (4,000 input + 800 output) costs about $0.0151 with 50% cached input, or $0.0182 without caching.
At 1,000 requests/day of a chat workload (4K in / 800 out, 50% cached): $451.50/month. At 10,000 requests/day: $4,515.00/month. Model your exact mix with the monthly cost calculator.