GPT-5.5 charges $5.00 per 1M input tokens and $30.00 per 1M output tokens (cached input: $0.50/M). Real bills depend on your input/output split — the tables below price GPT-5.5 at 1K–1M tokens across common workload shapes. Verified Aug 16, 2026
Cost by token volume
| Volume | Input-heavy (90/10) | Balanced (70/30) | Output-heavy (30/70) | All input | All output |
|---|---|---|---|---|---|
| 1,000 tokens | $0.0075 | $0.0125 | $0.0225 | $0.005 | $0.03 |
| 10,000 tokens | $0.075 | $0.125 | $0.225 | $0.05 | $0.30 |
| 100,000 tokens | $0.75 | $1.25 | $2.25 | $0.50 | $3.00 |
| 1 million tokens | $7.50 | $12.50 | $22.50 | $5.00 | $30.00 |
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% | $0.044 | $13,200.00 | — |
| 50% | $0.035 | $10,500.00 | −$2,700.00 |
| 75% | $0.0305 | $9,150.00 | −$4,050.00 |
Monthly projections
| Scale | Requests / day | Chat workload / month | Agentic workload / month* |
|---|---|---|---|
| 100 req/day | 3,000 | $105.00 | $384.00 |
| 1K req/day | 30,000 | $1,050.00 | $3,840.00 |
| 10K req/day | 300,000 | $10,500.00 | $38,400.00 |
| 100K req/day | 3,000,000 | $105,000.00 | $384,000.00 |
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 $5.00; 1M purely output tokens cost $30.00. 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 $0.035 with 50% cached input, or $0.044 without caching.
At 1,000 requests/day of a chat workload (4K in / 800 out, 50% cached): $1,050.00/month. At 10,000 requests/day: $10,500.00/month. Model your exact mix with the monthly cost calculator.