Text Embedding 3 (Large) charges $0.13 per 1M input tokens and $0.00 per 1M output tokens. Real bills depend on your input/output split — the tables below price Text Embedding 3 (Large) 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 | $0.000117 | $0.000091 | $0.000039 | $0.00013 | $0.00 |
| 10,000 tokens | $0.00117 | $0.00091 | $0.00039 | $0.0013 | $0.00 |
| 100,000 tokens | $0.0117 | $0.0091 | $0.0039 | $0.013 | $0.00 |
| 1 million tokens | $0.117 | $0.091 | $0.039 | $0.13 | $0.00 |
Uncached. Volume links open interactive pages with adjustable splits.
Monthly projections
| Scale | Requests / day | Chat workload / month | Agentic workload / month* |
|---|---|---|---|
| 100 req/day | 3,000 | $1.56 | $15.60 |
| 1K req/day | 30,000 | $15.60 | $156.00 |
| 10K req/day | 300,000 | $156.00 | $1,560.00 |
| 100K req/day | 3,000,000 | $1,560.00 | $15,600.00 |
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 $0.13; 1M purely output tokens cost $0.00. 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 $0.00052 with 50% cached input, or $0.00052 without caching.
At 1,000 requests/day of a chat workload (4K in / 800 out, 50% cached): $15.60/month. At 10,000 requests/day: $156.00/month. Model your exact mix with the monthly cost calculator.