AI21 Labs API pricing
12 AI21 Labs models, from price book 2026-10-22.
Billing rules Veqen applies
- Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
Reconcile your bill
AI21 Labs doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.
Prices come from AI21 Labs's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.
Text 12 models
| Model | Input | Output | Cached input | Batch input | Context | Status |
|---|---|---|---|---|---|---|
| jamba-1.5 | $0.20 | $0.40 | — | — | 256K | |
| jamba-1.5-mini | $0.20 | $0.40 | — | — | 256K | |
| jamba-1.5-mini@001 | $0.20 | $0.40 | — | — | 256K | |
| jamba-mini-1.6 | $0.20 | $0.40 | — | — | 256K | |
| jamba-mini-1.7 | $0.20 | $0.40 | — | — | 256K | |
| jamba-1.5-large | $2.00 | $8.00 | — | — | 256K | |
| jamba-1.5-large@001 | $2.00 | $8.00 | — | — | 256K | |
| jamba-large-1.6 | $2.00 | $8.00 | — | — | 256K | |
| jamba-large-1.7 | $2.00 | $8.00 | — | — | 256K | |
| j2-light | $3.00 | $3.00 | — | — | 8.2K | |
| j2-mid | $10.00 | $10.00 | — | — | 8.2K | |
| j2-ultra | $15.00 | $15.00 | — | — | 8.2K |