Models / AI21 Labs / Jamba Large

AI21 Labs · jamba

Jamba Large

AI21's hybrid SSM-Transformer long-context model for enterprise agents and grounded generation

$2.00 in · $8.00 out

per 1M tokens · first-party price. Reference price from AI21 Labs, the lab's own listing.

Context
256,000
Max output
4,096
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Yes
Vision
No
Open weights
Yes
License
—
Released
Jul 1, 2025
Updated in source
Jul 1, 2025
Knowledge
2024-08-22
Providers
1

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Jamba Large

$24.00

Cache hit is ignored because this model has no cache-read price.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
AI21 Labsreference$2.00$8.00———