AI21 Labs models & pricing

AI21 Labs hosts 12 models (12 with public pricing) covering 2 modalities. Jamba models — hybrid Mamba-Transformer with 256K context. Cheapest input starts at $0.200/M tokens; the most premium goes up to $15.00/M. Use Future AGI's Agent Command Center to route any AI21 Labs model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗

chat 9

Model Input / 1M Output / 1M Context Caps
Jamba 1.5 $0.200/M $0.400/M 256,000
Jamba 1.5 mini $0.200/M $0.400/M 256,000
Jamba 1.5 mini 001 $0.200/M $0.400/M 256,000
Jamba mini 1.6 $0.200/M $0.400/M 256,000
Jamba mini 1.7 $0.200/M $0.400/M 256,000
Jamba 1.5 Large $2.00/M $8.00/M 256,000
Jamba 1.5 Large 001 $2.00/M $8.00/M 256,000
Jamba Large 1.6 $2.00/M $8.00/M 256,000
Jamba Large 1.7 $2.00/M $8.00/M 256,000

completion 3

Model Input / 1M Output / 1M Context Caps
J2 Light $3.00/M $3.00/M 8,192
J2 Mid $10.00/M $10.00/M 8,192
J2 Ultra $15.00/M $15.00/M 8,192

FAQ

How many AI21 Labs models are there?

12 AI21 Labs models are listed across 2 modalities on this page. 12 have public per-token pricing.

How is AI21 Labs pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which AI21 Labs model is cheapest?

Input pricing on AI21 Labs starts at $0.200 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.

Can I route to AI21 Labs via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a AI21 Labs target, and call AI21 Labs models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any AI21 Labs model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.