---
title: "AI21 Labs API pricing per token: 2 models | BroadRouter"
description: "AI21 Labs API pricing per 1M tokens for 2 models, from USD 0.20 input, cheapest-host checks and maker price comparison."
url: https://broadrouter.com/llm-api-pricing/providers/ai21/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# AI21 Labs API pricing

Updated 2026-11-15

AI21 Labs lists standard per-token prices for 2 models. The cheapest is Jamba Mini 2 at USD 0.20 input and USD 0.40 output per 1M tokens; the dearest is Jamba Large 1.7 at USD 2 / USD 8. It publishes no cached-input prices, and lists no per-model batch, flex or priority prices on the pages we read. Checked 2026-11-15.

AI21 Labs is a model maker: 2 of the 2 models here are its own. By maker: AI21 Labs 2. 2 prices, each read from [AI21 Labs' own pricing page](https://www.ai21.com/pricing/), checked 2026-11-15. BroadRouter is BroadNet's own site and does not sell AI21 Labs' services. Automated re-check 2026-11-16: 2 of 2 prices still matched the provider's page. This page lists fewer than 3 models and fewer than 2 that other providers also price, so it is kept out of search results.

Models with a standard price

2

Median input / output

USD 1.10 / USD 4.20

Cached-input prices

0 of 2

Cheapest host for

0 of 0 shared models

## Which models is AI21 Labs the cheapest provider for?

No other provider in our data publishes a standard price for any model AI21 Labs prices, so there is nothing to rank against. All 2 models here are priced by AI21 Labs alone.

## AI21 Labs price list

USD per 1M tokens: 2 prices for 2 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-15 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means AI21 Labs is cheaper. AI21 Labs is the maker of every model here, so there is no maker price to compare with.

AI21 Labs API prices by model
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Jamba Large 1.7](https://broadrouter.com/llm-api-pricing/jamba-large-1.7/) | standard | USD 2 | — | USD 8 | 262,144 | own model | [source](https://www.ai21.com/pricing/) |
| [Jamba Mini 2](https://broadrouter.com/llm-api-pricing/jamba-mini-2/) | standard | USD 0.20 | — | USD 0.40 | 262,144 | own model | [source](https://www.ai21.com/pricing/) |

-   **Cached "—"** means AI21 Labs' page shows no cache price for that row; budget cached tokens at the input price.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20AI21%20Labs%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fproviders%2Fai21%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What service tiers does AI21 Labs publish?

Standard prices only: AI21 Labs publishes no per-model batch, flex, priority or fast price on the pages we read.

Cached input: no cache-read price is published, so repeated prompts bill at the full input price.

**What we recorded about AI21 Labs' pricing page:** Prices from ai21.com/pricing (AI21 platform, pay as you go). The page names "Jamba Mini" and "Jamba Large"; AI21 docs (docs.ai21.com/docs/jamba-foundation-models) say \`jamba-mini\` points to jamba-mini-2-2026-01 and \`jamba-large\` to jamba-large-1.7-2025-07, both 256K context. No cached or batch prices published.

## BroadNet Inference and AI21 Labs

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference serves none of the models AI21 Labs prices. [BroadNet Inference pricing](https://broadrouter.com/pricing/).

## More on AI21 Labs

-   [AI21 Labs' own pricing page](https://www.ai21.com/pricing/) (the source; checked 2026-11-15)
-   [All 41 providers compared](https://broadrouter.com/llm-api-pricing/providers/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [Download every price (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/)

## Questions

### How much does the AI21 Labs API cost per token?

AI21 Labs' standard prices run from USD 0.20 input and USD 0.40 output per 1M tokens (Jamba Mini 2) to USD 2 / USD 8 (Jamba Large 1.7). The median across 2 standard prices is USD 1.10 input and USD 4.20 output per 1M, which is USD 0.0000011 per input token. Input, cached input and output are billed separately.

### What is the cheapest model on AI21 Labs?

Jamba Mini 2, at USD 0.20 input and USD 0.40 output per 1M tokens (USD 0.25 on a 3:1 input-to-output blend).

### Is AI21 Labs cheaper than other providers?

None of the models AI21 Labs prices has a standard price from another provider in our data, so there is nothing to rank against yet. 2 models here are priced by AI21 Labs alone.

### Does AI21 Labs have batch, cached or priority pricing?

Cached input: no cached price is published on its pricing page, so budget repeated prompts at the input price. No batch, flex or priority prices are listed per model on the pages we read.

### How much does a chatbot cost per month on AI21 Labs?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 25.20 on Jamba Mini 2 and USD 324.00 on Jamba Large 1.7. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/).

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-providers-ai21&utm_content=page-cta) ·

**Sources**

-   [AI21 Labs: pricing page (checked 2026-11-15)](https://www.ai21.com/pricing/)
