How many AI models does AI21 serve?
1 tracked model as of 11 August 2026: 1 language model (1 with a public ModelCap Index position), across 1 live endpoint observed through OpenRouter.
Inference provider
AI21: AI models and API pricing
Every tracked model AI21 serves through OpenRouter, with AI21's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.
Snapshot as of 11 August 2026
AI21 serves 1 tracked model through 1 endpoint as of 11 August 2026; the highest-ranked is Jamba Large 1.7 (ModelCap Index #94).
Models served
1
On the ModelCap Index
1
Cheapest output price
$8.00/1M
Language models on AI21 (1)
Ranked models first, in ModelCap Index order. Prices are the lowest AI21 lists for the model; the endpoint count shows how many deployments carry it.
AI21 on ModelCap: common questions
What is the best model available on AI21?
Jamba Large 1.7 from AI21 Labs is the highest-ranked language model AI21 serves, at ModelCap Index position #94 and $8.00 per 1M output tokens on AI21. The table lists every model in Index order.
What is the cheapest model on AI21?
Jamba Large 1.7 at $8.00 per 1M output tokens ($2.00 per 1M input), the lowest positive language-token price AI21 lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.
Which AI21 model has the largest context window?
Jamba Large 1.7, served with a 256K-token context window on AI21. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
How reliable is AI21?
OpenRouter reports no uptime measurement for AI21 endpoints in the current snapshot.
Where do the AI21 prices come from?
From the OpenRouter catalogue entry for each AI21 endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where AI21 exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.
How current is this page?
It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.