How is Saba priced?
Saba via OpenRouter is listed at $0.20 input and $0.60 output per million tokens. Multiply those rates by your own token volume. Deepapi does not convert them into a monthly subscription on this page.
OpenRouter · chat
Saba is a chat model associated with OpenRouter. Saba on this URL is the OpenRouter route (router), not a claim that OpenRouter created the weights. OpenRouter is the recorded vendor. Router and host prices can diverge from the creator's API, and availability can move even when the model name stays the same. The recorded context window is 32,768 tokens, with max output around 8,192 tokens. Saba is marked for tool and function calling. Speed tier: medium. Stored use cases: General.
Saba is listed at $0.20 per million input tokens and $0.60 per million output tokens (USD). That quote is the recorded API rate for this page's provider route, not a subscription seat and not a blended monthly bill. A short prompt and a long agent trace will not cost the same amount even when the sticker price stays put.
Recorded access points for Saba: OpenRouter (router, available).
How to use this Saba page: read the price as a per-million-token quote, then open the API price directory if you need other providers for the same family. Open a related model page when you are choosing between sizes or between the creator API and a router. Open the product page when the practical question is a consumer subscription (seat, credits, or included models) rather than metered API spend. Status on this record is available, with a stored release date of 2025-02-17.
| Platform | Access Type | Availability | Action |
|---|---|---|---|
| OpenRouter | router | available | Open(opens in new tab) |
Saba via OpenRouter is listed at $0.20 input and $0.60 output per million tokens. Multiply those rates by your own token volume. Deepapi does not convert them into a monthly subscription on this page.
OpenRouter: available, payment required.
Saba is a chat model from OpenRouter. Vision is not marked supported. Tool use is supported. Reasoning is not marked supported. Context window: 32,768 tokens. Compare sibling model pages before you pick a larger or smaller variant.