Saba pricing and routing profile

Saba from Mistral AI lists at $0.20 per million input tokens and $0.60 per million output tokens, with a 32,768-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.20
Output, per 1M tokens$0.60
Cached input, per 1M$0.02
Context window33K
Confidence signalNot exposed

Tool callingStructured output

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.126
Chat reply (2,000 in, 400 out)$0.64
Retrieval-augmented answer (8,000 in, 500 out)$1.90

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Saba. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below Saba that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Qwen3 VL 30B A3B Instruct$0.15 / $0.6016%
gpt-oss-120b$0.15 / $0.6016%
GPT-4o-mini$0.15 / $0.6016%
GPT-4o-mini (2024-07-18)$0.15 / $0.6016%
GLM 5.3 Flash$0.15 / $0.5022%
Qwen3.8 Omni Flash$0.15 / $0.4724%

Questions

How much does Saba cost?

Saba lists at $0.20 per million input tokens and $0.60 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.64 per 1,000 requests.

What is the context window of Saba?

32,768 tokens.

Can a cheaper model replace Saba?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Saba on one half of your requests and make at most three answers worse on the other.