Skip to content
CostPerPrompt

Saba API Pricing

Mistral · context window 33K · prices updated 2026-08-02

Input per 1M tokens
$0.2
Output per 1M tokens
$0.6
Cached input per 1M
$0.02
90% cheaper than fresh input

What real workloads cost on Saba

Workload Per request Per month
1K short requests/day (500 in / 150 out) $0.0002 $5.70
Support chatbot, 500 convs/day (~5K in / 1.4K out per conv) $0.0018 $27.60
Document pipeline, 10K docs/day (3K in / 500 out) $0.0009 $270

Model your exact traffic in the API cost calculator — it preloads Saba with caching and batch options.

Cheaper alternatives

Mistral Small 3.1 24B Mistral $0.351 in · $0.555 out Qwen3 235B A22B Instruct 2507 Alibaba (Qwen) $0.09 in · $0.55 out Qwen3 VL 30B A3B Instruct Alibaba (Qwen) $0.13 in · $0.52 out

More Mistral models

Mistral Large 2407 Mixtral 8x22B Instruct Mistral Large Mistral Medium 3.5

Frequently asked questions

› How much does the Saba API cost?

Saba costs $0.2 per million input tokens and $0.6 per million output tokens, with cached input at $0.02 per million (90% cheaper). In practice, a typical short request (500 tokens in, 150 out) costs about $0.0002.

› What does 1,000 requests per day cost on Saba?

At 500 input + 150 output tokens per request, 1,000 requests/day costs about $5.70 per month. Heavier workloads scale linearly — use our API cost calculator to model your exact traffic.

› How can I reduce Saba costs?

Three levers, in order of impact: (1) route routine requests to a cheaper tier and keep Saba for hard cases; (2) enable prompt caching — cached input is 90% cheaper, which typically halves chatbot bills; (3) use the batch API for non-urgent jobs at a ~50% discount.

› Is Saba worth the price?

It depends on task difficulty. Flagship models earn their premium on complex reasoning, coding, and high-stakes output; mini/flash tiers handle classification, extraction and routine chat at 10–30× lower cost. Benchmark a sample of your real workload on both before committing.