$0.20 / $0.60per 1M tokens in / out
$0.02cache read · −90%
#523on OpenRouter by tokens · 7M / week
Price sheetper 1M tokens
| Input | $0.20 | list |
| Output | $0.60 | |
| Cache read | $0.02 | −90% vs input |
| Context · max output | 33K · 26K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Mistrallab | $0.20 | $0.60 | 33K |
In Mistral's line-upper 1M in / out
| Mistral Moderation 2 ↗ | $0 / $0 | −100% |
| Mistral 7B Instruct v0.3 | $0.028 / $0.054 | −88% |
| Mistral 7B Instruct v0.1 | $0.055 / $0.055 | −82% |
| Mistral 7B Instruct v0.2 | $0.055 / $0.055 | −82% |
| Mistral Small 3 | $0.05 / $0.08 | −81% |
| Ministral 3 3B 2512 | $0.10 / $0.10 | −67% |
| Ministral 3 8B 2512 | $0.15 / $0.15 | −50% |
Cheaper for the same workvs Saba
| Claude Haiku 5.5 max | -33% | score ×6.7 | $0.21 |
| MiniMax M3.1 Flash thinking | -13% | score ×6.6 | $0.22 |
| GLM 5.3 Flash maxOpen | -21% | score ×6.4 | $0.28 |
| Qwen3.8 Flash thinkingOpen | -23% | score ×6.1 | $0.37 |
| GPT-6 Luna max | -33% | score ×5.9 | $0.068 |
Pricing questions
How much does Saba cost?›
$0.20 per 1M input tokens and $0.60 per 1M output tokens. Cached input is $0.02.
Is Saba free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.02 per 1M, 90% below the input price.
What is a cheaper alternative to Saba?›
Claude Haiku 5.5 at max effort costs -33% per task with a score ×6.7 on .