Mistral: Saba API Pricing
Mistral: Saba costs $0.200 per 1M input tokens and $0.600 per 1M output tokens (cache reads: $0.020). Context window: 33K. Prices verified 2026-10-21 · source
Alternatives to consider
89% cheaper with nearly identical quality (20.1 vs 6.5)
+45.5 quality points for 23% more
Cheapest mistralai model — 90% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
From our own daily snapshot archive — independent of provider announcements.
Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $0.200 | — |
| Cache read | $0.020 | −90% |
| Output | $0.600 | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
Training data ends here — newer events require retrieval or web search.
What would Mistral: Saba cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $4.00 |
| Coding agent | 5,000 | 8,000 / 2,000 | $14.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $33.00 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $9.20 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About Mistral: Saba
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
Compare Mistral: Saba with
- Mistral: Saba vs OpenAI: GPT-5.6 Terra Pro
- Mistral: Saba vs Anthropic: Claude Fable 5
- Mistral: Saba vs Anthropic: Claude Opus 5
- Mistral: Saba vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does Mistral: Saba cost?
Mistral: Saba costs $0.200 per 1M input tokens and $0.600 per 1M output tokens; cached input tokens cost $0.020 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
33K tokens, with up to 26K output tokens per response. That's roughly 41 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.020/1M, about 90% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
ScaleDown: Summarize saves about 91% on a typical workload with comparable quality.
Official resources
- Mistral: Saba on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- Mistral models → — first-party model specifications and limits.
- Shred your current bill — paste a CSV and see if switching saves money.