mistral-small-latest · Mistral AI
Budget generalist at $0.15/$0.60 for chat, classification and drafting.
Last checked Aug 16, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Note: Cached input 90% off; batch half price. Confirm the current rate at the official provider source.
Input
$0.15
per 1M tokens
Output
$0.60
per 1M tokens
Cached input
$0.015
per 1M tokens
Context window
131.1K
max output 32.8K
Mistral Small 4 cost calculator
What Mistral Small 4 costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.000404 | $12.128 |
| RAG / search-augmented answers | 8,000 | 500 | $0.00096 | $28.80 |
| AI coding assistant | 12,000 | 2,000 | $0.002028 | $60.84 |
| Document summarization | 25,000 | 600 | $0.003773 | $113.175 |
| Agentic workflow | 40,000 | 1,500 | $0.00339 | $101.70 |
| Content generation | 800 | 1,200 | $0.000808 | $24.228 |
| Data extraction & tagging | 2,000 | 250 | $0.000396 | $11.88 |
| Translation | 5,000 | 5,500 | $0.003949 | $118.462 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| Mistral Small 4 | $0.15 | $0.60 | 131.1K | $0.00081 |
| GPT-5.6 Luna | $0.20 | $1.20 | 1.1M | $0.0014 |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1M | $0.00054 |
| Ministral 3 (8B) | $0.15 | $0.15 | 131.1K | $0.00045 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
Mistral Small 4 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens, with cached input at $0.015 per 1M tokens. Verified Aug 16, 2026 against https://mistral.ai/pricing/api/.
Mistral Small 4 supports a 131,072-token context window with up to 32,768 output tokens per request, tokenized with Tekken (131K vocab).
At $0.15/M input and $0.60/M output, Mistral Small 4 sits below GPT-5.6 Luna ($0.20/M in, $1.20/M out) — see the comparison table for full-workload differences.