ministral-3-latest-8b · Mistral AI
Edge-class 8B model with symmetric $0.15/$0.15 pricing — the flattest cost curve in the catalog.
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
$0.15
per 1M tokens
Cached input
$0.015
per 1M tokens
Context window
131.1K
max output 16.4K
Ministral 3 (8B) cost calculator
What Ministral 3 (8B) costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.000247 | $7.402 |
| RAG / search-augmented answers | 8,000 | 500 | $0.000735 | $22.05 |
| AI coding assistant | 12,000 | 2,000 | $0.001128 | $33.84 |
| Document summarization | 25,000 | 600 | $0.003503 | $105.075 |
| Agentic workflow | 40,000 | 1,500 | $0.002715 | $81.45 |
| Content generation | 800 | 1,200 | $0.000268 | $8.028 |
| Data extraction & tagging | 2,000 | 250 | $0.000284 | $8.505 |
| Translation | 5,000 | 5,500 | $0.001474 | $44.213 |
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* |
|---|---|---|---|---|
| Ministral 3 (8B) | $0.15 | $0.15 | 131.1K | $0.00045 |
| Gemini 2.5 Flash-Litecompare | $0.10 | $0.40 | 1M | $0.00054 |
| GPT-5.4 nano | $0.20 | $1.25 | 1.1M | $0.00144 |
| Mistral Small 4 | $0.15 | $0.60 | 131.1K | $0.00081 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
Ministral 3 (8B) costs $0.15 per 1M input tokens and $0.15 per 1M output tokens, with cached input at $0.015 per 1M tokens. Verified Aug 16, 2026 against https://mistral.ai/pricing/api/.
Ministral 3 (8B) supports a 131,072-token context window with up to 16,384 output tokens per request, tokenized with Tekken (131K vocab).
At $0.15/M input and $0.15/M output, Ministral 3 (8B) sits above Gemini 2.5 Flash-Lite ($0.10/M in, $0.40/M out) — see the comparison table for full-workload differences.