Ministral 3 3B 2512
by Mistral · mistralai/ministral-3b-2512 · #36 cheapest of 422 paid models
Prices updated Sep 19, 2026, 10:45 PM UTC · refreshed hourly
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.10
per 1M tokens
Output
$0.10
per 1M tokens
Blended (3:1)
$0.10
3 input : 1 output
Cache read
$0.01
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Ministral 3 3B 2512 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.10 | $0.0103 | — |
| 50% | $0.066 | $0.0058 | −44% |
| 90% | $0.039 | $0.0022 | −79% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $8.00e-5 | $0.08 |
| Document summary | 8,000 | 1,000 | $0.0009 | $0.9 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0032 | $3.20 |
| Long-context analysis | 150,000 | 5,000 | $0.0155 | $15.50 |
Performance
Intelligence Index
4.8
AA composite quality
Coding Index
4.8
Math Index
—
Agentic Index
0.8
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,040 |
| 3D | 991 |
| Game dev | 972 |
| Code categories | 1,025 |
Specs
Context window
131K
tokens
Max output
105K
tokens
Input modalities
text, image
Tokenizer
Mistral