Mistral
Ministral 3 8B 2512
Released 2025-12-02
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
You send / 1M
$0.150
tokens in
It replies / 1M
$0.150
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0003
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Mistral | $0.150 | $0.150 | 100% | Read |
| Mistral | $0.165 | $0.165 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 210K tokens
- Repeated text is billed at $0.015 per 1M (prompt caching)
- Intelligence score: 5.5 / 100 (Artificial Analysis)
Similar models
- Gemma 3 12BGoogle · $0.050 in / $0.150 out per 1M
- Llama Guard 4 12BMeta · $0.180 in / $0.180 out per 1M
- Ministral 3 14B 2512Mistral · $0.200 in / $0.200 out per 1M
- UI-TARS 7B Bytedance · $0.100 in / $0.200 out per 1M
- Mistral Small 3.2 24BMistral · $0.075 in / $0.200 out per 1M
- Reka EdgeRekaai · $0.100 in / $0.100 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Vision AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Vision AI ModelsTop No-Training Cheap Tool-Calling AI Models