Ministral 3B
by NanoGPT · family ministral · listed Dec 2025W
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Current rates USD per 1M tokens
Input$0.10
Output$0.10
Cache read$0.01
Cache write—
Against the market
On the record
- Model id
mistralai/ministral-3b-2512- Context window
- 131K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-12-02
- Last updated
- 2025-12-02
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.10 in · $0.10 out
- DevPass (LLM Gateway)$0.10 in · $0.10 out
- Eden AI$0.10 in · $0.10 out
- OpenRouter$0.10 in · $0.10 out
- Mistral$0.10 in · $0.10 out
- LLM Gateway$0.10 in · $0.10 out
- LowRouter$0.105 in · $0.105 out
- Cortecs$0.123 in · $0.123 out
- AI/ML API$0.159 in · $0.159 out