RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Mistral: Ministral 3 3B 2512 API pricing

$0.10 per 1M input tokens and $0.10 per 1M output tokens on OpenRouter. Context window: 131,072 tokens.

$0.10input / 1M tokens
$0.10output / 1M tokens
$0.01cached input / 1M
128Kcontext
text+image->textmodality

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$1.90
RAG: 1,000 queries (8,000 in / 600 out each)$0.860
Summarize 100 long documents (50,000 in / 1,000 out each)$0.510

Cross-check against the provider's list price

LiteLLM's price map lists mistral/ministral-3b-2512 (mistral) at $0.10 in / $0.10 out per 1M tokens. Matches OpenRouter

Price history

No price change recorded since we started tracking on Nov 17, 2026. We check every 6 hours and log every change.

Cheaper alternatives with similar context

Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.

ModelInput / 1MOutput / 1MContext
Inference.net: Schematron V2 Small$0.05$0.23125K
PrismML: Ternary Bonsai 2 9B$0.08$0.13256K
inclusionAI: Ling 3.0 Flash VL$0.06$0.18128K
DeepSeek: DeepSeek V4 Flash 0731$0.06$0.181M
Upstage: Solar Mini 4$0.05$0.20512K
OpenAI: GPT-4.1 Nano (batch)$0.05$0.201023K
IBM: Granite 4.2 8B$0.06$0.15128K
Google: Gemma 3 12B$0.05$0.15128K

Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 18, 2026. Model ID mistralai/ministral-3b-2512, listed Dec 2, 2025. Report an error.