Ministral 3 8B 2512
$0.15 per 1M input tokens and $0.15 per 1M output tokens · 262K context · vision, tools, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
Cheaper ways to run the same model: Ministral 3 8B 2512 (batch) at $0.075 / $0.075 — same model, different service (e.g. batch processing with a delay).
What Ministral 3 8B 2512 costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $37.44 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $13.41 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $21.15 |
| Content generation 30 long articles a day | $0.743 |
| Classification / extraction 100,000 short items a day | $142 |
Price history
We started tracking Ministral 3 8B 2512 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Ministral 3 8B 2512: 3 providers
Mistral is the cheapest at $0.15 input / $0.15 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
Cheaper alternatives to Ministral 3 8B 2512
Models with the same tool calling, image input, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.0 Flash VL inclusionAI | $0.06 | $0.18 | 131K | visiontoolsreasoningJSONopen weights |
| Qwen3.5-9B Qwen | $0.08 | $0.13 | 262K | visiontoolsreasoningJSONopen weights |
| Ministral 3 3B 2512 Mistral AI | $0.10 | $0.10 | 131K | visiontoolsJSONopen weights |
| Gemma 3 12B | $0.05 | $0.15 | 131K | visiontoolsJSONopen weights |
How to pay less for Ministral 3 8B 2512
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $66.60 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to GLM 5.3 Flash (similar capabilities) | $16.82 | $49.78 (75%) |
| Switch to Ministral 3 8B 2512 (batch) | $33.30 | $33.30 (50%) |
| Use prompt caching (60% of input cached) | $37.44 | $29.16 (44%) |
Other workloads: cut-your-bill tool for Ministral 3 8B 2512.
Specifications
| Model ID | mistralai/ministral-8b-2512 |
| Input | text, image |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | No |
| Open weights | Yes — mistralai/Ministral-3-8B-Instruct-2512 |
| Released | Dec 2, 2025 |
FAQ
- How much does Ministral 3 8B 2512 cost?
- $0.15 per million input tokens and $0.15 per million output tokens; cached input costs $0.015 per million. Prices as of Oct 21, 2026.
- What is the context window of Ministral 3 8B 2512?
- 262K tokens, with up to 210K output tokens per response.
- Does Ministral 3 8B 2512 support images, tools and structured output?
- Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: no.
- What are cheaper alternatives to Ministral 3 8B 2512?
- Models with the same key capabilities for at least 20% less include GLM 5.3 Flash ($0.041 / $0.12), Ling 3.0 Flash VL ($0.06 / $0.18), Qwen3.5-9B ($0.08 / $0.13).
More from Mistral AI: all Mistral AI models · how we collect prices