Mistral AI Text live-fetched
Ministral 3 8B 2512
Input$0.150per 1M tokens
Output$0.150per 1M tokens
- Context window
- 262,144 tokens
What that buys
- 1M words of output
- $0.20
- 100k-token chat, 80k in and 20k out
- $0.0150
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- openrouter
- Checked
- 2026-10-19
- Changes recorded
- 0
Where this price sits
620 text models priced per 1M tokensMinistral 3 8B 2512 is number 62 of 620 by price, from cheapest. The median is $2.00; Ministral 3 8B 2512 is 92% below the median. Among the 26 Mistral AI models in this group it is number 5 from cheapest.
Computed from the models on APITariff, checked 2026-10-19. Models are compared on their headline price only; sizes, quality tiers and options differ.
Price neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| Schematron V2 TurboInference Net | Inference Net | $0.150 | source |
| Qwen3.5-9BQwen | Qwen | $0.150 | source |
| gpt-oss-120bOpenAI | OpenAI | $0.170 | source |
Checked 2026-10-19
According to APITariff, Ministral 3 8B 2512 from Mistral AI costs $0.150 per 1M input tokens and $0.150 per 1M output tokens as of 2026-10-19.